Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- checkpoint-1000/added_tokens.json +4 -0
- checkpoint-1000/config.json +27 -0
- checkpoint-1000/generation_config.json +6 -0
- checkpoint-1000/model.safetensors +3 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/rng_state.pth +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/special_tokens_map.json +24 -0
- checkpoint-1000/tokenizer.json +0 -0
- checkpoint-1000/tokenizer.model +3 -0
- checkpoint-1000/tokenizer_config.json +61 -0
- checkpoint-1000/trainer_state.json +1473 -0
- checkpoint-1000/training_args.bin +3 -0
- checkpoint-1500/added_tokens.json +4 -0
- checkpoint-1500/config.json +27 -0
- checkpoint-1500/generation_config.json +6 -0
- checkpoint-1500/model.safetensors +3 -0
- checkpoint-1500/optimizer.pt +3 -0
- checkpoint-1500/rng_state.pth +3 -0
- checkpoint-1500/scheduler.pt +3 -0
- checkpoint-1500/special_tokens_map.json +24 -0
- checkpoint-1500/tokenizer.json +0 -0
- checkpoint-1500/tokenizer.model +3 -0
- checkpoint-1500/tokenizer_config.json +61 -0
- checkpoint-1500/trainer_state.json +2189 -0
- checkpoint-1500/training_args.bin +3 -0
- checkpoint-2000/added_tokens.json +4 -0
- checkpoint-2000/config.json +27 -0
- checkpoint-2000/generation_config.json +6 -0
- checkpoint-2000/model.safetensors +3 -0
- checkpoint-2000/optimizer.pt +3 -0
- checkpoint-2000/rng_state.pth +3 -0
- checkpoint-2000/scheduler.pt +3 -0
- checkpoint-2000/special_tokens_map.json +24 -0
- checkpoint-2000/tokenizer.json +0 -0
- checkpoint-2000/tokenizer.model +3 -0
- checkpoint-2000/tokenizer_config.json +61 -0
- checkpoint-2000/trainer_state.json +2913 -0
- checkpoint-2000/training_args.bin +3 -0
- checkpoint-500/added_tokens.json +4 -0
- checkpoint-500/config.json +27 -0
- checkpoint-500/generation_config.json +6 -0
- checkpoint-500/model.safetensors +3 -0
- checkpoint-500/optimizer.pt +3 -0
- checkpoint-500/rng_state.pth +3 -0
- checkpoint-500/scheduler.pt +3 -0
- checkpoint-500/special_tokens_map.json +24 -0
- checkpoint-500/tokenizer.json +0 -0
- checkpoint-500/tokenizer.model +3 -0
- checkpoint-500/tokenizer_config.json +61 -0
checkpoint-1000/added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|im_end|>": 32000,
|
| 3 |
+
"<|im_start|>": 32001
|
| 4 |
+
}
|
checkpoint-1000/config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Felladrin/Minueza-32M-Chat",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MistralForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 32000,
|
| 9 |
+
"head_dim": 26,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 312,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 1092,
|
| 14 |
+
"max_position_embeddings": 2048,
|
| 15 |
+
"model_type": "mistral",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 10,
|
| 18 |
+
"num_key_value_heads": 4,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_theta": 10000.0,
|
| 21 |
+
"sliding_window": 1024,
|
| 22 |
+
"tie_word_embeddings": false,
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.48.1",
|
| 25 |
+
"use_cache": false,
|
| 26 |
+
"vocab_size": 32002
|
| 27 |
+
}
|
checkpoint-1000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 32000,
|
| 5 |
+
"transformers_version": "4.48.1"
|
| 6 |
+
}
|
checkpoint-1000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02563fdb17f2e6d99f27e3e09ff134d70ab636e0790c26fcfd0bdb41eb8eb72b
|
| 3 |
+
size 131181272
|
checkpoint-1000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18e4b35653ac0ef3b4691a5b8b02753852872f1c718997792735d5aa55ac1830
|
| 3 |
+
size 262419258
|
checkpoint-1000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c062f7f375beded48b5337f5a3f3a5cb38807fa3e85dbf3e294c0ab6b627bfc2
|
| 3 |
+
size 14244
|
checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:753b60ceb48341188690448f803646e87b0db50bdbf0da140937469ffbf4f610
|
| 3 |
+
size 1064
|
checkpoint-1000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|im_end|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|im_end|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
checkpoint-1000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1000/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
checkpoint-1000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "<|im_end|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"32001": {
|
| 39 |
+
"content": "<|im_start|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
}
|
| 46 |
+
},
|
| 47 |
+
"additional_special_tokens": [],
|
| 48 |
+
"bos_token": "<s>",
|
| 49 |
+
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 50 |
+
"clean_up_tokenization_spaces": false,
|
| 51 |
+
"eos_token": "<|im_end|>",
|
| 52 |
+
"extra_special_tokens": {},
|
| 53 |
+
"legacy": true,
|
| 54 |
+
"model_max_length": 2048,
|
| 55 |
+
"pad_token": "<|im_end|>",
|
| 56 |
+
"sp_model_kwargs": {},
|
| 57 |
+
"spaces_between_special_tokens": false,
|
| 58 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 59 |
+
"unk_token": "<unk>",
|
| 60 |
+
"use_default_system_prompt": false
|
| 61 |
+
}
|
checkpoint-1000/trainer_state.json
ADDED
|
@@ -0,0 +1,1473 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.2408187838651415,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 1000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0012040939193257074,
|
| 13 |
+
"grad_norm": 4.470886707305908,
|
| 14 |
+
"learning_rate": 1.9975915221579964e-05,
|
| 15 |
+
"loss": 2.6688,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.002408187838651415,
|
| 20 |
+
"grad_norm": 4.067092418670654,
|
| 21 |
+
"learning_rate": 1.9951830443159926e-05,
|
| 22 |
+
"loss": 2.2509,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.003612281757977122,
|
| 27 |
+
"grad_norm": 4.133108615875244,
|
| 28 |
+
"learning_rate": 1.9927745664739885e-05,
|
| 29 |
+
"loss": 2.3732,
|
| 30 |
+
"step": 15
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.00481637567730283,
|
| 34 |
+
"grad_norm": 3.4890763759613037,
|
| 35 |
+
"learning_rate": 1.9903660886319848e-05,
|
| 36 |
+
"loss": 2.3632,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.006020469596628537,
|
| 41 |
+
"grad_norm": 4.1045308113098145,
|
| 42 |
+
"learning_rate": 1.987957610789981e-05,
|
| 43 |
+
"loss": 2.5203,
|
| 44 |
+
"step": 25
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.007224563515954244,
|
| 48 |
+
"grad_norm": 4.26784086227417,
|
| 49 |
+
"learning_rate": 1.985549132947977e-05,
|
| 50 |
+
"loss": 2.3349,
|
| 51 |
+
"step": 30
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.008428657435279952,
|
| 55 |
+
"grad_norm": 4.144766330718994,
|
| 56 |
+
"learning_rate": 1.983140655105973e-05,
|
| 57 |
+
"loss": 2.4106,
|
| 58 |
+
"step": 35
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.00963275135460566,
|
| 62 |
+
"grad_norm": 3.9538934230804443,
|
| 63 |
+
"learning_rate": 1.9807321772639694e-05,
|
| 64 |
+
"loss": 2.3192,
|
| 65 |
+
"step": 40
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.010836845273931367,
|
| 69 |
+
"grad_norm": 3.9219865798950195,
|
| 70 |
+
"learning_rate": 1.9783236994219656e-05,
|
| 71 |
+
"loss": 2.2012,
|
| 72 |
+
"step": 45
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.012040939193257074,
|
| 76 |
+
"grad_norm": 3.391493797302246,
|
| 77 |
+
"learning_rate": 1.9759152215799615e-05,
|
| 78 |
+
"loss": 2.4064,
|
| 79 |
+
"step": 50
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.013245033112582781,
|
| 83 |
+
"grad_norm": 4.393350124359131,
|
| 84 |
+
"learning_rate": 1.9735067437379577e-05,
|
| 85 |
+
"loss": 2.1513,
|
| 86 |
+
"step": 55
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.014449127031908489,
|
| 90 |
+
"grad_norm": 3.6243207454681396,
|
| 91 |
+
"learning_rate": 1.971098265895954e-05,
|
| 92 |
+
"loss": 2.2788,
|
| 93 |
+
"step": 60
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.015653220951234198,
|
| 97 |
+
"grad_norm": 3.642468214035034,
|
| 98 |
+
"learning_rate": 1.9686897880539502e-05,
|
| 99 |
+
"loss": 2.2244,
|
| 100 |
+
"step": 65
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.016857314870559904,
|
| 104 |
+
"grad_norm": 4.0894670486450195,
|
| 105 |
+
"learning_rate": 1.966281310211946e-05,
|
| 106 |
+
"loss": 2.3622,
|
| 107 |
+
"step": 70
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.018061408789885613,
|
| 111 |
+
"grad_norm": 4.033819198608398,
|
| 112 |
+
"learning_rate": 1.9638728323699423e-05,
|
| 113 |
+
"loss": 2.3803,
|
| 114 |
+
"step": 75
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.01926550270921132,
|
| 118 |
+
"grad_norm": 3.535987138748169,
|
| 119 |
+
"learning_rate": 1.9614643545279385e-05,
|
| 120 |
+
"loss": 2.2161,
|
| 121 |
+
"step": 80
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.020469596628537028,
|
| 125 |
+
"grad_norm": 3.541868209838867,
|
| 126 |
+
"learning_rate": 1.9590558766859348e-05,
|
| 127 |
+
"loss": 2.1721,
|
| 128 |
+
"step": 85
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.021673690547862733,
|
| 132 |
+
"grad_norm": 4.147072792053223,
|
| 133 |
+
"learning_rate": 1.9566473988439307e-05,
|
| 134 |
+
"loss": 2.3239,
|
| 135 |
+
"step": 90
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.022877784467188442,
|
| 139 |
+
"grad_norm": 3.4949986934661865,
|
| 140 |
+
"learning_rate": 1.954238921001927e-05,
|
| 141 |
+
"loss": 2.265,
|
| 142 |
+
"step": 95
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.024081878386514148,
|
| 146 |
+
"grad_norm": 3.793950319290161,
|
| 147 |
+
"learning_rate": 1.951830443159923e-05,
|
| 148 |
+
"loss": 2.152,
|
| 149 |
+
"step": 100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.025285972305839857,
|
| 153 |
+
"grad_norm": 3.9355053901672363,
|
| 154 |
+
"learning_rate": 1.949421965317919e-05,
|
| 155 |
+
"loss": 2.2534,
|
| 156 |
+
"step": 105
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.026490066225165563,
|
| 160 |
+
"grad_norm": 3.255175828933716,
|
| 161 |
+
"learning_rate": 1.9470134874759156e-05,
|
| 162 |
+
"loss": 2.2971,
|
| 163 |
+
"step": 110
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.027694160144491272,
|
| 167 |
+
"grad_norm": 3.650298595428467,
|
| 168 |
+
"learning_rate": 1.9446050096339115e-05,
|
| 169 |
+
"loss": 2.1228,
|
| 170 |
+
"step": 115
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.028898254063816978,
|
| 174 |
+
"grad_norm": 3.1906814575195312,
|
| 175 |
+
"learning_rate": 1.9421965317919077e-05,
|
| 176 |
+
"loss": 2.0995,
|
| 177 |
+
"step": 120
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.030102347983142687,
|
| 181 |
+
"grad_norm": 3.8122494220733643,
|
| 182 |
+
"learning_rate": 1.939788053949904e-05,
|
| 183 |
+
"loss": 2.1651,
|
| 184 |
+
"step": 125
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.031306441902468396,
|
| 188 |
+
"grad_norm": 3.8269336223602295,
|
| 189 |
+
"learning_rate": 1.9373795761079e-05,
|
| 190 |
+
"loss": 2.1731,
|
| 191 |
+
"step": 130
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.0325105358217941,
|
| 195 |
+
"grad_norm": 3.75238037109375,
|
| 196 |
+
"learning_rate": 1.934971098265896e-05,
|
| 197 |
+
"loss": 2.3071,
|
| 198 |
+
"step": 135
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.03371462974111981,
|
| 202 |
+
"grad_norm": 3.538330078125,
|
| 203 |
+
"learning_rate": 1.9325626204238923e-05,
|
| 204 |
+
"loss": 2.3015,
|
| 205 |
+
"step": 140
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.034918723660445516,
|
| 209 |
+
"grad_norm": 3.497131586074829,
|
| 210 |
+
"learning_rate": 1.9301541425818882e-05,
|
| 211 |
+
"loss": 2.128,
|
| 212 |
+
"step": 145
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.036122817579771226,
|
| 216 |
+
"grad_norm": 3.6173276901245117,
|
| 217 |
+
"learning_rate": 1.9277456647398845e-05,
|
| 218 |
+
"loss": 2.1792,
|
| 219 |
+
"step": 150
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.03732691149909693,
|
| 223 |
+
"grad_norm": 3.2987892627716064,
|
| 224 |
+
"learning_rate": 1.9253371868978807e-05,
|
| 225 |
+
"loss": 2.0246,
|
| 226 |
+
"step": 155
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.03853100541842264,
|
| 230 |
+
"grad_norm": 3.1787831783294678,
|
| 231 |
+
"learning_rate": 1.922928709055877e-05,
|
| 232 |
+
"loss": 2.2108,
|
| 233 |
+
"step": 160
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.039735099337748346,
|
| 237 |
+
"grad_norm": 3.5422236919403076,
|
| 238 |
+
"learning_rate": 1.920520231213873e-05,
|
| 239 |
+
"loss": 2.1738,
|
| 240 |
+
"step": 165
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.040939193257074055,
|
| 244 |
+
"grad_norm": 3.7987539768218994,
|
| 245 |
+
"learning_rate": 1.918111753371869e-05,
|
| 246 |
+
"loss": 2.1161,
|
| 247 |
+
"step": 170
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.04214328717639976,
|
| 251 |
+
"grad_norm": 3.2058522701263428,
|
| 252 |
+
"learning_rate": 1.9157032755298653e-05,
|
| 253 |
+
"loss": 2.0808,
|
| 254 |
+
"step": 175
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.04334738109572547,
|
| 258 |
+
"grad_norm": 3.00519061088562,
|
| 259 |
+
"learning_rate": 1.9132947976878615e-05,
|
| 260 |
+
"loss": 2.1412,
|
| 261 |
+
"step": 180
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.044551475015051176,
|
| 265 |
+
"grad_norm": 3.4471330642700195,
|
| 266 |
+
"learning_rate": 1.9108863198458578e-05,
|
| 267 |
+
"loss": 2.1695,
|
| 268 |
+
"step": 185
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.045755568934376885,
|
| 272 |
+
"grad_norm": 3.394496440887451,
|
| 273 |
+
"learning_rate": 1.9084778420038536e-05,
|
| 274 |
+
"loss": 1.9532,
|
| 275 |
+
"step": 190
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.04695966285370259,
|
| 279 |
+
"grad_norm": 3.03004789352417,
|
| 280 |
+
"learning_rate": 1.90606936416185e-05,
|
| 281 |
+
"loss": 2.0659,
|
| 282 |
+
"step": 195
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.048163756773028296,
|
| 286 |
+
"grad_norm": 3.4260365962982178,
|
| 287 |
+
"learning_rate": 1.903660886319846e-05,
|
| 288 |
+
"loss": 2.0792,
|
| 289 |
+
"step": 200
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.048163756773028296,
|
| 293 |
+
"eval_loss": 2.1430513858795166,
|
| 294 |
+
"eval_runtime": 16.4051,
|
| 295 |
+
"eval_samples_per_second": 6.096,
|
| 296 |
+
"eval_steps_per_second": 0.792,
|
| 297 |
+
"step": 200
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.049367850692354005,
|
| 301 |
+
"grad_norm": 4.670680999755859,
|
| 302 |
+
"learning_rate": 1.901252408477842e-05,
|
| 303 |
+
"loss": 2.0952,
|
| 304 |
+
"step": 205
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.050571944611679714,
|
| 308 |
+
"grad_norm": 3.510042667388916,
|
| 309 |
+
"learning_rate": 1.8988439306358382e-05,
|
| 310 |
+
"loss": 2.195,
|
| 311 |
+
"step": 210
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.05177603853100542,
|
| 315 |
+
"grad_norm": 3.0459847450256348,
|
| 316 |
+
"learning_rate": 1.8964354527938345e-05,
|
| 317 |
+
"loss": 2.2117,
|
| 318 |
+
"step": 215
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.052980132450331126,
|
| 322 |
+
"grad_norm": 4.36016321182251,
|
| 323 |
+
"learning_rate": 1.8940269749518304e-05,
|
| 324 |
+
"loss": 2.1191,
|
| 325 |
+
"step": 220
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.054184226369656835,
|
| 329 |
+
"grad_norm": 3.0498242378234863,
|
| 330 |
+
"learning_rate": 1.891618497109827e-05,
|
| 331 |
+
"loss": 2.0838,
|
| 332 |
+
"step": 225
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.055388320288982544,
|
| 336 |
+
"grad_norm": 3.218038558959961,
|
| 337 |
+
"learning_rate": 1.889210019267823e-05,
|
| 338 |
+
"loss": 2.1118,
|
| 339 |
+
"step": 230
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.056592414208308246,
|
| 343 |
+
"grad_norm": 3.3144683837890625,
|
| 344 |
+
"learning_rate": 1.886801541425819e-05,
|
| 345 |
+
"loss": 2.2176,
|
| 346 |
+
"step": 235
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.057796508127633955,
|
| 350 |
+
"grad_norm": 3.2364652156829834,
|
| 351 |
+
"learning_rate": 1.8843930635838153e-05,
|
| 352 |
+
"loss": 2.112,
|
| 353 |
+
"step": 240
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.059000602046959665,
|
| 357 |
+
"grad_norm": 3.291278839111328,
|
| 358 |
+
"learning_rate": 1.8819845857418112e-05,
|
| 359 |
+
"loss": 2.144,
|
| 360 |
+
"step": 245
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.060204695966285374,
|
| 364 |
+
"grad_norm": 3.65297794342041,
|
| 365 |
+
"learning_rate": 1.8795761078998074e-05,
|
| 366 |
+
"loss": 2.2597,
|
| 367 |
+
"step": 250
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.061408789885611076,
|
| 371 |
+
"grad_norm": 3.2321982383728027,
|
| 372 |
+
"learning_rate": 1.8771676300578037e-05,
|
| 373 |
+
"loss": 2.1618,
|
| 374 |
+
"step": 255
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.06261288380493679,
|
| 378 |
+
"grad_norm": 3.352842330932617,
|
| 379 |
+
"learning_rate": 1.8747591522158e-05,
|
| 380 |
+
"loss": 2.006,
|
| 381 |
+
"step": 260
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.0638169777242625,
|
| 385 |
+
"grad_norm": 3.5657215118408203,
|
| 386 |
+
"learning_rate": 1.8723506743737958e-05,
|
| 387 |
+
"loss": 2.2253,
|
| 388 |
+
"step": 265
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.0650210716435882,
|
| 392 |
+
"grad_norm": 3.060060739517212,
|
| 393 |
+
"learning_rate": 1.869942196531792e-05,
|
| 394 |
+
"loss": 2.1187,
|
| 395 |
+
"step": 270
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.06622516556291391,
|
| 399 |
+
"grad_norm": 3.473719835281372,
|
| 400 |
+
"learning_rate": 1.8675337186897883e-05,
|
| 401 |
+
"loss": 2.0299,
|
| 402 |
+
"step": 275
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.06742925948223961,
|
| 406 |
+
"grad_norm": 3.1167919635772705,
|
| 407 |
+
"learning_rate": 1.8651252408477845e-05,
|
| 408 |
+
"loss": 2.0381,
|
| 409 |
+
"step": 280
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.06863335340156532,
|
| 413 |
+
"grad_norm": 3.815816640853882,
|
| 414 |
+
"learning_rate": 1.8627167630057804e-05,
|
| 415 |
+
"loss": 2.1624,
|
| 416 |
+
"step": 285
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.06983744732089103,
|
| 420 |
+
"grad_norm": 3.2820959091186523,
|
| 421 |
+
"learning_rate": 1.8603082851637766e-05,
|
| 422 |
+
"loss": 2.0819,
|
| 423 |
+
"step": 290
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.07104154124021674,
|
| 427 |
+
"grad_norm": 3.568885087966919,
|
| 428 |
+
"learning_rate": 1.857899807321773e-05,
|
| 429 |
+
"loss": 2.0749,
|
| 430 |
+
"step": 295
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.07224563515954245,
|
| 434 |
+
"grad_norm": 3.424076795578003,
|
| 435 |
+
"learning_rate": 1.855491329479769e-05,
|
| 436 |
+
"loss": 2.129,
|
| 437 |
+
"step": 300
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.07344972907886815,
|
| 441 |
+
"grad_norm": 3.2800493240356445,
|
| 442 |
+
"learning_rate": 1.853082851637765e-05,
|
| 443 |
+
"loss": 2.2067,
|
| 444 |
+
"step": 305
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.07465382299819386,
|
| 448 |
+
"grad_norm": 3.487868547439575,
|
| 449 |
+
"learning_rate": 1.8506743737957612e-05,
|
| 450 |
+
"loss": 2.124,
|
| 451 |
+
"step": 310
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.07585791691751957,
|
| 455 |
+
"grad_norm": 3.3999245166778564,
|
| 456 |
+
"learning_rate": 1.8482658959537575e-05,
|
| 457 |
+
"loss": 1.9888,
|
| 458 |
+
"step": 315
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.07706201083684527,
|
| 462 |
+
"grad_norm": 3.973482370376587,
|
| 463 |
+
"learning_rate": 1.8458574181117533e-05,
|
| 464 |
+
"loss": 2.0592,
|
| 465 |
+
"step": 320
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.07826610475617098,
|
| 469 |
+
"grad_norm": 2.9601657390594482,
|
| 470 |
+
"learning_rate": 1.8434489402697496e-05,
|
| 471 |
+
"loss": 2.1022,
|
| 472 |
+
"step": 325
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.07947019867549669,
|
| 476 |
+
"grad_norm": 3.260118246078491,
|
| 477 |
+
"learning_rate": 1.8410404624277458e-05,
|
| 478 |
+
"loss": 1.9763,
|
| 479 |
+
"step": 330
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.0806742925948224,
|
| 483 |
+
"grad_norm": 3.509838819503784,
|
| 484 |
+
"learning_rate": 1.838631984585742e-05,
|
| 485 |
+
"loss": 2.0284,
|
| 486 |
+
"step": 335
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.08187838651414811,
|
| 490 |
+
"grad_norm": 4.363494396209717,
|
| 491 |
+
"learning_rate": 1.8362235067437383e-05,
|
| 492 |
+
"loss": 2.0479,
|
| 493 |
+
"step": 340
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.08308248043347381,
|
| 497 |
+
"grad_norm": 3.2578630447387695,
|
| 498 |
+
"learning_rate": 1.8338150289017342e-05,
|
| 499 |
+
"loss": 2.0488,
|
| 500 |
+
"step": 345
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.08428657435279951,
|
| 504 |
+
"grad_norm": 3.2846531867980957,
|
| 505 |
+
"learning_rate": 1.8314065510597304e-05,
|
| 506 |
+
"loss": 2.0876,
|
| 507 |
+
"step": 350
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.08549066827212523,
|
| 511 |
+
"grad_norm": 3.3275203704833984,
|
| 512 |
+
"learning_rate": 1.8289980732177266e-05,
|
| 513 |
+
"loss": 2.0564,
|
| 514 |
+
"step": 355
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.08669476219145093,
|
| 518 |
+
"grad_norm": 3.1368625164031982,
|
| 519 |
+
"learning_rate": 1.8265895953757225e-05,
|
| 520 |
+
"loss": 2.1533,
|
| 521 |
+
"step": 360
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.08789885611077664,
|
| 525 |
+
"grad_norm": 3.3824191093444824,
|
| 526 |
+
"learning_rate": 1.8241811175337188e-05,
|
| 527 |
+
"loss": 2.1821,
|
| 528 |
+
"step": 365
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.08910295003010235,
|
| 532 |
+
"grad_norm": 3.5150134563446045,
|
| 533 |
+
"learning_rate": 1.821772639691715e-05,
|
| 534 |
+
"loss": 2.0292,
|
| 535 |
+
"step": 370
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.09030704394942805,
|
| 539 |
+
"grad_norm": 3.421921730041504,
|
| 540 |
+
"learning_rate": 1.8193641618497112e-05,
|
| 541 |
+
"loss": 1.9862,
|
| 542 |
+
"step": 375
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.09151113786875377,
|
| 546 |
+
"grad_norm": 3.616887092590332,
|
| 547 |
+
"learning_rate": 1.8169556840077075e-05,
|
| 548 |
+
"loss": 2.0158,
|
| 549 |
+
"step": 380
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.09271523178807947,
|
| 553 |
+
"grad_norm": 5.063056945800781,
|
| 554 |
+
"learning_rate": 1.8145472061657034e-05,
|
| 555 |
+
"loss": 2.0579,
|
| 556 |
+
"step": 385
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.09391932570740517,
|
| 560 |
+
"grad_norm": 3.5242559909820557,
|
| 561 |
+
"learning_rate": 1.8121387283236996e-05,
|
| 562 |
+
"loss": 2.0272,
|
| 563 |
+
"step": 390
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.09512341962673089,
|
| 567 |
+
"grad_norm": 3.2852962017059326,
|
| 568 |
+
"learning_rate": 1.809730250481696e-05,
|
| 569 |
+
"loss": 2.077,
|
| 570 |
+
"step": 395
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.09632751354605659,
|
| 574 |
+
"grad_norm": 3.710927963256836,
|
| 575 |
+
"learning_rate": 1.8073217726396917e-05,
|
| 576 |
+
"loss": 2.1271,
|
| 577 |
+
"step": 400
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.09632751354605659,
|
| 581 |
+
"eval_loss": 2.0655810832977295,
|
| 582 |
+
"eval_runtime": 16.3755,
|
| 583 |
+
"eval_samples_per_second": 6.107,
|
| 584 |
+
"eval_steps_per_second": 0.794,
|
| 585 |
+
"step": 400
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.0975316074653823,
|
| 589 |
+
"grad_norm": 3.5019216537475586,
|
| 590 |
+
"learning_rate": 1.804913294797688e-05,
|
| 591 |
+
"loss": 2.1081,
|
| 592 |
+
"step": 405
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.09873570138470801,
|
| 596 |
+
"grad_norm": 3.5533690452575684,
|
| 597 |
+
"learning_rate": 1.8025048169556842e-05,
|
| 598 |
+
"loss": 2.0751,
|
| 599 |
+
"step": 410
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.09993979530403371,
|
| 603 |
+
"grad_norm": 3.4970240592956543,
|
| 604 |
+
"learning_rate": 1.8000963391136804e-05,
|
| 605 |
+
"loss": 2.066,
|
| 606 |
+
"step": 415
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.10114388922335943,
|
| 610 |
+
"grad_norm": 3.0926427841186523,
|
| 611 |
+
"learning_rate": 1.7976878612716763e-05,
|
| 612 |
+
"loss": 2.0516,
|
| 613 |
+
"step": 420
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.10234798314268513,
|
| 617 |
+
"grad_norm": 3.747452974319458,
|
| 618 |
+
"learning_rate": 1.7952793834296726e-05,
|
| 619 |
+
"loss": 2.0721,
|
| 620 |
+
"step": 425
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.10355207706201083,
|
| 624 |
+
"grad_norm": 3.3113677501678467,
|
| 625 |
+
"learning_rate": 1.7928709055876688e-05,
|
| 626 |
+
"loss": 2.1527,
|
| 627 |
+
"step": 430
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.10475617098133655,
|
| 631 |
+
"grad_norm": 3.357912063598633,
|
| 632 |
+
"learning_rate": 1.7904624277456647e-05,
|
| 633 |
+
"loss": 2.0113,
|
| 634 |
+
"step": 435
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.10596026490066225,
|
| 638 |
+
"grad_norm": 3.023893356323242,
|
| 639 |
+
"learning_rate": 1.7880539499036613e-05,
|
| 640 |
+
"loss": 2.1332,
|
| 641 |
+
"step": 440
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.10716435881998795,
|
| 645 |
+
"grad_norm": 3.3027355670928955,
|
| 646 |
+
"learning_rate": 1.785645472061657e-05,
|
| 647 |
+
"loss": 1.9699,
|
| 648 |
+
"step": 445
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.10836845273931367,
|
| 652 |
+
"grad_norm": 5.3524932861328125,
|
| 653 |
+
"learning_rate": 1.7832369942196534e-05,
|
| 654 |
+
"loss": 2.0182,
|
| 655 |
+
"step": 450
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.10957254665863937,
|
| 659 |
+
"grad_norm": 3.200258731842041,
|
| 660 |
+
"learning_rate": 1.7808285163776496e-05,
|
| 661 |
+
"loss": 2.007,
|
| 662 |
+
"step": 455
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.11077664057796509,
|
| 666 |
+
"grad_norm": 3.286268949508667,
|
| 667 |
+
"learning_rate": 1.7784200385356455e-05,
|
| 668 |
+
"loss": 2.0907,
|
| 669 |
+
"step": 460
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.11198073449729079,
|
| 673 |
+
"grad_norm": 3.15291428565979,
|
| 674 |
+
"learning_rate": 1.7760115606936417e-05,
|
| 675 |
+
"loss": 2.0468,
|
| 676 |
+
"step": 465
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.11318482841661649,
|
| 680 |
+
"grad_norm": 3.3798069953918457,
|
| 681 |
+
"learning_rate": 1.773603082851638e-05,
|
| 682 |
+
"loss": 1.9927,
|
| 683 |
+
"step": 470
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.11438892233594221,
|
| 687 |
+
"grad_norm": 3.4220967292785645,
|
| 688 |
+
"learning_rate": 1.771194605009634e-05,
|
| 689 |
+
"loss": 2.1326,
|
| 690 |
+
"step": 475
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.11559301625526791,
|
| 694 |
+
"grad_norm": 3.379628896713257,
|
| 695 |
+
"learning_rate": 1.76878612716763e-05,
|
| 696 |
+
"loss": 1.9202,
|
| 697 |
+
"step": 480
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.11679711017459361,
|
| 701 |
+
"grad_norm": 3.3020846843719482,
|
| 702 |
+
"learning_rate": 1.7663776493256263e-05,
|
| 703 |
+
"loss": 2.1176,
|
| 704 |
+
"step": 485
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.11800120409391933,
|
| 708 |
+
"grad_norm": 3.2711665630340576,
|
| 709 |
+
"learning_rate": 1.7639691714836226e-05,
|
| 710 |
+
"loss": 2.0865,
|
| 711 |
+
"step": 490
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.11920529801324503,
|
| 715 |
+
"grad_norm": 3.239253520965576,
|
| 716 |
+
"learning_rate": 1.7615606936416188e-05,
|
| 717 |
+
"loss": 1.9284,
|
| 718 |
+
"step": 495
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.12040939193257075,
|
| 722 |
+
"grad_norm": 3.4960460662841797,
|
| 723 |
+
"learning_rate": 1.7591522157996147e-05,
|
| 724 |
+
"loss": 2.0088,
|
| 725 |
+
"step": 500
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.12161348585189645,
|
| 729 |
+
"grad_norm": 3.337407350540161,
|
| 730 |
+
"learning_rate": 1.756743737957611e-05,
|
| 731 |
+
"loss": 1.9687,
|
| 732 |
+
"step": 505
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.12281757977122215,
|
| 736 |
+
"grad_norm": 3.534827709197998,
|
| 737 |
+
"learning_rate": 1.754335260115607e-05,
|
| 738 |
+
"loss": 2.0273,
|
| 739 |
+
"step": 510
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 0.12402167369054787,
|
| 743 |
+
"grad_norm": 3.6207938194274902,
|
| 744 |
+
"learning_rate": 1.7519267822736034e-05,
|
| 745 |
+
"loss": 2.0458,
|
| 746 |
+
"step": 515
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.12522576760987358,
|
| 750 |
+
"grad_norm": 3.396012544631958,
|
| 751 |
+
"learning_rate": 1.7495183044315993e-05,
|
| 752 |
+
"loss": 1.9185,
|
| 753 |
+
"step": 520
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.12642986152919927,
|
| 757 |
+
"grad_norm": 3.001236915588379,
|
| 758 |
+
"learning_rate": 1.7471098265895955e-05,
|
| 759 |
+
"loss": 1.9407,
|
| 760 |
+
"step": 525
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.127633955448525,
|
| 764 |
+
"grad_norm": 3.1318376064300537,
|
| 765 |
+
"learning_rate": 1.7447013487475918e-05,
|
| 766 |
+
"loss": 1.8984,
|
| 767 |
+
"step": 530
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.1288380493678507,
|
| 771 |
+
"grad_norm": 3.4541585445404053,
|
| 772 |
+
"learning_rate": 1.7422928709055877e-05,
|
| 773 |
+
"loss": 1.8846,
|
| 774 |
+
"step": 535
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.1300421432871764,
|
| 778 |
+
"grad_norm": 3.311082363128662,
|
| 779 |
+
"learning_rate": 1.739884393063584e-05,
|
| 780 |
+
"loss": 2.0015,
|
| 781 |
+
"step": 540
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 0.1312462372065021,
|
| 785 |
+
"grad_norm": 3.2366561889648438,
|
| 786 |
+
"learning_rate": 1.73747591522158e-05,
|
| 787 |
+
"loss": 2.0176,
|
| 788 |
+
"step": 545
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.13245033112582782,
|
| 792 |
+
"grad_norm": 3.123307943344116,
|
| 793 |
+
"learning_rate": 1.735067437379576e-05,
|
| 794 |
+
"loss": 1.9731,
|
| 795 |
+
"step": 550
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.1336544250451535,
|
| 799 |
+
"grad_norm": 3.776921033859253,
|
| 800 |
+
"learning_rate": 1.7326589595375726e-05,
|
| 801 |
+
"loss": 2.0484,
|
| 802 |
+
"step": 555
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.13485851896447923,
|
| 806 |
+
"grad_norm": 2.959716796875,
|
| 807 |
+
"learning_rate": 1.7302504816955685e-05,
|
| 808 |
+
"loss": 1.9689,
|
| 809 |
+
"step": 560
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.13606261288380495,
|
| 813 |
+
"grad_norm": 3.527384042739868,
|
| 814 |
+
"learning_rate": 1.7278420038535647e-05,
|
| 815 |
+
"loss": 1.9488,
|
| 816 |
+
"step": 565
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 0.13726670680313063,
|
| 820 |
+
"grad_norm": 3.0703189373016357,
|
| 821 |
+
"learning_rate": 1.725433526011561e-05,
|
| 822 |
+
"loss": 2.1226,
|
| 823 |
+
"step": 570
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 0.13847080072245635,
|
| 827 |
+
"grad_norm": 3.1028363704681396,
|
| 828 |
+
"learning_rate": 1.723025048169557e-05,
|
| 829 |
+
"loss": 1.8966,
|
| 830 |
+
"step": 575
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.13967489464178207,
|
| 834 |
+
"grad_norm": 3.340517044067383,
|
| 835 |
+
"learning_rate": 1.720616570327553e-05,
|
| 836 |
+
"loss": 2.2156,
|
| 837 |
+
"step": 580
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.14087898856110775,
|
| 841 |
+
"grad_norm": 3.2740213871002197,
|
| 842 |
+
"learning_rate": 1.7182080924855493e-05,
|
| 843 |
+
"loss": 1.9445,
|
| 844 |
+
"step": 585
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 0.14208308248043347,
|
| 848 |
+
"grad_norm": 3.240690231323242,
|
| 849 |
+
"learning_rate": 1.7157996146435455e-05,
|
| 850 |
+
"loss": 2.0295,
|
| 851 |
+
"step": 590
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 0.1432871763997592,
|
| 855 |
+
"grad_norm": 3.821340799331665,
|
| 856 |
+
"learning_rate": 1.7133911368015418e-05,
|
| 857 |
+
"loss": 2.1401,
|
| 858 |
+
"step": 595
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.1444912703190849,
|
| 862 |
+
"grad_norm": 3.103550910949707,
|
| 863 |
+
"learning_rate": 1.7109826589595377e-05,
|
| 864 |
+
"loss": 2.1164,
|
| 865 |
+
"step": 600
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.1444912703190849,
|
| 869 |
+
"eval_loss": 2.017059564590454,
|
| 870 |
+
"eval_runtime": 16.4324,
|
| 871 |
+
"eval_samples_per_second": 6.086,
|
| 872 |
+
"eval_steps_per_second": 0.791,
|
| 873 |
+
"step": 600
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.1456953642384106,
|
| 877 |
+
"grad_norm": 3.4971117973327637,
|
| 878 |
+
"learning_rate": 1.708574181117534e-05,
|
| 879 |
+
"loss": 1.9864,
|
| 880 |
+
"step": 605
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.1468994581577363,
|
| 884 |
+
"grad_norm": 3.324803590774536,
|
| 885 |
+
"learning_rate": 1.70616570327553e-05,
|
| 886 |
+
"loss": 2.0402,
|
| 887 |
+
"step": 610
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.14810355207706202,
|
| 891 |
+
"grad_norm": 3.302614450454712,
|
| 892 |
+
"learning_rate": 1.703757225433526e-05,
|
| 893 |
+
"loss": 1.9494,
|
| 894 |
+
"step": 615
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.1493076459963877,
|
| 898 |
+
"grad_norm": 3.3090734481811523,
|
| 899 |
+
"learning_rate": 1.7013487475915223e-05,
|
| 900 |
+
"loss": 2.0748,
|
| 901 |
+
"step": 620
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.15051173991571343,
|
| 905 |
+
"grad_norm": 3.559049129486084,
|
| 906 |
+
"learning_rate": 1.6989402697495185e-05,
|
| 907 |
+
"loss": 1.9038,
|
| 908 |
+
"step": 625
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.15171583383503914,
|
| 912 |
+
"grad_norm": 3.5149178504943848,
|
| 913 |
+
"learning_rate": 1.6965317919075147e-05,
|
| 914 |
+
"loss": 2.0261,
|
| 915 |
+
"step": 630
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.15291992775436483,
|
| 919 |
+
"grad_norm": 3.835693120956421,
|
| 920 |
+
"learning_rate": 1.6941233140655106e-05,
|
| 921 |
+
"loss": 1.9453,
|
| 922 |
+
"step": 635
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.15412402167369055,
|
| 926 |
+
"grad_norm": 3.521132469177246,
|
| 927 |
+
"learning_rate": 1.691714836223507e-05,
|
| 928 |
+
"loss": 2.0138,
|
| 929 |
+
"step": 640
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.15532811559301626,
|
| 933 |
+
"grad_norm": 3.2369840145111084,
|
| 934 |
+
"learning_rate": 1.689306358381503e-05,
|
| 935 |
+
"loss": 2.0285,
|
| 936 |
+
"step": 645
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.15653220951234195,
|
| 940 |
+
"grad_norm": 3.1592392921447754,
|
| 941 |
+
"learning_rate": 1.686897880539499e-05,
|
| 942 |
+
"loss": 1.9912,
|
| 943 |
+
"step": 650
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.15773630343166767,
|
| 947 |
+
"grad_norm": 3.2069106101989746,
|
| 948 |
+
"learning_rate": 1.6844894026974952e-05,
|
| 949 |
+
"loss": 2.0159,
|
| 950 |
+
"step": 655
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.15894039735099338,
|
| 954 |
+
"grad_norm": 3.318230390548706,
|
| 955 |
+
"learning_rate": 1.6820809248554915e-05,
|
| 956 |
+
"loss": 2.0412,
|
| 957 |
+
"step": 660
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.16014449127031907,
|
| 961 |
+
"grad_norm": 3.549443244934082,
|
| 962 |
+
"learning_rate": 1.6796724470134877e-05,
|
| 963 |
+
"loss": 2.0014,
|
| 964 |
+
"step": 665
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.1613485851896448,
|
| 968 |
+
"grad_norm": 3.32999324798584,
|
| 969 |
+
"learning_rate": 1.677263969171484e-05,
|
| 970 |
+
"loss": 2.0303,
|
| 971 |
+
"step": 670
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.1625526791089705,
|
| 975 |
+
"grad_norm": 3.262946367263794,
|
| 976 |
+
"learning_rate": 1.6748554913294798e-05,
|
| 977 |
+
"loss": 1.9883,
|
| 978 |
+
"step": 675
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.16375677302829622,
|
| 982 |
+
"grad_norm": 3.484685182571411,
|
| 983 |
+
"learning_rate": 1.672447013487476e-05,
|
| 984 |
+
"loss": 1.9695,
|
| 985 |
+
"step": 680
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.1649608669476219,
|
| 989 |
+
"grad_norm": 3.4177358150482178,
|
| 990 |
+
"learning_rate": 1.6700385356454723e-05,
|
| 991 |
+
"loss": 2.0088,
|
| 992 |
+
"step": 685
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.16616496086694763,
|
| 996 |
+
"grad_norm": 3.447498321533203,
|
| 997 |
+
"learning_rate": 1.6676300578034682e-05,
|
| 998 |
+
"loss": 2.0813,
|
| 999 |
+
"step": 690
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.16736905478627334,
|
| 1003 |
+
"grad_norm": 3.152740240097046,
|
| 1004 |
+
"learning_rate": 1.6652215799614644e-05,
|
| 1005 |
+
"loss": 1.9988,
|
| 1006 |
+
"step": 695
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.16857314870559903,
|
| 1010 |
+
"grad_norm": 3.8948824405670166,
|
| 1011 |
+
"learning_rate": 1.6628131021194607e-05,
|
| 1012 |
+
"loss": 2.0801,
|
| 1013 |
+
"step": 700
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.16977724262492475,
|
| 1017 |
+
"grad_norm": 3.81358003616333,
|
| 1018 |
+
"learning_rate": 1.660404624277457e-05,
|
| 1019 |
+
"loss": 1.944,
|
| 1020 |
+
"step": 705
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.17098133654425046,
|
| 1024 |
+
"grad_norm": 2.980236053466797,
|
| 1025 |
+
"learning_rate": 1.657996146435453e-05,
|
| 1026 |
+
"loss": 1.9151,
|
| 1027 |
+
"step": 710
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.17218543046357615,
|
| 1031 |
+
"grad_norm": 3.041680335998535,
|
| 1032 |
+
"learning_rate": 1.655587668593449e-05,
|
| 1033 |
+
"loss": 1.9486,
|
| 1034 |
+
"step": 715
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.17338952438290187,
|
| 1038 |
+
"grad_norm": 2.898974657058716,
|
| 1039 |
+
"learning_rate": 1.6531791907514452e-05,
|
| 1040 |
+
"loss": 2.1119,
|
| 1041 |
+
"step": 720
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.17459361830222758,
|
| 1045 |
+
"grad_norm": 3.161224603652954,
|
| 1046 |
+
"learning_rate": 1.6507707129094415e-05,
|
| 1047 |
+
"loss": 2.036,
|
| 1048 |
+
"step": 725
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.17579771222155327,
|
| 1052 |
+
"grad_norm": 3.2449426651000977,
|
| 1053 |
+
"learning_rate": 1.6483622350674374e-05,
|
| 1054 |
+
"loss": 2.0635,
|
| 1055 |
+
"step": 730
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.177001806140879,
|
| 1059 |
+
"grad_norm": 3.2805328369140625,
|
| 1060 |
+
"learning_rate": 1.6459537572254336e-05,
|
| 1061 |
+
"loss": 1.8022,
|
| 1062 |
+
"step": 735
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.1782059000602047,
|
| 1066 |
+
"grad_norm": 3.491149663925171,
|
| 1067 |
+
"learning_rate": 1.64354527938343e-05,
|
| 1068 |
+
"loss": 1.9832,
|
| 1069 |
+
"step": 740
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.1794099939795304,
|
| 1073 |
+
"grad_norm": 3.423267126083374,
|
| 1074 |
+
"learning_rate": 1.641136801541426e-05,
|
| 1075 |
+
"loss": 1.9574,
|
| 1076 |
+
"step": 745
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.1806140878988561,
|
| 1080 |
+
"grad_norm": 3.1914217472076416,
|
| 1081 |
+
"learning_rate": 1.638728323699422e-05,
|
| 1082 |
+
"loss": 1.9283,
|
| 1083 |
+
"step": 750
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.18181818181818182,
|
| 1087 |
+
"grad_norm": 3.2903149127960205,
|
| 1088 |
+
"learning_rate": 1.6363198458574182e-05,
|
| 1089 |
+
"loss": 2.1174,
|
| 1090 |
+
"step": 755
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 0.18302227573750754,
|
| 1094 |
+
"grad_norm": 3.113159656524658,
|
| 1095 |
+
"learning_rate": 1.6339113680154144e-05,
|
| 1096 |
+
"loss": 1.8794,
|
| 1097 |
+
"step": 760
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 0.18422636965683323,
|
| 1101 |
+
"grad_norm": 3.261596918106079,
|
| 1102 |
+
"learning_rate": 1.6315028901734103e-05,
|
| 1103 |
+
"loss": 2.0853,
|
| 1104 |
+
"step": 765
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 0.18543046357615894,
|
| 1108 |
+
"grad_norm": 2.9525296688079834,
|
| 1109 |
+
"learning_rate": 1.629094412331407e-05,
|
| 1110 |
+
"loss": 1.8622,
|
| 1111 |
+
"step": 770
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 0.18663455749548466,
|
| 1115 |
+
"grad_norm": 3.2103638648986816,
|
| 1116 |
+
"learning_rate": 1.6266859344894028e-05,
|
| 1117 |
+
"loss": 2.0536,
|
| 1118 |
+
"step": 775
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 0.18783865141481035,
|
| 1122 |
+
"grad_norm": 3.5312676429748535,
|
| 1123 |
+
"learning_rate": 1.624277456647399e-05,
|
| 1124 |
+
"loss": 1.9387,
|
| 1125 |
+
"step": 780
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.18904274533413606,
|
| 1129 |
+
"grad_norm": 3.277223825454712,
|
| 1130 |
+
"learning_rate": 1.6218689788053953e-05,
|
| 1131 |
+
"loss": 1.9804,
|
| 1132 |
+
"step": 785
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 0.19024683925346178,
|
| 1136 |
+
"grad_norm": 3.207287549972534,
|
| 1137 |
+
"learning_rate": 1.619460500963391e-05,
|
| 1138 |
+
"loss": 1.8782,
|
| 1139 |
+
"step": 790
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 0.19145093317278747,
|
| 1143 |
+
"grad_norm": 3.401834487915039,
|
| 1144 |
+
"learning_rate": 1.6170520231213874e-05,
|
| 1145 |
+
"loss": 1.9383,
|
| 1146 |
+
"step": 795
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 0.19265502709211318,
|
| 1150 |
+
"grad_norm": 3.5186078548431396,
|
| 1151 |
+
"learning_rate": 1.6146435452793836e-05,
|
| 1152 |
+
"loss": 2.0963,
|
| 1153 |
+
"step": 800
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 0.19265502709211318,
|
| 1157 |
+
"eval_loss": 1.979533076286316,
|
| 1158 |
+
"eval_runtime": 16.4348,
|
| 1159 |
+
"eval_samples_per_second": 6.085,
|
| 1160 |
+
"eval_steps_per_second": 0.791,
|
| 1161 |
+
"step": 800
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.1938591210114389,
|
| 1165 |
+
"grad_norm": 3.0080161094665527,
|
| 1166 |
+
"learning_rate": 1.6122350674373795e-05,
|
| 1167 |
+
"loss": 1.951,
|
| 1168 |
+
"step": 805
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.1950632149307646,
|
| 1172 |
+
"grad_norm": 3.124155044555664,
|
| 1173 |
+
"learning_rate": 1.6098265895953758e-05,
|
| 1174 |
+
"loss": 1.8663,
|
| 1175 |
+
"step": 810
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.1962673088500903,
|
| 1179 |
+
"grad_norm": 3.6262383460998535,
|
| 1180 |
+
"learning_rate": 1.607418111753372e-05,
|
| 1181 |
+
"loss": 1.9478,
|
| 1182 |
+
"step": 815
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.19747140276941602,
|
| 1186 |
+
"grad_norm": 3.3047947883605957,
|
| 1187 |
+
"learning_rate": 1.6050096339113682e-05,
|
| 1188 |
+
"loss": 1.9203,
|
| 1189 |
+
"step": 820
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.1986754966887417,
|
| 1193 |
+
"grad_norm": 3.0261447429656982,
|
| 1194 |
+
"learning_rate": 1.6026011560693645e-05,
|
| 1195 |
+
"loss": 1.8988,
|
| 1196 |
+
"step": 825
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.19987959060806743,
|
| 1200 |
+
"grad_norm": 4.233884334564209,
|
| 1201 |
+
"learning_rate": 1.6001926782273604e-05,
|
| 1202 |
+
"loss": 2.0327,
|
| 1203 |
+
"step": 830
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.20108368452739314,
|
| 1207 |
+
"grad_norm": 2.9169118404388428,
|
| 1208 |
+
"learning_rate": 1.5977842003853566e-05,
|
| 1209 |
+
"loss": 1.9264,
|
| 1210 |
+
"step": 835
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.20228777844671886,
|
| 1214 |
+
"grad_norm": 3.0078282356262207,
|
| 1215 |
+
"learning_rate": 1.5953757225433528e-05,
|
| 1216 |
+
"loss": 1.8821,
|
| 1217 |
+
"step": 840
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.20349187236604455,
|
| 1221 |
+
"grad_norm": 3.4188835620880127,
|
| 1222 |
+
"learning_rate": 1.592967244701349e-05,
|
| 1223 |
+
"loss": 1.933,
|
| 1224 |
+
"step": 845
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.20469596628537026,
|
| 1228 |
+
"grad_norm": 4.739987850189209,
|
| 1229 |
+
"learning_rate": 1.590558766859345e-05,
|
| 1230 |
+
"loss": 1.9182,
|
| 1231 |
+
"step": 850
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.20590006020469598,
|
| 1235 |
+
"grad_norm": 3.1810977458953857,
|
| 1236 |
+
"learning_rate": 1.5881502890173412e-05,
|
| 1237 |
+
"loss": 1.984,
|
| 1238 |
+
"step": 855
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.20710415412402167,
|
| 1242 |
+
"grad_norm": 3.174739360809326,
|
| 1243 |
+
"learning_rate": 1.5857418111753374e-05,
|
| 1244 |
+
"loss": 1.7719,
|
| 1245 |
+
"step": 860
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.20830824804334738,
|
| 1249 |
+
"grad_norm": 3.379767656326294,
|
| 1250 |
+
"learning_rate": 1.5833333333333333e-05,
|
| 1251 |
+
"loss": 1.9481,
|
| 1252 |
+
"step": 865
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.2095123419626731,
|
| 1256 |
+
"grad_norm": 3.3487260341644287,
|
| 1257 |
+
"learning_rate": 1.5809248554913295e-05,
|
| 1258 |
+
"loss": 1.9416,
|
| 1259 |
+
"step": 870
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.2107164358819988,
|
| 1263 |
+
"grad_norm": 3.4879958629608154,
|
| 1264 |
+
"learning_rate": 1.5785163776493258e-05,
|
| 1265 |
+
"loss": 2.0463,
|
| 1266 |
+
"step": 875
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.2119205298013245,
|
| 1270 |
+
"grad_norm": 3.2338194847106934,
|
| 1271 |
+
"learning_rate": 1.5761078998073217e-05,
|
| 1272 |
+
"loss": 1.9441,
|
| 1273 |
+
"step": 880
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.21312462372065022,
|
| 1277 |
+
"grad_norm": 3.122405529022217,
|
| 1278 |
+
"learning_rate": 1.5736994219653182e-05,
|
| 1279 |
+
"loss": 2.0644,
|
| 1280 |
+
"step": 885
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.2143287176399759,
|
| 1284 |
+
"grad_norm": 3.0773510932922363,
|
| 1285 |
+
"learning_rate": 1.571290944123314e-05,
|
| 1286 |
+
"loss": 1.9415,
|
| 1287 |
+
"step": 890
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.21553281155930162,
|
| 1291 |
+
"grad_norm": 3.004040241241455,
|
| 1292 |
+
"learning_rate": 1.5688824662813104e-05,
|
| 1293 |
+
"loss": 1.9305,
|
| 1294 |
+
"step": 895
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.21673690547862734,
|
| 1298 |
+
"grad_norm": 3.547109603881836,
|
| 1299 |
+
"learning_rate": 1.5664739884393066e-05,
|
| 1300 |
+
"loss": 2.1088,
|
| 1301 |
+
"step": 900
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.21794099939795303,
|
| 1305 |
+
"grad_norm": 3.1982204914093018,
|
| 1306 |
+
"learning_rate": 1.5640655105973025e-05,
|
| 1307 |
+
"loss": 1.8667,
|
| 1308 |
+
"step": 905
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.21914509331727874,
|
| 1312 |
+
"grad_norm": 3.381781578063965,
|
| 1313 |
+
"learning_rate": 1.5616570327552987e-05,
|
| 1314 |
+
"loss": 1.9783,
|
| 1315 |
+
"step": 910
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.22034918723660446,
|
| 1319 |
+
"grad_norm": 2.9775896072387695,
|
| 1320 |
+
"learning_rate": 1.559248554913295e-05,
|
| 1321 |
+
"loss": 2.0211,
|
| 1322 |
+
"step": 915
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.22155328115593018,
|
| 1326 |
+
"grad_norm": 2.864551067352295,
|
| 1327 |
+
"learning_rate": 1.5568400770712912e-05,
|
| 1328 |
+
"loss": 1.8579,
|
| 1329 |
+
"step": 920
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.22275737507525586,
|
| 1333 |
+
"grad_norm": 3.0532050132751465,
|
| 1334 |
+
"learning_rate": 1.5544315992292874e-05,
|
| 1335 |
+
"loss": 1.9398,
|
| 1336 |
+
"step": 925
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.22396146899458158,
|
| 1340 |
+
"grad_norm": 2.859631061553955,
|
| 1341 |
+
"learning_rate": 1.5520231213872833e-05,
|
| 1342 |
+
"loss": 1.8625,
|
| 1343 |
+
"step": 930
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.2251655629139073,
|
| 1347 |
+
"grad_norm": 3.1373536586761475,
|
| 1348 |
+
"learning_rate": 1.5496146435452796e-05,
|
| 1349 |
+
"loss": 1.9003,
|
| 1350 |
+
"step": 935
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.22636965683323299,
|
| 1354 |
+
"grad_norm": 3.3248465061187744,
|
| 1355 |
+
"learning_rate": 1.5472061657032758e-05,
|
| 1356 |
+
"loss": 2.0517,
|
| 1357 |
+
"step": 940
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.2275737507525587,
|
| 1361 |
+
"grad_norm": 3.5990936756134033,
|
| 1362 |
+
"learning_rate": 1.5447976878612717e-05,
|
| 1363 |
+
"loss": 1.8975,
|
| 1364 |
+
"step": 945
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.22877784467188442,
|
| 1368 |
+
"grad_norm": 3.4047725200653076,
|
| 1369 |
+
"learning_rate": 1.542389210019268e-05,
|
| 1370 |
+
"loss": 1.9786,
|
| 1371 |
+
"step": 950
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.2299819385912101,
|
| 1375 |
+
"grad_norm": 3.3326022624969482,
|
| 1376 |
+
"learning_rate": 1.539980732177264e-05,
|
| 1377 |
+
"loss": 1.7848,
|
| 1378 |
+
"step": 955
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.23118603251053582,
|
| 1382 |
+
"grad_norm": 3.2942848205566406,
|
| 1383 |
+
"learning_rate": 1.5375722543352604e-05,
|
| 1384 |
+
"loss": 1.8549,
|
| 1385 |
+
"step": 960
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.23239012642986154,
|
| 1389 |
+
"grad_norm": 3.4602601528167725,
|
| 1390 |
+
"learning_rate": 1.5351637764932563e-05,
|
| 1391 |
+
"loss": 1.917,
|
| 1392 |
+
"step": 965
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.23359422034918723,
|
| 1396 |
+
"grad_norm": 3.591327428817749,
|
| 1397 |
+
"learning_rate": 1.5327552986512525e-05,
|
| 1398 |
+
"loss": 1.9457,
|
| 1399 |
+
"step": 970
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.23479831426851294,
|
| 1403 |
+
"grad_norm": 3.215808868408203,
|
| 1404 |
+
"learning_rate": 1.5303468208092487e-05,
|
| 1405 |
+
"loss": 1.9261,
|
| 1406 |
+
"step": 975
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.23600240818783866,
|
| 1410 |
+
"grad_norm": 3.5032927989959717,
|
| 1411 |
+
"learning_rate": 1.5279383429672446e-05,
|
| 1412 |
+
"loss": 1.967,
|
| 1413 |
+
"step": 980
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.23720650210716435,
|
| 1417 |
+
"grad_norm": 3.1476144790649414,
|
| 1418 |
+
"learning_rate": 1.525529865125241e-05,
|
| 1419 |
+
"loss": 2.0448,
|
| 1420 |
+
"step": 985
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.23841059602649006,
|
| 1424 |
+
"grad_norm": 3.046126365661621,
|
| 1425 |
+
"learning_rate": 1.5231213872832371e-05,
|
| 1426 |
+
"loss": 1.9086,
|
| 1427 |
+
"step": 990
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.23961468994581578,
|
| 1431 |
+
"grad_norm": 3.0403099060058594,
|
| 1432 |
+
"learning_rate": 1.5207129094412332e-05,
|
| 1433 |
+
"loss": 1.9671,
|
| 1434 |
+
"step": 995
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.2408187838651415,
|
| 1438 |
+
"grad_norm": 3.524573802947998,
|
| 1439 |
+
"learning_rate": 1.5183044315992294e-05,
|
| 1440 |
+
"loss": 1.9532,
|
| 1441 |
+
"step": 1000
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.2408187838651415,
|
| 1445 |
+
"eval_loss": 1.9571956396102905,
|
| 1446 |
+
"eval_runtime": 16.4441,
|
| 1447 |
+
"eval_samples_per_second": 6.081,
|
| 1448 |
+
"eval_steps_per_second": 0.791,
|
| 1449 |
+
"step": 1000
|
| 1450 |
+
}
|
| 1451 |
+
],
|
| 1452 |
+
"logging_steps": 5,
|
| 1453 |
+
"max_steps": 4152,
|
| 1454 |
+
"num_input_tokens_seen": 0,
|
| 1455 |
+
"num_train_epochs": 1,
|
| 1456 |
+
"save_steps": 500,
|
| 1457 |
+
"stateful_callbacks": {
|
| 1458 |
+
"TrainerControl": {
|
| 1459 |
+
"args": {
|
| 1460 |
+
"should_epoch_stop": false,
|
| 1461 |
+
"should_evaluate": false,
|
| 1462 |
+
"should_log": false,
|
| 1463 |
+
"should_save": true,
|
| 1464 |
+
"should_training_stop": false
|
| 1465 |
+
},
|
| 1466 |
+
"attributes": {}
|
| 1467 |
+
}
|
| 1468 |
+
},
|
| 1469 |
+
"total_flos": 1054167504365664.0,
|
| 1470 |
+
"train_batch_size": 1,
|
| 1471 |
+
"trial_name": null,
|
| 1472 |
+
"trial_params": null
|
| 1473 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd020aa9333054ccbd44f2f69522647a4bdda52101c5b015e38e78115982722b
|
| 3 |
+
size 5816
|
checkpoint-1500/added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|im_end|>": 32000,
|
| 3 |
+
"<|im_start|>": 32001
|
| 4 |
+
}
|
checkpoint-1500/config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Felladrin/Minueza-32M-Chat",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MistralForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 32000,
|
| 9 |
+
"head_dim": 26,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 312,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 1092,
|
| 14 |
+
"max_position_embeddings": 2048,
|
| 15 |
+
"model_type": "mistral",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 10,
|
| 18 |
+
"num_key_value_heads": 4,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_theta": 10000.0,
|
| 21 |
+
"sliding_window": 1024,
|
| 22 |
+
"tie_word_embeddings": false,
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.48.1",
|
| 25 |
+
"use_cache": false,
|
| 26 |
+
"vocab_size": 32002
|
| 27 |
+
}
|
checkpoint-1500/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 32000,
|
| 5 |
+
"transformers_version": "4.48.1"
|
| 6 |
+
}
|
checkpoint-1500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae77a3b4589ed3c32499d8a9282916075fcf1985a4e586bdbb041ebba8d7ad6c
|
| 3 |
+
size 131181272
|
checkpoint-1500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a57335810720a4f9d8d5a04bebec0887838484b90101b756da32e3ef233f22a8
|
| 3 |
+
size 262419258
|
checkpoint-1500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9899ccda7f0d8d9511991180b93aab508ce6e8489de708c88ad1188e7e1d90d6
|
| 3 |
+
size 14244
|
checkpoint-1500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7acaaba5bf80cb5d5e1a88c4be3ebca794cd4bacb62bf046245137790e9a740
|
| 3 |
+
size 1064
|
checkpoint-1500/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|im_end|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|im_end|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
checkpoint-1500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1500/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
checkpoint-1500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "<|im_end|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"32001": {
|
| 39 |
+
"content": "<|im_start|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
}
|
| 46 |
+
},
|
| 47 |
+
"additional_special_tokens": [],
|
| 48 |
+
"bos_token": "<s>",
|
| 49 |
+
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 50 |
+
"clean_up_tokenization_spaces": false,
|
| 51 |
+
"eos_token": "<|im_end|>",
|
| 52 |
+
"extra_special_tokens": {},
|
| 53 |
+
"legacy": true,
|
| 54 |
+
"model_max_length": 2048,
|
| 55 |
+
"pad_token": "<|im_end|>",
|
| 56 |
+
"sp_model_kwargs": {},
|
| 57 |
+
"spaces_between_special_tokens": false,
|
| 58 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 59 |
+
"unk_token": "<unk>",
|
| 60 |
+
"use_default_system_prompt": false
|
| 61 |
+
}
|
checkpoint-1500/trainer_state.json
ADDED
|
@@ -0,0 +1,2189 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.3612281757977122,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 1500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0012040939193257074,
|
| 13 |
+
"grad_norm": 4.470886707305908,
|
| 14 |
+
"learning_rate": 1.9975915221579964e-05,
|
| 15 |
+
"loss": 2.6688,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.002408187838651415,
|
| 20 |
+
"grad_norm": 4.067092418670654,
|
| 21 |
+
"learning_rate": 1.9951830443159926e-05,
|
| 22 |
+
"loss": 2.2509,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.003612281757977122,
|
| 27 |
+
"grad_norm": 4.133108615875244,
|
| 28 |
+
"learning_rate": 1.9927745664739885e-05,
|
| 29 |
+
"loss": 2.3732,
|
| 30 |
+
"step": 15
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.00481637567730283,
|
| 34 |
+
"grad_norm": 3.4890763759613037,
|
| 35 |
+
"learning_rate": 1.9903660886319848e-05,
|
| 36 |
+
"loss": 2.3632,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.006020469596628537,
|
| 41 |
+
"grad_norm": 4.1045308113098145,
|
| 42 |
+
"learning_rate": 1.987957610789981e-05,
|
| 43 |
+
"loss": 2.5203,
|
| 44 |
+
"step": 25
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.007224563515954244,
|
| 48 |
+
"grad_norm": 4.26784086227417,
|
| 49 |
+
"learning_rate": 1.985549132947977e-05,
|
| 50 |
+
"loss": 2.3349,
|
| 51 |
+
"step": 30
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.008428657435279952,
|
| 55 |
+
"grad_norm": 4.144766330718994,
|
| 56 |
+
"learning_rate": 1.983140655105973e-05,
|
| 57 |
+
"loss": 2.4106,
|
| 58 |
+
"step": 35
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.00963275135460566,
|
| 62 |
+
"grad_norm": 3.9538934230804443,
|
| 63 |
+
"learning_rate": 1.9807321772639694e-05,
|
| 64 |
+
"loss": 2.3192,
|
| 65 |
+
"step": 40
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.010836845273931367,
|
| 69 |
+
"grad_norm": 3.9219865798950195,
|
| 70 |
+
"learning_rate": 1.9783236994219656e-05,
|
| 71 |
+
"loss": 2.2012,
|
| 72 |
+
"step": 45
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.012040939193257074,
|
| 76 |
+
"grad_norm": 3.391493797302246,
|
| 77 |
+
"learning_rate": 1.9759152215799615e-05,
|
| 78 |
+
"loss": 2.4064,
|
| 79 |
+
"step": 50
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.013245033112582781,
|
| 83 |
+
"grad_norm": 4.393350124359131,
|
| 84 |
+
"learning_rate": 1.9735067437379577e-05,
|
| 85 |
+
"loss": 2.1513,
|
| 86 |
+
"step": 55
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.014449127031908489,
|
| 90 |
+
"grad_norm": 3.6243207454681396,
|
| 91 |
+
"learning_rate": 1.971098265895954e-05,
|
| 92 |
+
"loss": 2.2788,
|
| 93 |
+
"step": 60
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.015653220951234198,
|
| 97 |
+
"grad_norm": 3.642468214035034,
|
| 98 |
+
"learning_rate": 1.9686897880539502e-05,
|
| 99 |
+
"loss": 2.2244,
|
| 100 |
+
"step": 65
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.016857314870559904,
|
| 104 |
+
"grad_norm": 4.0894670486450195,
|
| 105 |
+
"learning_rate": 1.966281310211946e-05,
|
| 106 |
+
"loss": 2.3622,
|
| 107 |
+
"step": 70
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.018061408789885613,
|
| 111 |
+
"grad_norm": 4.033819198608398,
|
| 112 |
+
"learning_rate": 1.9638728323699423e-05,
|
| 113 |
+
"loss": 2.3803,
|
| 114 |
+
"step": 75
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.01926550270921132,
|
| 118 |
+
"grad_norm": 3.535987138748169,
|
| 119 |
+
"learning_rate": 1.9614643545279385e-05,
|
| 120 |
+
"loss": 2.2161,
|
| 121 |
+
"step": 80
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.020469596628537028,
|
| 125 |
+
"grad_norm": 3.541868209838867,
|
| 126 |
+
"learning_rate": 1.9590558766859348e-05,
|
| 127 |
+
"loss": 2.1721,
|
| 128 |
+
"step": 85
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.021673690547862733,
|
| 132 |
+
"grad_norm": 4.147072792053223,
|
| 133 |
+
"learning_rate": 1.9566473988439307e-05,
|
| 134 |
+
"loss": 2.3239,
|
| 135 |
+
"step": 90
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.022877784467188442,
|
| 139 |
+
"grad_norm": 3.4949986934661865,
|
| 140 |
+
"learning_rate": 1.954238921001927e-05,
|
| 141 |
+
"loss": 2.265,
|
| 142 |
+
"step": 95
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.024081878386514148,
|
| 146 |
+
"grad_norm": 3.793950319290161,
|
| 147 |
+
"learning_rate": 1.951830443159923e-05,
|
| 148 |
+
"loss": 2.152,
|
| 149 |
+
"step": 100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.025285972305839857,
|
| 153 |
+
"grad_norm": 3.9355053901672363,
|
| 154 |
+
"learning_rate": 1.949421965317919e-05,
|
| 155 |
+
"loss": 2.2534,
|
| 156 |
+
"step": 105
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.026490066225165563,
|
| 160 |
+
"grad_norm": 3.255175828933716,
|
| 161 |
+
"learning_rate": 1.9470134874759156e-05,
|
| 162 |
+
"loss": 2.2971,
|
| 163 |
+
"step": 110
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.027694160144491272,
|
| 167 |
+
"grad_norm": 3.650298595428467,
|
| 168 |
+
"learning_rate": 1.9446050096339115e-05,
|
| 169 |
+
"loss": 2.1228,
|
| 170 |
+
"step": 115
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.028898254063816978,
|
| 174 |
+
"grad_norm": 3.1906814575195312,
|
| 175 |
+
"learning_rate": 1.9421965317919077e-05,
|
| 176 |
+
"loss": 2.0995,
|
| 177 |
+
"step": 120
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.030102347983142687,
|
| 181 |
+
"grad_norm": 3.8122494220733643,
|
| 182 |
+
"learning_rate": 1.939788053949904e-05,
|
| 183 |
+
"loss": 2.1651,
|
| 184 |
+
"step": 125
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.031306441902468396,
|
| 188 |
+
"grad_norm": 3.8269336223602295,
|
| 189 |
+
"learning_rate": 1.9373795761079e-05,
|
| 190 |
+
"loss": 2.1731,
|
| 191 |
+
"step": 130
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.0325105358217941,
|
| 195 |
+
"grad_norm": 3.75238037109375,
|
| 196 |
+
"learning_rate": 1.934971098265896e-05,
|
| 197 |
+
"loss": 2.3071,
|
| 198 |
+
"step": 135
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.03371462974111981,
|
| 202 |
+
"grad_norm": 3.538330078125,
|
| 203 |
+
"learning_rate": 1.9325626204238923e-05,
|
| 204 |
+
"loss": 2.3015,
|
| 205 |
+
"step": 140
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.034918723660445516,
|
| 209 |
+
"grad_norm": 3.497131586074829,
|
| 210 |
+
"learning_rate": 1.9301541425818882e-05,
|
| 211 |
+
"loss": 2.128,
|
| 212 |
+
"step": 145
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.036122817579771226,
|
| 216 |
+
"grad_norm": 3.6173276901245117,
|
| 217 |
+
"learning_rate": 1.9277456647398845e-05,
|
| 218 |
+
"loss": 2.1792,
|
| 219 |
+
"step": 150
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.03732691149909693,
|
| 223 |
+
"grad_norm": 3.2987892627716064,
|
| 224 |
+
"learning_rate": 1.9253371868978807e-05,
|
| 225 |
+
"loss": 2.0246,
|
| 226 |
+
"step": 155
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.03853100541842264,
|
| 230 |
+
"grad_norm": 3.1787831783294678,
|
| 231 |
+
"learning_rate": 1.922928709055877e-05,
|
| 232 |
+
"loss": 2.2108,
|
| 233 |
+
"step": 160
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.039735099337748346,
|
| 237 |
+
"grad_norm": 3.5422236919403076,
|
| 238 |
+
"learning_rate": 1.920520231213873e-05,
|
| 239 |
+
"loss": 2.1738,
|
| 240 |
+
"step": 165
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.040939193257074055,
|
| 244 |
+
"grad_norm": 3.7987539768218994,
|
| 245 |
+
"learning_rate": 1.918111753371869e-05,
|
| 246 |
+
"loss": 2.1161,
|
| 247 |
+
"step": 170
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.04214328717639976,
|
| 251 |
+
"grad_norm": 3.2058522701263428,
|
| 252 |
+
"learning_rate": 1.9157032755298653e-05,
|
| 253 |
+
"loss": 2.0808,
|
| 254 |
+
"step": 175
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.04334738109572547,
|
| 258 |
+
"grad_norm": 3.00519061088562,
|
| 259 |
+
"learning_rate": 1.9132947976878615e-05,
|
| 260 |
+
"loss": 2.1412,
|
| 261 |
+
"step": 180
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.044551475015051176,
|
| 265 |
+
"grad_norm": 3.4471330642700195,
|
| 266 |
+
"learning_rate": 1.9108863198458578e-05,
|
| 267 |
+
"loss": 2.1695,
|
| 268 |
+
"step": 185
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.045755568934376885,
|
| 272 |
+
"grad_norm": 3.394496440887451,
|
| 273 |
+
"learning_rate": 1.9084778420038536e-05,
|
| 274 |
+
"loss": 1.9532,
|
| 275 |
+
"step": 190
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.04695966285370259,
|
| 279 |
+
"grad_norm": 3.03004789352417,
|
| 280 |
+
"learning_rate": 1.90606936416185e-05,
|
| 281 |
+
"loss": 2.0659,
|
| 282 |
+
"step": 195
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.048163756773028296,
|
| 286 |
+
"grad_norm": 3.4260365962982178,
|
| 287 |
+
"learning_rate": 1.903660886319846e-05,
|
| 288 |
+
"loss": 2.0792,
|
| 289 |
+
"step": 200
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.048163756773028296,
|
| 293 |
+
"eval_loss": 2.1430513858795166,
|
| 294 |
+
"eval_runtime": 16.4051,
|
| 295 |
+
"eval_samples_per_second": 6.096,
|
| 296 |
+
"eval_steps_per_second": 0.792,
|
| 297 |
+
"step": 200
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.049367850692354005,
|
| 301 |
+
"grad_norm": 4.670680999755859,
|
| 302 |
+
"learning_rate": 1.901252408477842e-05,
|
| 303 |
+
"loss": 2.0952,
|
| 304 |
+
"step": 205
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.050571944611679714,
|
| 308 |
+
"grad_norm": 3.510042667388916,
|
| 309 |
+
"learning_rate": 1.8988439306358382e-05,
|
| 310 |
+
"loss": 2.195,
|
| 311 |
+
"step": 210
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.05177603853100542,
|
| 315 |
+
"grad_norm": 3.0459847450256348,
|
| 316 |
+
"learning_rate": 1.8964354527938345e-05,
|
| 317 |
+
"loss": 2.2117,
|
| 318 |
+
"step": 215
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.052980132450331126,
|
| 322 |
+
"grad_norm": 4.36016321182251,
|
| 323 |
+
"learning_rate": 1.8940269749518304e-05,
|
| 324 |
+
"loss": 2.1191,
|
| 325 |
+
"step": 220
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.054184226369656835,
|
| 329 |
+
"grad_norm": 3.0498242378234863,
|
| 330 |
+
"learning_rate": 1.891618497109827e-05,
|
| 331 |
+
"loss": 2.0838,
|
| 332 |
+
"step": 225
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.055388320288982544,
|
| 336 |
+
"grad_norm": 3.218038558959961,
|
| 337 |
+
"learning_rate": 1.889210019267823e-05,
|
| 338 |
+
"loss": 2.1118,
|
| 339 |
+
"step": 230
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.056592414208308246,
|
| 343 |
+
"grad_norm": 3.3144683837890625,
|
| 344 |
+
"learning_rate": 1.886801541425819e-05,
|
| 345 |
+
"loss": 2.2176,
|
| 346 |
+
"step": 235
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.057796508127633955,
|
| 350 |
+
"grad_norm": 3.2364652156829834,
|
| 351 |
+
"learning_rate": 1.8843930635838153e-05,
|
| 352 |
+
"loss": 2.112,
|
| 353 |
+
"step": 240
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.059000602046959665,
|
| 357 |
+
"grad_norm": 3.291278839111328,
|
| 358 |
+
"learning_rate": 1.8819845857418112e-05,
|
| 359 |
+
"loss": 2.144,
|
| 360 |
+
"step": 245
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.060204695966285374,
|
| 364 |
+
"grad_norm": 3.65297794342041,
|
| 365 |
+
"learning_rate": 1.8795761078998074e-05,
|
| 366 |
+
"loss": 2.2597,
|
| 367 |
+
"step": 250
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.061408789885611076,
|
| 371 |
+
"grad_norm": 3.2321982383728027,
|
| 372 |
+
"learning_rate": 1.8771676300578037e-05,
|
| 373 |
+
"loss": 2.1618,
|
| 374 |
+
"step": 255
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.06261288380493679,
|
| 378 |
+
"grad_norm": 3.352842330932617,
|
| 379 |
+
"learning_rate": 1.8747591522158e-05,
|
| 380 |
+
"loss": 2.006,
|
| 381 |
+
"step": 260
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.0638169777242625,
|
| 385 |
+
"grad_norm": 3.5657215118408203,
|
| 386 |
+
"learning_rate": 1.8723506743737958e-05,
|
| 387 |
+
"loss": 2.2253,
|
| 388 |
+
"step": 265
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.0650210716435882,
|
| 392 |
+
"grad_norm": 3.060060739517212,
|
| 393 |
+
"learning_rate": 1.869942196531792e-05,
|
| 394 |
+
"loss": 2.1187,
|
| 395 |
+
"step": 270
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.06622516556291391,
|
| 399 |
+
"grad_norm": 3.473719835281372,
|
| 400 |
+
"learning_rate": 1.8675337186897883e-05,
|
| 401 |
+
"loss": 2.0299,
|
| 402 |
+
"step": 275
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.06742925948223961,
|
| 406 |
+
"grad_norm": 3.1167919635772705,
|
| 407 |
+
"learning_rate": 1.8651252408477845e-05,
|
| 408 |
+
"loss": 2.0381,
|
| 409 |
+
"step": 280
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.06863335340156532,
|
| 413 |
+
"grad_norm": 3.815816640853882,
|
| 414 |
+
"learning_rate": 1.8627167630057804e-05,
|
| 415 |
+
"loss": 2.1624,
|
| 416 |
+
"step": 285
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.06983744732089103,
|
| 420 |
+
"grad_norm": 3.2820959091186523,
|
| 421 |
+
"learning_rate": 1.8603082851637766e-05,
|
| 422 |
+
"loss": 2.0819,
|
| 423 |
+
"step": 290
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.07104154124021674,
|
| 427 |
+
"grad_norm": 3.568885087966919,
|
| 428 |
+
"learning_rate": 1.857899807321773e-05,
|
| 429 |
+
"loss": 2.0749,
|
| 430 |
+
"step": 295
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.07224563515954245,
|
| 434 |
+
"grad_norm": 3.424076795578003,
|
| 435 |
+
"learning_rate": 1.855491329479769e-05,
|
| 436 |
+
"loss": 2.129,
|
| 437 |
+
"step": 300
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.07344972907886815,
|
| 441 |
+
"grad_norm": 3.2800493240356445,
|
| 442 |
+
"learning_rate": 1.853082851637765e-05,
|
| 443 |
+
"loss": 2.2067,
|
| 444 |
+
"step": 305
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.07465382299819386,
|
| 448 |
+
"grad_norm": 3.487868547439575,
|
| 449 |
+
"learning_rate": 1.8506743737957612e-05,
|
| 450 |
+
"loss": 2.124,
|
| 451 |
+
"step": 310
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.07585791691751957,
|
| 455 |
+
"grad_norm": 3.3999245166778564,
|
| 456 |
+
"learning_rate": 1.8482658959537575e-05,
|
| 457 |
+
"loss": 1.9888,
|
| 458 |
+
"step": 315
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.07706201083684527,
|
| 462 |
+
"grad_norm": 3.973482370376587,
|
| 463 |
+
"learning_rate": 1.8458574181117533e-05,
|
| 464 |
+
"loss": 2.0592,
|
| 465 |
+
"step": 320
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.07826610475617098,
|
| 469 |
+
"grad_norm": 2.9601657390594482,
|
| 470 |
+
"learning_rate": 1.8434489402697496e-05,
|
| 471 |
+
"loss": 2.1022,
|
| 472 |
+
"step": 325
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.07947019867549669,
|
| 476 |
+
"grad_norm": 3.260118246078491,
|
| 477 |
+
"learning_rate": 1.8410404624277458e-05,
|
| 478 |
+
"loss": 1.9763,
|
| 479 |
+
"step": 330
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.0806742925948224,
|
| 483 |
+
"grad_norm": 3.509838819503784,
|
| 484 |
+
"learning_rate": 1.838631984585742e-05,
|
| 485 |
+
"loss": 2.0284,
|
| 486 |
+
"step": 335
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.08187838651414811,
|
| 490 |
+
"grad_norm": 4.363494396209717,
|
| 491 |
+
"learning_rate": 1.8362235067437383e-05,
|
| 492 |
+
"loss": 2.0479,
|
| 493 |
+
"step": 340
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.08308248043347381,
|
| 497 |
+
"grad_norm": 3.2578630447387695,
|
| 498 |
+
"learning_rate": 1.8338150289017342e-05,
|
| 499 |
+
"loss": 2.0488,
|
| 500 |
+
"step": 345
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.08428657435279951,
|
| 504 |
+
"grad_norm": 3.2846531867980957,
|
| 505 |
+
"learning_rate": 1.8314065510597304e-05,
|
| 506 |
+
"loss": 2.0876,
|
| 507 |
+
"step": 350
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.08549066827212523,
|
| 511 |
+
"grad_norm": 3.3275203704833984,
|
| 512 |
+
"learning_rate": 1.8289980732177266e-05,
|
| 513 |
+
"loss": 2.0564,
|
| 514 |
+
"step": 355
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.08669476219145093,
|
| 518 |
+
"grad_norm": 3.1368625164031982,
|
| 519 |
+
"learning_rate": 1.8265895953757225e-05,
|
| 520 |
+
"loss": 2.1533,
|
| 521 |
+
"step": 360
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.08789885611077664,
|
| 525 |
+
"grad_norm": 3.3824191093444824,
|
| 526 |
+
"learning_rate": 1.8241811175337188e-05,
|
| 527 |
+
"loss": 2.1821,
|
| 528 |
+
"step": 365
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.08910295003010235,
|
| 532 |
+
"grad_norm": 3.5150134563446045,
|
| 533 |
+
"learning_rate": 1.821772639691715e-05,
|
| 534 |
+
"loss": 2.0292,
|
| 535 |
+
"step": 370
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.09030704394942805,
|
| 539 |
+
"grad_norm": 3.421921730041504,
|
| 540 |
+
"learning_rate": 1.8193641618497112e-05,
|
| 541 |
+
"loss": 1.9862,
|
| 542 |
+
"step": 375
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.09151113786875377,
|
| 546 |
+
"grad_norm": 3.616887092590332,
|
| 547 |
+
"learning_rate": 1.8169556840077075e-05,
|
| 548 |
+
"loss": 2.0158,
|
| 549 |
+
"step": 380
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.09271523178807947,
|
| 553 |
+
"grad_norm": 5.063056945800781,
|
| 554 |
+
"learning_rate": 1.8145472061657034e-05,
|
| 555 |
+
"loss": 2.0579,
|
| 556 |
+
"step": 385
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.09391932570740517,
|
| 560 |
+
"grad_norm": 3.5242559909820557,
|
| 561 |
+
"learning_rate": 1.8121387283236996e-05,
|
| 562 |
+
"loss": 2.0272,
|
| 563 |
+
"step": 390
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.09512341962673089,
|
| 567 |
+
"grad_norm": 3.2852962017059326,
|
| 568 |
+
"learning_rate": 1.809730250481696e-05,
|
| 569 |
+
"loss": 2.077,
|
| 570 |
+
"step": 395
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.09632751354605659,
|
| 574 |
+
"grad_norm": 3.710927963256836,
|
| 575 |
+
"learning_rate": 1.8073217726396917e-05,
|
| 576 |
+
"loss": 2.1271,
|
| 577 |
+
"step": 400
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.09632751354605659,
|
| 581 |
+
"eval_loss": 2.0655810832977295,
|
| 582 |
+
"eval_runtime": 16.3755,
|
| 583 |
+
"eval_samples_per_second": 6.107,
|
| 584 |
+
"eval_steps_per_second": 0.794,
|
| 585 |
+
"step": 400
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.0975316074653823,
|
| 589 |
+
"grad_norm": 3.5019216537475586,
|
| 590 |
+
"learning_rate": 1.804913294797688e-05,
|
| 591 |
+
"loss": 2.1081,
|
| 592 |
+
"step": 405
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.09873570138470801,
|
| 596 |
+
"grad_norm": 3.5533690452575684,
|
| 597 |
+
"learning_rate": 1.8025048169556842e-05,
|
| 598 |
+
"loss": 2.0751,
|
| 599 |
+
"step": 410
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.09993979530403371,
|
| 603 |
+
"grad_norm": 3.4970240592956543,
|
| 604 |
+
"learning_rate": 1.8000963391136804e-05,
|
| 605 |
+
"loss": 2.066,
|
| 606 |
+
"step": 415
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.10114388922335943,
|
| 610 |
+
"grad_norm": 3.0926427841186523,
|
| 611 |
+
"learning_rate": 1.7976878612716763e-05,
|
| 612 |
+
"loss": 2.0516,
|
| 613 |
+
"step": 420
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.10234798314268513,
|
| 617 |
+
"grad_norm": 3.747452974319458,
|
| 618 |
+
"learning_rate": 1.7952793834296726e-05,
|
| 619 |
+
"loss": 2.0721,
|
| 620 |
+
"step": 425
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.10355207706201083,
|
| 624 |
+
"grad_norm": 3.3113677501678467,
|
| 625 |
+
"learning_rate": 1.7928709055876688e-05,
|
| 626 |
+
"loss": 2.1527,
|
| 627 |
+
"step": 430
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.10475617098133655,
|
| 631 |
+
"grad_norm": 3.357912063598633,
|
| 632 |
+
"learning_rate": 1.7904624277456647e-05,
|
| 633 |
+
"loss": 2.0113,
|
| 634 |
+
"step": 435
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.10596026490066225,
|
| 638 |
+
"grad_norm": 3.023893356323242,
|
| 639 |
+
"learning_rate": 1.7880539499036613e-05,
|
| 640 |
+
"loss": 2.1332,
|
| 641 |
+
"step": 440
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.10716435881998795,
|
| 645 |
+
"grad_norm": 3.3027355670928955,
|
| 646 |
+
"learning_rate": 1.785645472061657e-05,
|
| 647 |
+
"loss": 1.9699,
|
| 648 |
+
"step": 445
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.10836845273931367,
|
| 652 |
+
"grad_norm": 5.3524932861328125,
|
| 653 |
+
"learning_rate": 1.7832369942196534e-05,
|
| 654 |
+
"loss": 2.0182,
|
| 655 |
+
"step": 450
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.10957254665863937,
|
| 659 |
+
"grad_norm": 3.200258731842041,
|
| 660 |
+
"learning_rate": 1.7808285163776496e-05,
|
| 661 |
+
"loss": 2.007,
|
| 662 |
+
"step": 455
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.11077664057796509,
|
| 666 |
+
"grad_norm": 3.286268949508667,
|
| 667 |
+
"learning_rate": 1.7784200385356455e-05,
|
| 668 |
+
"loss": 2.0907,
|
| 669 |
+
"step": 460
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.11198073449729079,
|
| 673 |
+
"grad_norm": 3.15291428565979,
|
| 674 |
+
"learning_rate": 1.7760115606936417e-05,
|
| 675 |
+
"loss": 2.0468,
|
| 676 |
+
"step": 465
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.11318482841661649,
|
| 680 |
+
"grad_norm": 3.3798069953918457,
|
| 681 |
+
"learning_rate": 1.773603082851638e-05,
|
| 682 |
+
"loss": 1.9927,
|
| 683 |
+
"step": 470
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.11438892233594221,
|
| 687 |
+
"grad_norm": 3.4220967292785645,
|
| 688 |
+
"learning_rate": 1.771194605009634e-05,
|
| 689 |
+
"loss": 2.1326,
|
| 690 |
+
"step": 475
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.11559301625526791,
|
| 694 |
+
"grad_norm": 3.379628896713257,
|
| 695 |
+
"learning_rate": 1.76878612716763e-05,
|
| 696 |
+
"loss": 1.9202,
|
| 697 |
+
"step": 480
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.11679711017459361,
|
| 701 |
+
"grad_norm": 3.3020846843719482,
|
| 702 |
+
"learning_rate": 1.7663776493256263e-05,
|
| 703 |
+
"loss": 2.1176,
|
| 704 |
+
"step": 485
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.11800120409391933,
|
| 708 |
+
"grad_norm": 3.2711665630340576,
|
| 709 |
+
"learning_rate": 1.7639691714836226e-05,
|
| 710 |
+
"loss": 2.0865,
|
| 711 |
+
"step": 490
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.11920529801324503,
|
| 715 |
+
"grad_norm": 3.239253520965576,
|
| 716 |
+
"learning_rate": 1.7615606936416188e-05,
|
| 717 |
+
"loss": 1.9284,
|
| 718 |
+
"step": 495
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.12040939193257075,
|
| 722 |
+
"grad_norm": 3.4960460662841797,
|
| 723 |
+
"learning_rate": 1.7591522157996147e-05,
|
| 724 |
+
"loss": 2.0088,
|
| 725 |
+
"step": 500
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.12161348585189645,
|
| 729 |
+
"grad_norm": 3.337407350540161,
|
| 730 |
+
"learning_rate": 1.756743737957611e-05,
|
| 731 |
+
"loss": 1.9687,
|
| 732 |
+
"step": 505
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.12281757977122215,
|
| 736 |
+
"grad_norm": 3.534827709197998,
|
| 737 |
+
"learning_rate": 1.754335260115607e-05,
|
| 738 |
+
"loss": 2.0273,
|
| 739 |
+
"step": 510
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 0.12402167369054787,
|
| 743 |
+
"grad_norm": 3.6207938194274902,
|
| 744 |
+
"learning_rate": 1.7519267822736034e-05,
|
| 745 |
+
"loss": 2.0458,
|
| 746 |
+
"step": 515
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.12522576760987358,
|
| 750 |
+
"grad_norm": 3.396012544631958,
|
| 751 |
+
"learning_rate": 1.7495183044315993e-05,
|
| 752 |
+
"loss": 1.9185,
|
| 753 |
+
"step": 520
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.12642986152919927,
|
| 757 |
+
"grad_norm": 3.001236915588379,
|
| 758 |
+
"learning_rate": 1.7471098265895955e-05,
|
| 759 |
+
"loss": 1.9407,
|
| 760 |
+
"step": 525
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.127633955448525,
|
| 764 |
+
"grad_norm": 3.1318376064300537,
|
| 765 |
+
"learning_rate": 1.7447013487475918e-05,
|
| 766 |
+
"loss": 1.8984,
|
| 767 |
+
"step": 530
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.1288380493678507,
|
| 771 |
+
"grad_norm": 3.4541585445404053,
|
| 772 |
+
"learning_rate": 1.7422928709055877e-05,
|
| 773 |
+
"loss": 1.8846,
|
| 774 |
+
"step": 535
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.1300421432871764,
|
| 778 |
+
"grad_norm": 3.311082363128662,
|
| 779 |
+
"learning_rate": 1.739884393063584e-05,
|
| 780 |
+
"loss": 2.0015,
|
| 781 |
+
"step": 540
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 0.1312462372065021,
|
| 785 |
+
"grad_norm": 3.2366561889648438,
|
| 786 |
+
"learning_rate": 1.73747591522158e-05,
|
| 787 |
+
"loss": 2.0176,
|
| 788 |
+
"step": 545
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.13245033112582782,
|
| 792 |
+
"grad_norm": 3.123307943344116,
|
| 793 |
+
"learning_rate": 1.735067437379576e-05,
|
| 794 |
+
"loss": 1.9731,
|
| 795 |
+
"step": 550
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.1336544250451535,
|
| 799 |
+
"grad_norm": 3.776921033859253,
|
| 800 |
+
"learning_rate": 1.7326589595375726e-05,
|
| 801 |
+
"loss": 2.0484,
|
| 802 |
+
"step": 555
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.13485851896447923,
|
| 806 |
+
"grad_norm": 2.959716796875,
|
| 807 |
+
"learning_rate": 1.7302504816955685e-05,
|
| 808 |
+
"loss": 1.9689,
|
| 809 |
+
"step": 560
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.13606261288380495,
|
| 813 |
+
"grad_norm": 3.527384042739868,
|
| 814 |
+
"learning_rate": 1.7278420038535647e-05,
|
| 815 |
+
"loss": 1.9488,
|
| 816 |
+
"step": 565
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 0.13726670680313063,
|
| 820 |
+
"grad_norm": 3.0703189373016357,
|
| 821 |
+
"learning_rate": 1.725433526011561e-05,
|
| 822 |
+
"loss": 2.1226,
|
| 823 |
+
"step": 570
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 0.13847080072245635,
|
| 827 |
+
"grad_norm": 3.1028363704681396,
|
| 828 |
+
"learning_rate": 1.723025048169557e-05,
|
| 829 |
+
"loss": 1.8966,
|
| 830 |
+
"step": 575
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.13967489464178207,
|
| 834 |
+
"grad_norm": 3.340517044067383,
|
| 835 |
+
"learning_rate": 1.720616570327553e-05,
|
| 836 |
+
"loss": 2.2156,
|
| 837 |
+
"step": 580
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.14087898856110775,
|
| 841 |
+
"grad_norm": 3.2740213871002197,
|
| 842 |
+
"learning_rate": 1.7182080924855493e-05,
|
| 843 |
+
"loss": 1.9445,
|
| 844 |
+
"step": 585
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 0.14208308248043347,
|
| 848 |
+
"grad_norm": 3.240690231323242,
|
| 849 |
+
"learning_rate": 1.7157996146435455e-05,
|
| 850 |
+
"loss": 2.0295,
|
| 851 |
+
"step": 590
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 0.1432871763997592,
|
| 855 |
+
"grad_norm": 3.821340799331665,
|
| 856 |
+
"learning_rate": 1.7133911368015418e-05,
|
| 857 |
+
"loss": 2.1401,
|
| 858 |
+
"step": 595
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.1444912703190849,
|
| 862 |
+
"grad_norm": 3.103550910949707,
|
| 863 |
+
"learning_rate": 1.7109826589595377e-05,
|
| 864 |
+
"loss": 2.1164,
|
| 865 |
+
"step": 600
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.1444912703190849,
|
| 869 |
+
"eval_loss": 2.017059564590454,
|
| 870 |
+
"eval_runtime": 16.4324,
|
| 871 |
+
"eval_samples_per_second": 6.086,
|
| 872 |
+
"eval_steps_per_second": 0.791,
|
| 873 |
+
"step": 600
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.1456953642384106,
|
| 877 |
+
"grad_norm": 3.4971117973327637,
|
| 878 |
+
"learning_rate": 1.708574181117534e-05,
|
| 879 |
+
"loss": 1.9864,
|
| 880 |
+
"step": 605
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.1468994581577363,
|
| 884 |
+
"grad_norm": 3.324803590774536,
|
| 885 |
+
"learning_rate": 1.70616570327553e-05,
|
| 886 |
+
"loss": 2.0402,
|
| 887 |
+
"step": 610
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.14810355207706202,
|
| 891 |
+
"grad_norm": 3.302614450454712,
|
| 892 |
+
"learning_rate": 1.703757225433526e-05,
|
| 893 |
+
"loss": 1.9494,
|
| 894 |
+
"step": 615
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.1493076459963877,
|
| 898 |
+
"grad_norm": 3.3090734481811523,
|
| 899 |
+
"learning_rate": 1.7013487475915223e-05,
|
| 900 |
+
"loss": 2.0748,
|
| 901 |
+
"step": 620
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.15051173991571343,
|
| 905 |
+
"grad_norm": 3.559049129486084,
|
| 906 |
+
"learning_rate": 1.6989402697495185e-05,
|
| 907 |
+
"loss": 1.9038,
|
| 908 |
+
"step": 625
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.15171583383503914,
|
| 912 |
+
"grad_norm": 3.5149178504943848,
|
| 913 |
+
"learning_rate": 1.6965317919075147e-05,
|
| 914 |
+
"loss": 2.0261,
|
| 915 |
+
"step": 630
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.15291992775436483,
|
| 919 |
+
"grad_norm": 3.835693120956421,
|
| 920 |
+
"learning_rate": 1.6941233140655106e-05,
|
| 921 |
+
"loss": 1.9453,
|
| 922 |
+
"step": 635
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.15412402167369055,
|
| 926 |
+
"grad_norm": 3.521132469177246,
|
| 927 |
+
"learning_rate": 1.691714836223507e-05,
|
| 928 |
+
"loss": 2.0138,
|
| 929 |
+
"step": 640
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.15532811559301626,
|
| 933 |
+
"grad_norm": 3.2369840145111084,
|
| 934 |
+
"learning_rate": 1.689306358381503e-05,
|
| 935 |
+
"loss": 2.0285,
|
| 936 |
+
"step": 645
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.15653220951234195,
|
| 940 |
+
"grad_norm": 3.1592392921447754,
|
| 941 |
+
"learning_rate": 1.686897880539499e-05,
|
| 942 |
+
"loss": 1.9912,
|
| 943 |
+
"step": 650
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.15773630343166767,
|
| 947 |
+
"grad_norm": 3.2069106101989746,
|
| 948 |
+
"learning_rate": 1.6844894026974952e-05,
|
| 949 |
+
"loss": 2.0159,
|
| 950 |
+
"step": 655
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.15894039735099338,
|
| 954 |
+
"grad_norm": 3.318230390548706,
|
| 955 |
+
"learning_rate": 1.6820809248554915e-05,
|
| 956 |
+
"loss": 2.0412,
|
| 957 |
+
"step": 660
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.16014449127031907,
|
| 961 |
+
"grad_norm": 3.549443244934082,
|
| 962 |
+
"learning_rate": 1.6796724470134877e-05,
|
| 963 |
+
"loss": 2.0014,
|
| 964 |
+
"step": 665
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.1613485851896448,
|
| 968 |
+
"grad_norm": 3.32999324798584,
|
| 969 |
+
"learning_rate": 1.677263969171484e-05,
|
| 970 |
+
"loss": 2.0303,
|
| 971 |
+
"step": 670
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.1625526791089705,
|
| 975 |
+
"grad_norm": 3.262946367263794,
|
| 976 |
+
"learning_rate": 1.6748554913294798e-05,
|
| 977 |
+
"loss": 1.9883,
|
| 978 |
+
"step": 675
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.16375677302829622,
|
| 982 |
+
"grad_norm": 3.484685182571411,
|
| 983 |
+
"learning_rate": 1.672447013487476e-05,
|
| 984 |
+
"loss": 1.9695,
|
| 985 |
+
"step": 680
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.1649608669476219,
|
| 989 |
+
"grad_norm": 3.4177358150482178,
|
| 990 |
+
"learning_rate": 1.6700385356454723e-05,
|
| 991 |
+
"loss": 2.0088,
|
| 992 |
+
"step": 685
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.16616496086694763,
|
| 996 |
+
"grad_norm": 3.447498321533203,
|
| 997 |
+
"learning_rate": 1.6676300578034682e-05,
|
| 998 |
+
"loss": 2.0813,
|
| 999 |
+
"step": 690
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.16736905478627334,
|
| 1003 |
+
"grad_norm": 3.152740240097046,
|
| 1004 |
+
"learning_rate": 1.6652215799614644e-05,
|
| 1005 |
+
"loss": 1.9988,
|
| 1006 |
+
"step": 695
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.16857314870559903,
|
| 1010 |
+
"grad_norm": 3.8948824405670166,
|
| 1011 |
+
"learning_rate": 1.6628131021194607e-05,
|
| 1012 |
+
"loss": 2.0801,
|
| 1013 |
+
"step": 700
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.16977724262492475,
|
| 1017 |
+
"grad_norm": 3.81358003616333,
|
| 1018 |
+
"learning_rate": 1.660404624277457e-05,
|
| 1019 |
+
"loss": 1.944,
|
| 1020 |
+
"step": 705
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.17098133654425046,
|
| 1024 |
+
"grad_norm": 2.980236053466797,
|
| 1025 |
+
"learning_rate": 1.657996146435453e-05,
|
| 1026 |
+
"loss": 1.9151,
|
| 1027 |
+
"step": 710
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.17218543046357615,
|
| 1031 |
+
"grad_norm": 3.041680335998535,
|
| 1032 |
+
"learning_rate": 1.655587668593449e-05,
|
| 1033 |
+
"loss": 1.9486,
|
| 1034 |
+
"step": 715
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.17338952438290187,
|
| 1038 |
+
"grad_norm": 2.898974657058716,
|
| 1039 |
+
"learning_rate": 1.6531791907514452e-05,
|
| 1040 |
+
"loss": 2.1119,
|
| 1041 |
+
"step": 720
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.17459361830222758,
|
| 1045 |
+
"grad_norm": 3.161224603652954,
|
| 1046 |
+
"learning_rate": 1.6507707129094415e-05,
|
| 1047 |
+
"loss": 2.036,
|
| 1048 |
+
"step": 725
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.17579771222155327,
|
| 1052 |
+
"grad_norm": 3.2449426651000977,
|
| 1053 |
+
"learning_rate": 1.6483622350674374e-05,
|
| 1054 |
+
"loss": 2.0635,
|
| 1055 |
+
"step": 730
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.177001806140879,
|
| 1059 |
+
"grad_norm": 3.2805328369140625,
|
| 1060 |
+
"learning_rate": 1.6459537572254336e-05,
|
| 1061 |
+
"loss": 1.8022,
|
| 1062 |
+
"step": 735
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.1782059000602047,
|
| 1066 |
+
"grad_norm": 3.491149663925171,
|
| 1067 |
+
"learning_rate": 1.64354527938343e-05,
|
| 1068 |
+
"loss": 1.9832,
|
| 1069 |
+
"step": 740
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.1794099939795304,
|
| 1073 |
+
"grad_norm": 3.423267126083374,
|
| 1074 |
+
"learning_rate": 1.641136801541426e-05,
|
| 1075 |
+
"loss": 1.9574,
|
| 1076 |
+
"step": 745
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.1806140878988561,
|
| 1080 |
+
"grad_norm": 3.1914217472076416,
|
| 1081 |
+
"learning_rate": 1.638728323699422e-05,
|
| 1082 |
+
"loss": 1.9283,
|
| 1083 |
+
"step": 750
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.18181818181818182,
|
| 1087 |
+
"grad_norm": 3.2903149127960205,
|
| 1088 |
+
"learning_rate": 1.6363198458574182e-05,
|
| 1089 |
+
"loss": 2.1174,
|
| 1090 |
+
"step": 755
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 0.18302227573750754,
|
| 1094 |
+
"grad_norm": 3.113159656524658,
|
| 1095 |
+
"learning_rate": 1.6339113680154144e-05,
|
| 1096 |
+
"loss": 1.8794,
|
| 1097 |
+
"step": 760
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 0.18422636965683323,
|
| 1101 |
+
"grad_norm": 3.261596918106079,
|
| 1102 |
+
"learning_rate": 1.6315028901734103e-05,
|
| 1103 |
+
"loss": 2.0853,
|
| 1104 |
+
"step": 765
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 0.18543046357615894,
|
| 1108 |
+
"grad_norm": 2.9525296688079834,
|
| 1109 |
+
"learning_rate": 1.629094412331407e-05,
|
| 1110 |
+
"loss": 1.8622,
|
| 1111 |
+
"step": 770
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 0.18663455749548466,
|
| 1115 |
+
"grad_norm": 3.2103638648986816,
|
| 1116 |
+
"learning_rate": 1.6266859344894028e-05,
|
| 1117 |
+
"loss": 2.0536,
|
| 1118 |
+
"step": 775
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 0.18783865141481035,
|
| 1122 |
+
"grad_norm": 3.5312676429748535,
|
| 1123 |
+
"learning_rate": 1.624277456647399e-05,
|
| 1124 |
+
"loss": 1.9387,
|
| 1125 |
+
"step": 780
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.18904274533413606,
|
| 1129 |
+
"grad_norm": 3.277223825454712,
|
| 1130 |
+
"learning_rate": 1.6218689788053953e-05,
|
| 1131 |
+
"loss": 1.9804,
|
| 1132 |
+
"step": 785
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 0.19024683925346178,
|
| 1136 |
+
"grad_norm": 3.207287549972534,
|
| 1137 |
+
"learning_rate": 1.619460500963391e-05,
|
| 1138 |
+
"loss": 1.8782,
|
| 1139 |
+
"step": 790
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 0.19145093317278747,
|
| 1143 |
+
"grad_norm": 3.401834487915039,
|
| 1144 |
+
"learning_rate": 1.6170520231213874e-05,
|
| 1145 |
+
"loss": 1.9383,
|
| 1146 |
+
"step": 795
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 0.19265502709211318,
|
| 1150 |
+
"grad_norm": 3.5186078548431396,
|
| 1151 |
+
"learning_rate": 1.6146435452793836e-05,
|
| 1152 |
+
"loss": 2.0963,
|
| 1153 |
+
"step": 800
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 0.19265502709211318,
|
| 1157 |
+
"eval_loss": 1.979533076286316,
|
| 1158 |
+
"eval_runtime": 16.4348,
|
| 1159 |
+
"eval_samples_per_second": 6.085,
|
| 1160 |
+
"eval_steps_per_second": 0.791,
|
| 1161 |
+
"step": 800
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.1938591210114389,
|
| 1165 |
+
"grad_norm": 3.0080161094665527,
|
| 1166 |
+
"learning_rate": 1.6122350674373795e-05,
|
| 1167 |
+
"loss": 1.951,
|
| 1168 |
+
"step": 805
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.1950632149307646,
|
| 1172 |
+
"grad_norm": 3.124155044555664,
|
| 1173 |
+
"learning_rate": 1.6098265895953758e-05,
|
| 1174 |
+
"loss": 1.8663,
|
| 1175 |
+
"step": 810
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.1962673088500903,
|
| 1179 |
+
"grad_norm": 3.6262383460998535,
|
| 1180 |
+
"learning_rate": 1.607418111753372e-05,
|
| 1181 |
+
"loss": 1.9478,
|
| 1182 |
+
"step": 815
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.19747140276941602,
|
| 1186 |
+
"grad_norm": 3.3047947883605957,
|
| 1187 |
+
"learning_rate": 1.6050096339113682e-05,
|
| 1188 |
+
"loss": 1.9203,
|
| 1189 |
+
"step": 820
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.1986754966887417,
|
| 1193 |
+
"grad_norm": 3.0261447429656982,
|
| 1194 |
+
"learning_rate": 1.6026011560693645e-05,
|
| 1195 |
+
"loss": 1.8988,
|
| 1196 |
+
"step": 825
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.19987959060806743,
|
| 1200 |
+
"grad_norm": 4.233884334564209,
|
| 1201 |
+
"learning_rate": 1.6001926782273604e-05,
|
| 1202 |
+
"loss": 2.0327,
|
| 1203 |
+
"step": 830
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.20108368452739314,
|
| 1207 |
+
"grad_norm": 2.9169118404388428,
|
| 1208 |
+
"learning_rate": 1.5977842003853566e-05,
|
| 1209 |
+
"loss": 1.9264,
|
| 1210 |
+
"step": 835
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.20228777844671886,
|
| 1214 |
+
"grad_norm": 3.0078282356262207,
|
| 1215 |
+
"learning_rate": 1.5953757225433528e-05,
|
| 1216 |
+
"loss": 1.8821,
|
| 1217 |
+
"step": 840
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.20349187236604455,
|
| 1221 |
+
"grad_norm": 3.4188835620880127,
|
| 1222 |
+
"learning_rate": 1.592967244701349e-05,
|
| 1223 |
+
"loss": 1.933,
|
| 1224 |
+
"step": 845
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.20469596628537026,
|
| 1228 |
+
"grad_norm": 4.739987850189209,
|
| 1229 |
+
"learning_rate": 1.590558766859345e-05,
|
| 1230 |
+
"loss": 1.9182,
|
| 1231 |
+
"step": 850
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.20590006020469598,
|
| 1235 |
+
"grad_norm": 3.1810977458953857,
|
| 1236 |
+
"learning_rate": 1.5881502890173412e-05,
|
| 1237 |
+
"loss": 1.984,
|
| 1238 |
+
"step": 855
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.20710415412402167,
|
| 1242 |
+
"grad_norm": 3.174739360809326,
|
| 1243 |
+
"learning_rate": 1.5857418111753374e-05,
|
| 1244 |
+
"loss": 1.7719,
|
| 1245 |
+
"step": 860
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.20830824804334738,
|
| 1249 |
+
"grad_norm": 3.379767656326294,
|
| 1250 |
+
"learning_rate": 1.5833333333333333e-05,
|
| 1251 |
+
"loss": 1.9481,
|
| 1252 |
+
"step": 865
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.2095123419626731,
|
| 1256 |
+
"grad_norm": 3.3487260341644287,
|
| 1257 |
+
"learning_rate": 1.5809248554913295e-05,
|
| 1258 |
+
"loss": 1.9416,
|
| 1259 |
+
"step": 870
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.2107164358819988,
|
| 1263 |
+
"grad_norm": 3.4879958629608154,
|
| 1264 |
+
"learning_rate": 1.5785163776493258e-05,
|
| 1265 |
+
"loss": 2.0463,
|
| 1266 |
+
"step": 875
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.2119205298013245,
|
| 1270 |
+
"grad_norm": 3.2338194847106934,
|
| 1271 |
+
"learning_rate": 1.5761078998073217e-05,
|
| 1272 |
+
"loss": 1.9441,
|
| 1273 |
+
"step": 880
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.21312462372065022,
|
| 1277 |
+
"grad_norm": 3.122405529022217,
|
| 1278 |
+
"learning_rate": 1.5736994219653182e-05,
|
| 1279 |
+
"loss": 2.0644,
|
| 1280 |
+
"step": 885
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.2143287176399759,
|
| 1284 |
+
"grad_norm": 3.0773510932922363,
|
| 1285 |
+
"learning_rate": 1.571290944123314e-05,
|
| 1286 |
+
"loss": 1.9415,
|
| 1287 |
+
"step": 890
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.21553281155930162,
|
| 1291 |
+
"grad_norm": 3.004040241241455,
|
| 1292 |
+
"learning_rate": 1.5688824662813104e-05,
|
| 1293 |
+
"loss": 1.9305,
|
| 1294 |
+
"step": 895
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.21673690547862734,
|
| 1298 |
+
"grad_norm": 3.547109603881836,
|
| 1299 |
+
"learning_rate": 1.5664739884393066e-05,
|
| 1300 |
+
"loss": 2.1088,
|
| 1301 |
+
"step": 900
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.21794099939795303,
|
| 1305 |
+
"grad_norm": 3.1982204914093018,
|
| 1306 |
+
"learning_rate": 1.5640655105973025e-05,
|
| 1307 |
+
"loss": 1.8667,
|
| 1308 |
+
"step": 905
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.21914509331727874,
|
| 1312 |
+
"grad_norm": 3.381781578063965,
|
| 1313 |
+
"learning_rate": 1.5616570327552987e-05,
|
| 1314 |
+
"loss": 1.9783,
|
| 1315 |
+
"step": 910
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.22034918723660446,
|
| 1319 |
+
"grad_norm": 2.9775896072387695,
|
| 1320 |
+
"learning_rate": 1.559248554913295e-05,
|
| 1321 |
+
"loss": 2.0211,
|
| 1322 |
+
"step": 915
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.22155328115593018,
|
| 1326 |
+
"grad_norm": 2.864551067352295,
|
| 1327 |
+
"learning_rate": 1.5568400770712912e-05,
|
| 1328 |
+
"loss": 1.8579,
|
| 1329 |
+
"step": 920
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.22275737507525586,
|
| 1333 |
+
"grad_norm": 3.0532050132751465,
|
| 1334 |
+
"learning_rate": 1.5544315992292874e-05,
|
| 1335 |
+
"loss": 1.9398,
|
| 1336 |
+
"step": 925
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.22396146899458158,
|
| 1340 |
+
"grad_norm": 2.859631061553955,
|
| 1341 |
+
"learning_rate": 1.5520231213872833e-05,
|
| 1342 |
+
"loss": 1.8625,
|
| 1343 |
+
"step": 930
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.2251655629139073,
|
| 1347 |
+
"grad_norm": 3.1373536586761475,
|
| 1348 |
+
"learning_rate": 1.5496146435452796e-05,
|
| 1349 |
+
"loss": 1.9003,
|
| 1350 |
+
"step": 935
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.22636965683323299,
|
| 1354 |
+
"grad_norm": 3.3248465061187744,
|
| 1355 |
+
"learning_rate": 1.5472061657032758e-05,
|
| 1356 |
+
"loss": 2.0517,
|
| 1357 |
+
"step": 940
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.2275737507525587,
|
| 1361 |
+
"grad_norm": 3.5990936756134033,
|
| 1362 |
+
"learning_rate": 1.5447976878612717e-05,
|
| 1363 |
+
"loss": 1.8975,
|
| 1364 |
+
"step": 945
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.22877784467188442,
|
| 1368 |
+
"grad_norm": 3.4047725200653076,
|
| 1369 |
+
"learning_rate": 1.542389210019268e-05,
|
| 1370 |
+
"loss": 1.9786,
|
| 1371 |
+
"step": 950
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.2299819385912101,
|
| 1375 |
+
"grad_norm": 3.3326022624969482,
|
| 1376 |
+
"learning_rate": 1.539980732177264e-05,
|
| 1377 |
+
"loss": 1.7848,
|
| 1378 |
+
"step": 955
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.23118603251053582,
|
| 1382 |
+
"grad_norm": 3.2942848205566406,
|
| 1383 |
+
"learning_rate": 1.5375722543352604e-05,
|
| 1384 |
+
"loss": 1.8549,
|
| 1385 |
+
"step": 960
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.23239012642986154,
|
| 1389 |
+
"grad_norm": 3.4602601528167725,
|
| 1390 |
+
"learning_rate": 1.5351637764932563e-05,
|
| 1391 |
+
"loss": 1.917,
|
| 1392 |
+
"step": 965
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.23359422034918723,
|
| 1396 |
+
"grad_norm": 3.591327428817749,
|
| 1397 |
+
"learning_rate": 1.5327552986512525e-05,
|
| 1398 |
+
"loss": 1.9457,
|
| 1399 |
+
"step": 970
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.23479831426851294,
|
| 1403 |
+
"grad_norm": 3.215808868408203,
|
| 1404 |
+
"learning_rate": 1.5303468208092487e-05,
|
| 1405 |
+
"loss": 1.9261,
|
| 1406 |
+
"step": 975
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.23600240818783866,
|
| 1410 |
+
"grad_norm": 3.5032927989959717,
|
| 1411 |
+
"learning_rate": 1.5279383429672446e-05,
|
| 1412 |
+
"loss": 1.967,
|
| 1413 |
+
"step": 980
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.23720650210716435,
|
| 1417 |
+
"grad_norm": 3.1476144790649414,
|
| 1418 |
+
"learning_rate": 1.525529865125241e-05,
|
| 1419 |
+
"loss": 2.0448,
|
| 1420 |
+
"step": 985
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.23841059602649006,
|
| 1424 |
+
"grad_norm": 3.046126365661621,
|
| 1425 |
+
"learning_rate": 1.5231213872832371e-05,
|
| 1426 |
+
"loss": 1.9086,
|
| 1427 |
+
"step": 990
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.23961468994581578,
|
| 1431 |
+
"grad_norm": 3.0403099060058594,
|
| 1432 |
+
"learning_rate": 1.5207129094412332e-05,
|
| 1433 |
+
"loss": 1.9671,
|
| 1434 |
+
"step": 995
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.2408187838651415,
|
| 1438 |
+
"grad_norm": 3.524573802947998,
|
| 1439 |
+
"learning_rate": 1.5183044315992294e-05,
|
| 1440 |
+
"loss": 1.9532,
|
| 1441 |
+
"step": 1000
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.2408187838651415,
|
| 1445 |
+
"eval_loss": 1.9571956396102905,
|
| 1446 |
+
"eval_runtime": 16.4441,
|
| 1447 |
+
"eval_samples_per_second": 6.081,
|
| 1448 |
+
"eval_steps_per_second": 0.791,
|
| 1449 |
+
"step": 1000
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.24202287778446718,
|
| 1453 |
+
"grad_norm": 3.518422842025757,
|
| 1454 |
+
"learning_rate": 1.5158959537572255e-05,
|
| 1455 |
+
"loss": 1.9851,
|
| 1456 |
+
"step": 1005
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 0.2432269717037929,
|
| 1460 |
+
"grad_norm": 3.0476677417755127,
|
| 1461 |
+
"learning_rate": 1.5134874759152215e-05,
|
| 1462 |
+
"loss": 2.0102,
|
| 1463 |
+
"step": 1010
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 0.24443106562311862,
|
| 1467 |
+
"grad_norm": 2.7093968391418457,
|
| 1468 |
+
"learning_rate": 1.511078998073218e-05,
|
| 1469 |
+
"loss": 1.8704,
|
| 1470 |
+
"step": 1015
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 0.2456351595424443,
|
| 1474 |
+
"grad_norm": 2.8607966899871826,
|
| 1475 |
+
"learning_rate": 1.508670520231214e-05,
|
| 1476 |
+
"loss": 1.9948,
|
| 1477 |
+
"step": 1020
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 0.24683925346177002,
|
| 1481 |
+
"grad_norm": 3.224783182144165,
|
| 1482 |
+
"learning_rate": 1.50626204238921e-05,
|
| 1483 |
+
"loss": 1.9097,
|
| 1484 |
+
"step": 1025
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 0.24804334738109574,
|
| 1488 |
+
"grad_norm": 3.199155807495117,
|
| 1489 |
+
"learning_rate": 1.5038535645472063e-05,
|
| 1490 |
+
"loss": 2.0205,
|
| 1491 |
+
"step": 1030
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 0.24924744130042142,
|
| 1495 |
+
"grad_norm": 3.12842059135437,
|
| 1496 |
+
"learning_rate": 1.5014450867052024e-05,
|
| 1497 |
+
"loss": 1.8666,
|
| 1498 |
+
"step": 1035
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 0.25045153521974717,
|
| 1502 |
+
"grad_norm": 3.7331671714782715,
|
| 1503 |
+
"learning_rate": 1.4990366088631986e-05,
|
| 1504 |
+
"loss": 1.913,
|
| 1505 |
+
"step": 1040
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 0.25165562913907286,
|
| 1509 |
+
"grad_norm": 3.0594935417175293,
|
| 1510 |
+
"learning_rate": 1.4966281310211948e-05,
|
| 1511 |
+
"loss": 2.0016,
|
| 1512 |
+
"step": 1045
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 0.25285972305839854,
|
| 1516 |
+
"grad_norm": 3.166200637817383,
|
| 1517 |
+
"learning_rate": 1.4942196531791909e-05,
|
| 1518 |
+
"loss": 1.9481,
|
| 1519 |
+
"step": 1050
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 0.2540638169777243,
|
| 1523 |
+
"grad_norm": 3.08423113822937,
|
| 1524 |
+
"learning_rate": 1.4918111753371871e-05,
|
| 1525 |
+
"loss": 1.9168,
|
| 1526 |
+
"step": 1055
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 0.25526791089705,
|
| 1530 |
+
"grad_norm": 3.7309155464172363,
|
| 1531 |
+
"learning_rate": 1.4894026974951832e-05,
|
| 1532 |
+
"loss": 1.9698,
|
| 1533 |
+
"step": 1060
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 0.25647200481637566,
|
| 1537 |
+
"grad_norm": 3.5642640590667725,
|
| 1538 |
+
"learning_rate": 1.4869942196531793e-05,
|
| 1539 |
+
"loss": 2.0914,
|
| 1540 |
+
"step": 1065
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"epoch": 0.2576760987357014,
|
| 1544 |
+
"grad_norm": 3.201970338821411,
|
| 1545 |
+
"learning_rate": 1.4845857418111755e-05,
|
| 1546 |
+
"loss": 1.9358,
|
| 1547 |
+
"step": 1070
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 0.2588801926550271,
|
| 1551 |
+
"grad_norm": 3.19600510597229,
|
| 1552 |
+
"learning_rate": 1.4821772639691716e-05,
|
| 1553 |
+
"loss": 1.9028,
|
| 1554 |
+
"step": 1075
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 0.2600842865743528,
|
| 1558 |
+
"grad_norm": 2.8048558235168457,
|
| 1559 |
+
"learning_rate": 1.4797687861271676e-05,
|
| 1560 |
+
"loss": 1.9104,
|
| 1561 |
+
"step": 1080
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 0.26128838049367853,
|
| 1565 |
+
"grad_norm": 3.3447604179382324,
|
| 1566 |
+
"learning_rate": 1.477360308285164e-05,
|
| 1567 |
+
"loss": 1.9683,
|
| 1568 |
+
"step": 1085
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 0.2624924744130042,
|
| 1572 |
+
"grad_norm": 3.2456166744232178,
|
| 1573 |
+
"learning_rate": 1.4749518304431601e-05,
|
| 1574 |
+
"loss": 1.9469,
|
| 1575 |
+
"step": 1090
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 0.2636965683323299,
|
| 1579 |
+
"grad_norm": 4.318637847900391,
|
| 1580 |
+
"learning_rate": 1.4725433526011562e-05,
|
| 1581 |
+
"loss": 1.9199,
|
| 1582 |
+
"step": 1095
|
| 1583 |
+
},
|
| 1584 |
+
{
|
| 1585 |
+
"epoch": 0.26490066225165565,
|
| 1586 |
+
"grad_norm": 3.258910655975342,
|
| 1587 |
+
"learning_rate": 1.4701348747591524e-05,
|
| 1588 |
+
"loss": 1.9996,
|
| 1589 |
+
"step": 1100
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"epoch": 0.26610475617098134,
|
| 1593 |
+
"grad_norm": 3.2944164276123047,
|
| 1594 |
+
"learning_rate": 1.4677263969171484e-05,
|
| 1595 |
+
"loss": 1.9373,
|
| 1596 |
+
"step": 1105
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 0.267308850090307,
|
| 1600 |
+
"grad_norm": 2.938908815383911,
|
| 1601 |
+
"learning_rate": 1.4653179190751445e-05,
|
| 1602 |
+
"loss": 1.8301,
|
| 1603 |
+
"step": 1110
|
| 1604 |
+
},
|
| 1605 |
+
{
|
| 1606 |
+
"epoch": 0.26851294400963277,
|
| 1607 |
+
"grad_norm": 3.38433575630188,
|
| 1608 |
+
"learning_rate": 1.4629094412331407e-05,
|
| 1609 |
+
"loss": 2.0615,
|
| 1610 |
+
"step": 1115
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 0.26971703792895846,
|
| 1614 |
+
"grad_norm": 2.9752516746520996,
|
| 1615 |
+
"learning_rate": 1.4605009633911368e-05,
|
| 1616 |
+
"loss": 2.0132,
|
| 1617 |
+
"step": 1120
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 0.27092113184828415,
|
| 1621 |
+
"grad_norm": 2.9489858150482178,
|
| 1622 |
+
"learning_rate": 1.458092485549133e-05,
|
| 1623 |
+
"loss": 1.9319,
|
| 1624 |
+
"step": 1125
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 0.2721252257676099,
|
| 1628 |
+
"grad_norm": 3.231663465499878,
|
| 1629 |
+
"learning_rate": 1.4556840077071293e-05,
|
| 1630 |
+
"loss": 1.8924,
|
| 1631 |
+
"step": 1130
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 0.2733293196869356,
|
| 1635 |
+
"grad_norm": 3.2028298377990723,
|
| 1636 |
+
"learning_rate": 1.4532755298651253e-05,
|
| 1637 |
+
"loss": 1.9836,
|
| 1638 |
+
"step": 1135
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 0.27453341360626127,
|
| 1642 |
+
"grad_norm": 3.348498582839966,
|
| 1643 |
+
"learning_rate": 1.4508670520231216e-05,
|
| 1644 |
+
"loss": 2.0908,
|
| 1645 |
+
"step": 1140
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 0.275737507525587,
|
| 1649 |
+
"grad_norm": 3.1415324211120605,
|
| 1650 |
+
"learning_rate": 1.4484585741811176e-05,
|
| 1651 |
+
"loss": 2.043,
|
| 1652 |
+
"step": 1145
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 0.2769416014449127,
|
| 1656 |
+
"grad_norm": 2.9878766536712646,
|
| 1657 |
+
"learning_rate": 1.4460500963391137e-05,
|
| 1658 |
+
"loss": 1.9536,
|
| 1659 |
+
"step": 1150
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 0.2781456953642384,
|
| 1663 |
+
"grad_norm": 3.9880380630493164,
|
| 1664 |
+
"learning_rate": 1.4436416184971101e-05,
|
| 1665 |
+
"loss": 1.7441,
|
| 1666 |
+
"step": 1155
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 0.27934978928356413,
|
| 1670 |
+
"grad_norm": 3.2457761764526367,
|
| 1671 |
+
"learning_rate": 1.4412331406551062e-05,
|
| 1672 |
+
"loss": 2.0117,
|
| 1673 |
+
"step": 1160
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 0.2805538832028898,
|
| 1677 |
+
"grad_norm": 2.9482262134552,
|
| 1678 |
+
"learning_rate": 1.4388246628131022e-05,
|
| 1679 |
+
"loss": 1.9502,
|
| 1680 |
+
"step": 1165
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 0.2817579771222155,
|
| 1684 |
+
"grad_norm": 3.3882107734680176,
|
| 1685 |
+
"learning_rate": 1.4364161849710985e-05,
|
| 1686 |
+
"loss": 1.9861,
|
| 1687 |
+
"step": 1170
|
| 1688 |
+
},
|
| 1689 |
+
{
|
| 1690 |
+
"epoch": 0.28296207104154125,
|
| 1691 |
+
"grad_norm": 3.379577398300171,
|
| 1692 |
+
"learning_rate": 1.4340077071290945e-05,
|
| 1693 |
+
"loss": 2.0115,
|
| 1694 |
+
"step": 1175
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 0.28416616496086694,
|
| 1698 |
+
"grad_norm": 3.02996826171875,
|
| 1699 |
+
"learning_rate": 1.4315992292870906e-05,
|
| 1700 |
+
"loss": 1.9103,
|
| 1701 |
+
"step": 1180
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 0.28537025888019263,
|
| 1705 |
+
"grad_norm": 2.9293081760406494,
|
| 1706 |
+
"learning_rate": 1.4291907514450868e-05,
|
| 1707 |
+
"loss": 1.9432,
|
| 1708 |
+
"step": 1185
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 0.2865743527995184,
|
| 1712 |
+
"grad_norm": 3.3768506050109863,
|
| 1713 |
+
"learning_rate": 1.4267822736030829e-05,
|
| 1714 |
+
"loss": 1.8372,
|
| 1715 |
+
"step": 1190
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 0.28777844671884406,
|
| 1719 |
+
"grad_norm": 3.0163660049438477,
|
| 1720 |
+
"learning_rate": 1.424373795761079e-05,
|
| 1721 |
+
"loss": 1.7784,
|
| 1722 |
+
"step": 1195
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 0.2889825406381698,
|
| 1726 |
+
"grad_norm": 3.591684103012085,
|
| 1727 |
+
"learning_rate": 1.4219653179190754e-05,
|
| 1728 |
+
"loss": 1.9951,
|
| 1729 |
+
"step": 1200
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 0.2889825406381698,
|
| 1733 |
+
"eval_loss": 1.9316246509552002,
|
| 1734 |
+
"eval_runtime": 16.3758,
|
| 1735 |
+
"eval_samples_per_second": 6.107,
|
| 1736 |
+
"eval_steps_per_second": 0.794,
|
| 1737 |
+
"step": 1200
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 0.2901866345574955,
|
| 1741 |
+
"grad_norm": 3.3553686141967773,
|
| 1742 |
+
"learning_rate": 1.4195568400770714e-05,
|
| 1743 |
+
"loss": 1.8822,
|
| 1744 |
+
"step": 1205
|
| 1745 |
+
},
|
| 1746 |
+
{
|
| 1747 |
+
"epoch": 0.2913907284768212,
|
| 1748 |
+
"grad_norm": 3.1767303943634033,
|
| 1749 |
+
"learning_rate": 1.4171483622350675e-05,
|
| 1750 |
+
"loss": 1.9386,
|
| 1751 |
+
"step": 1210
|
| 1752 |
+
},
|
| 1753 |
+
{
|
| 1754 |
+
"epoch": 0.2925948223961469,
|
| 1755 |
+
"grad_norm": 3.6845219135284424,
|
| 1756 |
+
"learning_rate": 1.4147398843930637e-05,
|
| 1757 |
+
"loss": 1.8512,
|
| 1758 |
+
"step": 1215
|
| 1759 |
+
},
|
| 1760 |
+
{
|
| 1761 |
+
"epoch": 0.2937989163154726,
|
| 1762 |
+
"grad_norm": 3.189955949783325,
|
| 1763 |
+
"learning_rate": 1.4123314065510598e-05,
|
| 1764 |
+
"loss": 1.9804,
|
| 1765 |
+
"step": 1220
|
| 1766 |
+
},
|
| 1767 |
+
{
|
| 1768 |
+
"epoch": 0.2950030102347983,
|
| 1769 |
+
"grad_norm": 3.7629036903381348,
|
| 1770 |
+
"learning_rate": 1.4099229287090558e-05,
|
| 1771 |
+
"loss": 1.9759,
|
| 1772 |
+
"step": 1225
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 0.29620710415412405,
|
| 1776 |
+
"grad_norm": 3.6975581645965576,
|
| 1777 |
+
"learning_rate": 1.4075144508670523e-05,
|
| 1778 |
+
"loss": 2.0106,
|
| 1779 |
+
"step": 1230
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 0.29741119807344973,
|
| 1783 |
+
"grad_norm": 3.1638119220733643,
|
| 1784 |
+
"learning_rate": 1.4051059730250483e-05,
|
| 1785 |
+
"loss": 1.9846,
|
| 1786 |
+
"step": 1235
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 0.2986152919927754,
|
| 1790 |
+
"grad_norm": 3.2830159664154053,
|
| 1791 |
+
"learning_rate": 1.4026974951830444e-05,
|
| 1792 |
+
"loss": 2.0757,
|
| 1793 |
+
"step": 1240
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 0.29981938591210117,
|
| 1797 |
+
"grad_norm": 3.1656594276428223,
|
| 1798 |
+
"learning_rate": 1.4002890173410406e-05,
|
| 1799 |
+
"loss": 1.9831,
|
| 1800 |
+
"step": 1245
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 0.30102347983142685,
|
| 1804 |
+
"grad_norm": 3.056269407272339,
|
| 1805 |
+
"learning_rate": 1.3978805394990367e-05,
|
| 1806 |
+
"loss": 1.897,
|
| 1807 |
+
"step": 1250
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 0.30222757375075254,
|
| 1811 |
+
"grad_norm": 3.1246907711029053,
|
| 1812 |
+
"learning_rate": 1.3954720616570329e-05,
|
| 1813 |
+
"loss": 1.9663,
|
| 1814 |
+
"step": 1255
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 0.3034316676700783,
|
| 1818 |
+
"grad_norm": 2.964416980743408,
|
| 1819 |
+
"learning_rate": 1.393063583815029e-05,
|
| 1820 |
+
"loss": 2.0476,
|
| 1821 |
+
"step": 1260
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 0.304635761589404,
|
| 1825 |
+
"grad_norm": 3.241818904876709,
|
| 1826 |
+
"learning_rate": 1.390655105973025e-05,
|
| 1827 |
+
"loss": 2.0771,
|
| 1828 |
+
"step": 1265
|
| 1829 |
+
},
|
| 1830 |
+
{
|
| 1831 |
+
"epoch": 0.30583985550872966,
|
| 1832 |
+
"grad_norm": 3.29571795463562,
|
| 1833 |
+
"learning_rate": 1.3882466281310214e-05,
|
| 1834 |
+
"loss": 2.0502,
|
| 1835 |
+
"step": 1270
|
| 1836 |
+
},
|
| 1837 |
+
{
|
| 1838 |
+
"epoch": 0.3070439494280554,
|
| 1839 |
+
"grad_norm": 3.6429920196533203,
|
| 1840 |
+
"learning_rate": 1.3858381502890175e-05,
|
| 1841 |
+
"loss": 2.0583,
|
| 1842 |
+
"step": 1275
|
| 1843 |
+
},
|
| 1844 |
+
{
|
| 1845 |
+
"epoch": 0.3082480433473811,
|
| 1846 |
+
"grad_norm": 3.16072416305542,
|
| 1847 |
+
"learning_rate": 1.3834296724470136e-05,
|
| 1848 |
+
"loss": 1.8808,
|
| 1849 |
+
"step": 1280
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 0.3094521372667068,
|
| 1853 |
+
"grad_norm": 3.2263102531433105,
|
| 1854 |
+
"learning_rate": 1.3810211946050098e-05,
|
| 1855 |
+
"loss": 1.8824,
|
| 1856 |
+
"step": 1285
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 0.3106562311860325,
|
| 1860 |
+
"grad_norm": 3.2608978748321533,
|
| 1861 |
+
"learning_rate": 1.3786127167630059e-05,
|
| 1862 |
+
"loss": 1.8209,
|
| 1863 |
+
"step": 1290
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 0.3118603251053582,
|
| 1867 |
+
"grad_norm": 3.1739134788513184,
|
| 1868 |
+
"learning_rate": 1.376204238921002e-05,
|
| 1869 |
+
"loss": 2.0042,
|
| 1870 |
+
"step": 1295
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"epoch": 0.3130644190246839,
|
| 1874 |
+
"grad_norm": 3.8513424396514893,
|
| 1875 |
+
"learning_rate": 1.3737957610789983e-05,
|
| 1876 |
+
"loss": 1.9969,
|
| 1877 |
+
"step": 1300
|
| 1878 |
+
},
|
| 1879 |
+
{
|
| 1880 |
+
"epoch": 0.31426851294400965,
|
| 1881 |
+
"grad_norm": 2.987257957458496,
|
| 1882 |
+
"learning_rate": 1.3713872832369944e-05,
|
| 1883 |
+
"loss": 1.8387,
|
| 1884 |
+
"step": 1305
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"epoch": 0.31547260686333534,
|
| 1888 |
+
"grad_norm": 3.1317367553710938,
|
| 1889 |
+
"learning_rate": 1.3689788053949905e-05,
|
| 1890 |
+
"loss": 2.0304,
|
| 1891 |
+
"step": 1310
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 0.316676700782661,
|
| 1895 |
+
"grad_norm": 3.459153413772583,
|
| 1896 |
+
"learning_rate": 1.3665703275529867e-05,
|
| 1897 |
+
"loss": 1.977,
|
| 1898 |
+
"step": 1315
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 0.31788079470198677,
|
| 1902 |
+
"grad_norm": 3.1578195095062256,
|
| 1903 |
+
"learning_rate": 1.3641618497109828e-05,
|
| 1904 |
+
"loss": 1.8042,
|
| 1905 |
+
"step": 1320
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 0.31908488862131246,
|
| 1909 |
+
"grad_norm": 3.375023126602173,
|
| 1910 |
+
"learning_rate": 1.3617533718689788e-05,
|
| 1911 |
+
"loss": 1.8485,
|
| 1912 |
+
"step": 1325
|
| 1913 |
+
},
|
| 1914 |
+
{
|
| 1915 |
+
"epoch": 0.32028898254063815,
|
| 1916 |
+
"grad_norm": 3.1867401599884033,
|
| 1917 |
+
"learning_rate": 1.359344894026975e-05,
|
| 1918 |
+
"loss": 1.9303,
|
| 1919 |
+
"step": 1330
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 0.3214930764599639,
|
| 1923 |
+
"grad_norm": 3.303433418273926,
|
| 1924 |
+
"learning_rate": 1.3569364161849711e-05,
|
| 1925 |
+
"loss": 1.8925,
|
| 1926 |
+
"step": 1335
|
| 1927 |
+
},
|
| 1928 |
+
{
|
| 1929 |
+
"epoch": 0.3226971703792896,
|
| 1930 |
+
"grad_norm": 2.990525960922241,
|
| 1931 |
+
"learning_rate": 1.3545279383429672e-05,
|
| 1932 |
+
"loss": 1.8612,
|
| 1933 |
+
"step": 1340
|
| 1934 |
+
},
|
| 1935 |
+
{
|
| 1936 |
+
"epoch": 0.32390126429861527,
|
| 1937 |
+
"grad_norm": 3.570690155029297,
|
| 1938 |
+
"learning_rate": 1.3521194605009636e-05,
|
| 1939 |
+
"loss": 1.9175,
|
| 1940 |
+
"step": 1345
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 0.325105358217941,
|
| 1944 |
+
"grad_norm": 3.3581953048706055,
|
| 1945 |
+
"learning_rate": 1.3497109826589597e-05,
|
| 1946 |
+
"loss": 2.0293,
|
| 1947 |
+
"step": 1350
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 0.3263094521372667,
|
| 1951 |
+
"grad_norm": 3.111626148223877,
|
| 1952 |
+
"learning_rate": 1.3473025048169559e-05,
|
| 1953 |
+
"loss": 1.9314,
|
| 1954 |
+
"step": 1355
|
| 1955 |
+
},
|
| 1956 |
+
{
|
| 1957 |
+
"epoch": 0.32751354605659244,
|
| 1958 |
+
"grad_norm": 2.8977465629577637,
|
| 1959 |
+
"learning_rate": 1.344894026974952e-05,
|
| 1960 |
+
"loss": 1.9008,
|
| 1961 |
+
"step": 1360
|
| 1962 |
+
},
|
| 1963 |
+
{
|
| 1964 |
+
"epoch": 0.32871763997591813,
|
| 1965 |
+
"grad_norm": 3.2835822105407715,
|
| 1966 |
+
"learning_rate": 1.342485549132948e-05,
|
| 1967 |
+
"loss": 1.8344,
|
| 1968 |
+
"step": 1365
|
| 1969 |
+
},
|
| 1970 |
+
{
|
| 1971 |
+
"epoch": 0.3299217338952438,
|
| 1972 |
+
"grad_norm": 3.041848659515381,
|
| 1973 |
+
"learning_rate": 1.3400770712909442e-05,
|
| 1974 |
+
"loss": 2.0046,
|
| 1975 |
+
"step": 1370
|
| 1976 |
+
},
|
| 1977 |
+
{
|
| 1978 |
+
"epoch": 0.33112582781456956,
|
| 1979 |
+
"grad_norm": 3.252289295196533,
|
| 1980 |
+
"learning_rate": 1.3376685934489405e-05,
|
| 1981 |
+
"loss": 2.015,
|
| 1982 |
+
"step": 1375
|
| 1983 |
+
},
|
| 1984 |
+
{
|
| 1985 |
+
"epoch": 0.33232992173389525,
|
| 1986 |
+
"grad_norm": 3.0157580375671387,
|
| 1987 |
+
"learning_rate": 1.3352601156069365e-05,
|
| 1988 |
+
"loss": 1.7938,
|
| 1989 |
+
"step": 1380
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 0.33353401565322094,
|
| 1993 |
+
"grad_norm": 3.2034637928009033,
|
| 1994 |
+
"learning_rate": 1.3328516377649328e-05,
|
| 1995 |
+
"loss": 1.7438,
|
| 1996 |
+
"step": 1385
|
| 1997 |
+
},
|
| 1998 |
+
{
|
| 1999 |
+
"epoch": 0.3347381095725467,
|
| 2000 |
+
"grad_norm": 2.962069034576416,
|
| 2001 |
+
"learning_rate": 1.3304431599229288e-05,
|
| 2002 |
+
"loss": 1.8915,
|
| 2003 |
+
"step": 1390
|
| 2004 |
+
},
|
| 2005 |
+
{
|
| 2006 |
+
"epoch": 0.33594220349187237,
|
| 2007 |
+
"grad_norm": 3.4406933784484863,
|
| 2008 |
+
"learning_rate": 1.3280346820809249e-05,
|
| 2009 |
+
"loss": 1.7684,
|
| 2010 |
+
"step": 1395
|
| 2011 |
+
},
|
| 2012 |
+
{
|
| 2013 |
+
"epoch": 0.33714629741119806,
|
| 2014 |
+
"grad_norm": 3.531928062438965,
|
| 2015 |
+
"learning_rate": 1.3256262042389211e-05,
|
| 2016 |
+
"loss": 1.8796,
|
| 2017 |
+
"step": 1400
|
| 2018 |
+
},
|
| 2019 |
+
{
|
| 2020 |
+
"epoch": 0.33714629741119806,
|
| 2021 |
+
"eval_loss": 1.9124047756195068,
|
| 2022 |
+
"eval_runtime": 16.4823,
|
| 2023 |
+
"eval_samples_per_second": 6.067,
|
| 2024 |
+
"eval_steps_per_second": 0.789,
|
| 2025 |
+
"step": 1400
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.3383503913305238,
|
| 2029 |
+
"grad_norm": 3.052105665206909,
|
| 2030 |
+
"learning_rate": 1.3232177263969172e-05,
|
| 2031 |
+
"loss": 1.8796,
|
| 2032 |
+
"step": 1405
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 0.3395544852498495,
|
| 2036 |
+
"grad_norm": 3.317544460296631,
|
| 2037 |
+
"learning_rate": 1.3208092485549133e-05,
|
| 2038 |
+
"loss": 1.975,
|
| 2039 |
+
"step": 1410
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.3407585791691752,
|
| 2043 |
+
"grad_norm": 3.8019814491271973,
|
| 2044 |
+
"learning_rate": 1.3184007707129097e-05,
|
| 2045 |
+
"loss": 1.8014,
|
| 2046 |
+
"step": 1415
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 0.3419626730885009,
|
| 2050 |
+
"grad_norm": 3.2202208042144775,
|
| 2051 |
+
"learning_rate": 1.3159922928709057e-05,
|
| 2052 |
+
"loss": 2.0098,
|
| 2053 |
+
"step": 1420
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.3431667670078266,
|
| 2057 |
+
"grad_norm": 3.2262189388275146,
|
| 2058 |
+
"learning_rate": 1.3135838150289018e-05,
|
| 2059 |
+
"loss": 1.758,
|
| 2060 |
+
"step": 1425
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 0.3443708609271523,
|
| 2064 |
+
"grad_norm": 3.03486704826355,
|
| 2065 |
+
"learning_rate": 1.311175337186898e-05,
|
| 2066 |
+
"loss": 1.9254,
|
| 2067 |
+
"step": 1430
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.34557495484647804,
|
| 2071 |
+
"grad_norm": 3.063431978225708,
|
| 2072 |
+
"learning_rate": 1.3087668593448941e-05,
|
| 2073 |
+
"loss": 1.9091,
|
| 2074 |
+
"step": 1435
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 0.34677904876580373,
|
| 2078 |
+
"grad_norm": 3.082839012145996,
|
| 2079 |
+
"learning_rate": 1.3063583815028902e-05,
|
| 2080 |
+
"loss": 1.951,
|
| 2081 |
+
"step": 1440
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.3479831426851294,
|
| 2085 |
+
"grad_norm": 3.692833662033081,
|
| 2086 |
+
"learning_rate": 1.3039499036608864e-05,
|
| 2087 |
+
"loss": 1.9771,
|
| 2088 |
+
"step": 1445
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 0.34918723660445516,
|
| 2092 |
+
"grad_norm": 3.4902002811431885,
|
| 2093 |
+
"learning_rate": 1.3015414258188825e-05,
|
| 2094 |
+
"loss": 1.8954,
|
| 2095 |
+
"step": 1450
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.35039133052378085,
|
| 2099 |
+
"grad_norm": 2.9592397212982178,
|
| 2100 |
+
"learning_rate": 1.2991329479768787e-05,
|
| 2101 |
+
"loss": 1.8791,
|
| 2102 |
+
"step": 1455
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 0.35159542444310654,
|
| 2106 |
+
"grad_norm": 3.3300886154174805,
|
| 2107 |
+
"learning_rate": 1.296724470134875e-05,
|
| 2108 |
+
"loss": 1.9712,
|
| 2109 |
+
"step": 1460
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.3527995183624323,
|
| 2113 |
+
"grad_norm": 3.206303834915161,
|
| 2114 |
+
"learning_rate": 1.294315992292871e-05,
|
| 2115 |
+
"loss": 1.8155,
|
| 2116 |
+
"step": 1465
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.354003612281758,
|
| 2120 |
+
"grad_norm": 3.2186410427093506,
|
| 2121 |
+
"learning_rate": 1.2919075144508672e-05,
|
| 2122 |
+
"loss": 1.8583,
|
| 2123 |
+
"step": 1470
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.35520770620108366,
|
| 2127 |
+
"grad_norm": 3.482147216796875,
|
| 2128 |
+
"learning_rate": 1.2894990366088633e-05,
|
| 2129 |
+
"loss": 1.8233,
|
| 2130 |
+
"step": 1475
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 0.3564118001204094,
|
| 2134 |
+
"grad_norm": 3.317288637161255,
|
| 2135 |
+
"learning_rate": 1.2870905587668594e-05,
|
| 2136 |
+
"loss": 2.0094,
|
| 2137 |
+
"step": 1480
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.3576158940397351,
|
| 2141 |
+
"grad_norm": 2.962334632873535,
|
| 2142 |
+
"learning_rate": 1.2846820809248558e-05,
|
| 2143 |
+
"loss": 2.0041,
|
| 2144 |
+
"step": 1485
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 0.3588199879590608,
|
| 2148 |
+
"grad_norm": 3.1497514247894287,
|
| 2149 |
+
"learning_rate": 1.2822736030828518e-05,
|
| 2150 |
+
"loss": 1.8808,
|
| 2151 |
+
"step": 1490
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.3600240818783865,
|
| 2155 |
+
"grad_norm": 3.3814947605133057,
|
| 2156 |
+
"learning_rate": 1.2798651252408479e-05,
|
| 2157 |
+
"loss": 1.8085,
|
| 2158 |
+
"step": 1495
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 0.3612281757977122,
|
| 2162 |
+
"grad_norm": 3.426969051361084,
|
| 2163 |
+
"learning_rate": 1.2774566473988441e-05,
|
| 2164 |
+
"loss": 1.8659,
|
| 2165 |
+
"step": 1500
|
| 2166 |
+
}
|
| 2167 |
+
],
|
| 2168 |
+
"logging_steps": 5,
|
| 2169 |
+
"max_steps": 4152,
|
| 2170 |
+
"num_input_tokens_seen": 0,
|
| 2171 |
+
"num_train_epochs": 1,
|
| 2172 |
+
"save_steps": 500,
|
| 2173 |
+
"stateful_callbacks": {
|
| 2174 |
+
"TrainerControl": {
|
| 2175 |
+
"args": {
|
| 2176 |
+
"should_epoch_stop": false,
|
| 2177 |
+
"should_evaluate": false,
|
| 2178 |
+
"should_log": false,
|
| 2179 |
+
"should_save": true,
|
| 2180 |
+
"should_training_stop": false
|
| 2181 |
+
},
|
| 2182 |
+
"attributes": {}
|
| 2183 |
+
}
|
| 2184 |
+
},
|
| 2185 |
+
"total_flos": 1582373279990880.0,
|
| 2186 |
+
"train_batch_size": 1,
|
| 2187 |
+
"trial_name": null,
|
| 2188 |
+
"trial_params": null
|
| 2189 |
+
}
|
checkpoint-1500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd020aa9333054ccbd44f2f69522647a4bdda52101c5b015e38e78115982722b
|
| 3 |
+
size 5816
|
checkpoint-2000/added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|im_end|>": 32000,
|
| 3 |
+
"<|im_start|>": 32001
|
| 4 |
+
}
|
checkpoint-2000/config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Felladrin/Minueza-32M-Chat",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MistralForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 32000,
|
| 9 |
+
"head_dim": 26,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 312,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 1092,
|
| 14 |
+
"max_position_embeddings": 2048,
|
| 15 |
+
"model_type": "mistral",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 10,
|
| 18 |
+
"num_key_value_heads": 4,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_theta": 10000.0,
|
| 21 |
+
"sliding_window": 1024,
|
| 22 |
+
"tie_word_embeddings": false,
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.48.1",
|
| 25 |
+
"use_cache": false,
|
| 26 |
+
"vocab_size": 32002
|
| 27 |
+
}
|
checkpoint-2000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 32000,
|
| 5 |
+
"transformers_version": "4.48.1"
|
| 6 |
+
}
|
checkpoint-2000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5e5ae12002ae7acfcc7e9e689ac9f7111109f3f0d398163dc5325ba2036c51a
|
| 3 |
+
size 131181272
|
checkpoint-2000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f456a2495078924ddab825fa63567c5c9efa44e8572a8ffcbdb5235f584babf
|
| 3 |
+
size 262419258
|
checkpoint-2000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5edb34d031c0c2b447f3eaadb401a4c1e7e7e6d8c096e28b7092e01a8bd48c92
|
| 3 |
+
size 14244
|
checkpoint-2000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a6a91dbc2ee0881caca567a1c7d4bda579188bc179e9e0441bb8880b35c4bd4
|
| 3 |
+
size 1064
|
checkpoint-2000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|im_end|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|im_end|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
checkpoint-2000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2000/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
checkpoint-2000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "<|im_end|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"32001": {
|
| 39 |
+
"content": "<|im_start|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
}
|
| 46 |
+
},
|
| 47 |
+
"additional_special_tokens": [],
|
| 48 |
+
"bos_token": "<s>",
|
| 49 |
+
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 50 |
+
"clean_up_tokenization_spaces": false,
|
| 51 |
+
"eos_token": "<|im_end|>",
|
| 52 |
+
"extra_special_tokens": {},
|
| 53 |
+
"legacy": true,
|
| 54 |
+
"model_max_length": 2048,
|
| 55 |
+
"pad_token": "<|im_end|>",
|
| 56 |
+
"sp_model_kwargs": {},
|
| 57 |
+
"spaces_between_special_tokens": false,
|
| 58 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 59 |
+
"unk_token": "<unk>",
|
| 60 |
+
"use_default_system_prompt": false
|
| 61 |
+
}
|
checkpoint-2000/trainer_state.json
ADDED
|
@@ -0,0 +1,2913 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.481637567730283,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 2000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0012040939193257074,
|
| 13 |
+
"grad_norm": 4.470886707305908,
|
| 14 |
+
"learning_rate": 1.9975915221579964e-05,
|
| 15 |
+
"loss": 2.6688,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.002408187838651415,
|
| 20 |
+
"grad_norm": 4.067092418670654,
|
| 21 |
+
"learning_rate": 1.9951830443159926e-05,
|
| 22 |
+
"loss": 2.2509,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.003612281757977122,
|
| 27 |
+
"grad_norm": 4.133108615875244,
|
| 28 |
+
"learning_rate": 1.9927745664739885e-05,
|
| 29 |
+
"loss": 2.3732,
|
| 30 |
+
"step": 15
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.00481637567730283,
|
| 34 |
+
"grad_norm": 3.4890763759613037,
|
| 35 |
+
"learning_rate": 1.9903660886319848e-05,
|
| 36 |
+
"loss": 2.3632,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.006020469596628537,
|
| 41 |
+
"grad_norm": 4.1045308113098145,
|
| 42 |
+
"learning_rate": 1.987957610789981e-05,
|
| 43 |
+
"loss": 2.5203,
|
| 44 |
+
"step": 25
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.007224563515954244,
|
| 48 |
+
"grad_norm": 4.26784086227417,
|
| 49 |
+
"learning_rate": 1.985549132947977e-05,
|
| 50 |
+
"loss": 2.3349,
|
| 51 |
+
"step": 30
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.008428657435279952,
|
| 55 |
+
"grad_norm": 4.144766330718994,
|
| 56 |
+
"learning_rate": 1.983140655105973e-05,
|
| 57 |
+
"loss": 2.4106,
|
| 58 |
+
"step": 35
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.00963275135460566,
|
| 62 |
+
"grad_norm": 3.9538934230804443,
|
| 63 |
+
"learning_rate": 1.9807321772639694e-05,
|
| 64 |
+
"loss": 2.3192,
|
| 65 |
+
"step": 40
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.010836845273931367,
|
| 69 |
+
"grad_norm": 3.9219865798950195,
|
| 70 |
+
"learning_rate": 1.9783236994219656e-05,
|
| 71 |
+
"loss": 2.2012,
|
| 72 |
+
"step": 45
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.012040939193257074,
|
| 76 |
+
"grad_norm": 3.391493797302246,
|
| 77 |
+
"learning_rate": 1.9759152215799615e-05,
|
| 78 |
+
"loss": 2.4064,
|
| 79 |
+
"step": 50
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.013245033112582781,
|
| 83 |
+
"grad_norm": 4.393350124359131,
|
| 84 |
+
"learning_rate": 1.9735067437379577e-05,
|
| 85 |
+
"loss": 2.1513,
|
| 86 |
+
"step": 55
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.014449127031908489,
|
| 90 |
+
"grad_norm": 3.6243207454681396,
|
| 91 |
+
"learning_rate": 1.971098265895954e-05,
|
| 92 |
+
"loss": 2.2788,
|
| 93 |
+
"step": 60
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.015653220951234198,
|
| 97 |
+
"grad_norm": 3.642468214035034,
|
| 98 |
+
"learning_rate": 1.9686897880539502e-05,
|
| 99 |
+
"loss": 2.2244,
|
| 100 |
+
"step": 65
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.016857314870559904,
|
| 104 |
+
"grad_norm": 4.0894670486450195,
|
| 105 |
+
"learning_rate": 1.966281310211946e-05,
|
| 106 |
+
"loss": 2.3622,
|
| 107 |
+
"step": 70
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.018061408789885613,
|
| 111 |
+
"grad_norm": 4.033819198608398,
|
| 112 |
+
"learning_rate": 1.9638728323699423e-05,
|
| 113 |
+
"loss": 2.3803,
|
| 114 |
+
"step": 75
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.01926550270921132,
|
| 118 |
+
"grad_norm": 3.535987138748169,
|
| 119 |
+
"learning_rate": 1.9614643545279385e-05,
|
| 120 |
+
"loss": 2.2161,
|
| 121 |
+
"step": 80
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.020469596628537028,
|
| 125 |
+
"grad_norm": 3.541868209838867,
|
| 126 |
+
"learning_rate": 1.9590558766859348e-05,
|
| 127 |
+
"loss": 2.1721,
|
| 128 |
+
"step": 85
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.021673690547862733,
|
| 132 |
+
"grad_norm": 4.147072792053223,
|
| 133 |
+
"learning_rate": 1.9566473988439307e-05,
|
| 134 |
+
"loss": 2.3239,
|
| 135 |
+
"step": 90
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.022877784467188442,
|
| 139 |
+
"grad_norm": 3.4949986934661865,
|
| 140 |
+
"learning_rate": 1.954238921001927e-05,
|
| 141 |
+
"loss": 2.265,
|
| 142 |
+
"step": 95
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.024081878386514148,
|
| 146 |
+
"grad_norm": 3.793950319290161,
|
| 147 |
+
"learning_rate": 1.951830443159923e-05,
|
| 148 |
+
"loss": 2.152,
|
| 149 |
+
"step": 100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.025285972305839857,
|
| 153 |
+
"grad_norm": 3.9355053901672363,
|
| 154 |
+
"learning_rate": 1.949421965317919e-05,
|
| 155 |
+
"loss": 2.2534,
|
| 156 |
+
"step": 105
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.026490066225165563,
|
| 160 |
+
"grad_norm": 3.255175828933716,
|
| 161 |
+
"learning_rate": 1.9470134874759156e-05,
|
| 162 |
+
"loss": 2.2971,
|
| 163 |
+
"step": 110
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.027694160144491272,
|
| 167 |
+
"grad_norm": 3.650298595428467,
|
| 168 |
+
"learning_rate": 1.9446050096339115e-05,
|
| 169 |
+
"loss": 2.1228,
|
| 170 |
+
"step": 115
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.028898254063816978,
|
| 174 |
+
"grad_norm": 3.1906814575195312,
|
| 175 |
+
"learning_rate": 1.9421965317919077e-05,
|
| 176 |
+
"loss": 2.0995,
|
| 177 |
+
"step": 120
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.030102347983142687,
|
| 181 |
+
"grad_norm": 3.8122494220733643,
|
| 182 |
+
"learning_rate": 1.939788053949904e-05,
|
| 183 |
+
"loss": 2.1651,
|
| 184 |
+
"step": 125
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.031306441902468396,
|
| 188 |
+
"grad_norm": 3.8269336223602295,
|
| 189 |
+
"learning_rate": 1.9373795761079e-05,
|
| 190 |
+
"loss": 2.1731,
|
| 191 |
+
"step": 130
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.0325105358217941,
|
| 195 |
+
"grad_norm": 3.75238037109375,
|
| 196 |
+
"learning_rate": 1.934971098265896e-05,
|
| 197 |
+
"loss": 2.3071,
|
| 198 |
+
"step": 135
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.03371462974111981,
|
| 202 |
+
"grad_norm": 3.538330078125,
|
| 203 |
+
"learning_rate": 1.9325626204238923e-05,
|
| 204 |
+
"loss": 2.3015,
|
| 205 |
+
"step": 140
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.034918723660445516,
|
| 209 |
+
"grad_norm": 3.497131586074829,
|
| 210 |
+
"learning_rate": 1.9301541425818882e-05,
|
| 211 |
+
"loss": 2.128,
|
| 212 |
+
"step": 145
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.036122817579771226,
|
| 216 |
+
"grad_norm": 3.6173276901245117,
|
| 217 |
+
"learning_rate": 1.9277456647398845e-05,
|
| 218 |
+
"loss": 2.1792,
|
| 219 |
+
"step": 150
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.03732691149909693,
|
| 223 |
+
"grad_norm": 3.2987892627716064,
|
| 224 |
+
"learning_rate": 1.9253371868978807e-05,
|
| 225 |
+
"loss": 2.0246,
|
| 226 |
+
"step": 155
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.03853100541842264,
|
| 230 |
+
"grad_norm": 3.1787831783294678,
|
| 231 |
+
"learning_rate": 1.922928709055877e-05,
|
| 232 |
+
"loss": 2.2108,
|
| 233 |
+
"step": 160
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.039735099337748346,
|
| 237 |
+
"grad_norm": 3.5422236919403076,
|
| 238 |
+
"learning_rate": 1.920520231213873e-05,
|
| 239 |
+
"loss": 2.1738,
|
| 240 |
+
"step": 165
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.040939193257074055,
|
| 244 |
+
"grad_norm": 3.7987539768218994,
|
| 245 |
+
"learning_rate": 1.918111753371869e-05,
|
| 246 |
+
"loss": 2.1161,
|
| 247 |
+
"step": 170
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.04214328717639976,
|
| 251 |
+
"grad_norm": 3.2058522701263428,
|
| 252 |
+
"learning_rate": 1.9157032755298653e-05,
|
| 253 |
+
"loss": 2.0808,
|
| 254 |
+
"step": 175
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.04334738109572547,
|
| 258 |
+
"grad_norm": 3.00519061088562,
|
| 259 |
+
"learning_rate": 1.9132947976878615e-05,
|
| 260 |
+
"loss": 2.1412,
|
| 261 |
+
"step": 180
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.044551475015051176,
|
| 265 |
+
"grad_norm": 3.4471330642700195,
|
| 266 |
+
"learning_rate": 1.9108863198458578e-05,
|
| 267 |
+
"loss": 2.1695,
|
| 268 |
+
"step": 185
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.045755568934376885,
|
| 272 |
+
"grad_norm": 3.394496440887451,
|
| 273 |
+
"learning_rate": 1.9084778420038536e-05,
|
| 274 |
+
"loss": 1.9532,
|
| 275 |
+
"step": 190
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.04695966285370259,
|
| 279 |
+
"grad_norm": 3.03004789352417,
|
| 280 |
+
"learning_rate": 1.90606936416185e-05,
|
| 281 |
+
"loss": 2.0659,
|
| 282 |
+
"step": 195
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.048163756773028296,
|
| 286 |
+
"grad_norm": 3.4260365962982178,
|
| 287 |
+
"learning_rate": 1.903660886319846e-05,
|
| 288 |
+
"loss": 2.0792,
|
| 289 |
+
"step": 200
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.048163756773028296,
|
| 293 |
+
"eval_loss": 2.1430513858795166,
|
| 294 |
+
"eval_runtime": 16.4051,
|
| 295 |
+
"eval_samples_per_second": 6.096,
|
| 296 |
+
"eval_steps_per_second": 0.792,
|
| 297 |
+
"step": 200
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.049367850692354005,
|
| 301 |
+
"grad_norm": 4.670680999755859,
|
| 302 |
+
"learning_rate": 1.901252408477842e-05,
|
| 303 |
+
"loss": 2.0952,
|
| 304 |
+
"step": 205
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.050571944611679714,
|
| 308 |
+
"grad_norm": 3.510042667388916,
|
| 309 |
+
"learning_rate": 1.8988439306358382e-05,
|
| 310 |
+
"loss": 2.195,
|
| 311 |
+
"step": 210
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.05177603853100542,
|
| 315 |
+
"grad_norm": 3.0459847450256348,
|
| 316 |
+
"learning_rate": 1.8964354527938345e-05,
|
| 317 |
+
"loss": 2.2117,
|
| 318 |
+
"step": 215
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.052980132450331126,
|
| 322 |
+
"grad_norm": 4.36016321182251,
|
| 323 |
+
"learning_rate": 1.8940269749518304e-05,
|
| 324 |
+
"loss": 2.1191,
|
| 325 |
+
"step": 220
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.054184226369656835,
|
| 329 |
+
"grad_norm": 3.0498242378234863,
|
| 330 |
+
"learning_rate": 1.891618497109827e-05,
|
| 331 |
+
"loss": 2.0838,
|
| 332 |
+
"step": 225
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.055388320288982544,
|
| 336 |
+
"grad_norm": 3.218038558959961,
|
| 337 |
+
"learning_rate": 1.889210019267823e-05,
|
| 338 |
+
"loss": 2.1118,
|
| 339 |
+
"step": 230
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.056592414208308246,
|
| 343 |
+
"grad_norm": 3.3144683837890625,
|
| 344 |
+
"learning_rate": 1.886801541425819e-05,
|
| 345 |
+
"loss": 2.2176,
|
| 346 |
+
"step": 235
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.057796508127633955,
|
| 350 |
+
"grad_norm": 3.2364652156829834,
|
| 351 |
+
"learning_rate": 1.8843930635838153e-05,
|
| 352 |
+
"loss": 2.112,
|
| 353 |
+
"step": 240
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.059000602046959665,
|
| 357 |
+
"grad_norm": 3.291278839111328,
|
| 358 |
+
"learning_rate": 1.8819845857418112e-05,
|
| 359 |
+
"loss": 2.144,
|
| 360 |
+
"step": 245
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.060204695966285374,
|
| 364 |
+
"grad_norm": 3.65297794342041,
|
| 365 |
+
"learning_rate": 1.8795761078998074e-05,
|
| 366 |
+
"loss": 2.2597,
|
| 367 |
+
"step": 250
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.061408789885611076,
|
| 371 |
+
"grad_norm": 3.2321982383728027,
|
| 372 |
+
"learning_rate": 1.8771676300578037e-05,
|
| 373 |
+
"loss": 2.1618,
|
| 374 |
+
"step": 255
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.06261288380493679,
|
| 378 |
+
"grad_norm": 3.352842330932617,
|
| 379 |
+
"learning_rate": 1.8747591522158e-05,
|
| 380 |
+
"loss": 2.006,
|
| 381 |
+
"step": 260
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.0638169777242625,
|
| 385 |
+
"grad_norm": 3.5657215118408203,
|
| 386 |
+
"learning_rate": 1.8723506743737958e-05,
|
| 387 |
+
"loss": 2.2253,
|
| 388 |
+
"step": 265
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.0650210716435882,
|
| 392 |
+
"grad_norm": 3.060060739517212,
|
| 393 |
+
"learning_rate": 1.869942196531792e-05,
|
| 394 |
+
"loss": 2.1187,
|
| 395 |
+
"step": 270
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.06622516556291391,
|
| 399 |
+
"grad_norm": 3.473719835281372,
|
| 400 |
+
"learning_rate": 1.8675337186897883e-05,
|
| 401 |
+
"loss": 2.0299,
|
| 402 |
+
"step": 275
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.06742925948223961,
|
| 406 |
+
"grad_norm": 3.1167919635772705,
|
| 407 |
+
"learning_rate": 1.8651252408477845e-05,
|
| 408 |
+
"loss": 2.0381,
|
| 409 |
+
"step": 280
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.06863335340156532,
|
| 413 |
+
"grad_norm": 3.815816640853882,
|
| 414 |
+
"learning_rate": 1.8627167630057804e-05,
|
| 415 |
+
"loss": 2.1624,
|
| 416 |
+
"step": 285
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.06983744732089103,
|
| 420 |
+
"grad_norm": 3.2820959091186523,
|
| 421 |
+
"learning_rate": 1.8603082851637766e-05,
|
| 422 |
+
"loss": 2.0819,
|
| 423 |
+
"step": 290
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.07104154124021674,
|
| 427 |
+
"grad_norm": 3.568885087966919,
|
| 428 |
+
"learning_rate": 1.857899807321773e-05,
|
| 429 |
+
"loss": 2.0749,
|
| 430 |
+
"step": 295
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.07224563515954245,
|
| 434 |
+
"grad_norm": 3.424076795578003,
|
| 435 |
+
"learning_rate": 1.855491329479769e-05,
|
| 436 |
+
"loss": 2.129,
|
| 437 |
+
"step": 300
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.07344972907886815,
|
| 441 |
+
"grad_norm": 3.2800493240356445,
|
| 442 |
+
"learning_rate": 1.853082851637765e-05,
|
| 443 |
+
"loss": 2.2067,
|
| 444 |
+
"step": 305
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.07465382299819386,
|
| 448 |
+
"grad_norm": 3.487868547439575,
|
| 449 |
+
"learning_rate": 1.8506743737957612e-05,
|
| 450 |
+
"loss": 2.124,
|
| 451 |
+
"step": 310
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.07585791691751957,
|
| 455 |
+
"grad_norm": 3.3999245166778564,
|
| 456 |
+
"learning_rate": 1.8482658959537575e-05,
|
| 457 |
+
"loss": 1.9888,
|
| 458 |
+
"step": 315
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.07706201083684527,
|
| 462 |
+
"grad_norm": 3.973482370376587,
|
| 463 |
+
"learning_rate": 1.8458574181117533e-05,
|
| 464 |
+
"loss": 2.0592,
|
| 465 |
+
"step": 320
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.07826610475617098,
|
| 469 |
+
"grad_norm": 2.9601657390594482,
|
| 470 |
+
"learning_rate": 1.8434489402697496e-05,
|
| 471 |
+
"loss": 2.1022,
|
| 472 |
+
"step": 325
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.07947019867549669,
|
| 476 |
+
"grad_norm": 3.260118246078491,
|
| 477 |
+
"learning_rate": 1.8410404624277458e-05,
|
| 478 |
+
"loss": 1.9763,
|
| 479 |
+
"step": 330
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.0806742925948224,
|
| 483 |
+
"grad_norm": 3.509838819503784,
|
| 484 |
+
"learning_rate": 1.838631984585742e-05,
|
| 485 |
+
"loss": 2.0284,
|
| 486 |
+
"step": 335
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.08187838651414811,
|
| 490 |
+
"grad_norm": 4.363494396209717,
|
| 491 |
+
"learning_rate": 1.8362235067437383e-05,
|
| 492 |
+
"loss": 2.0479,
|
| 493 |
+
"step": 340
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.08308248043347381,
|
| 497 |
+
"grad_norm": 3.2578630447387695,
|
| 498 |
+
"learning_rate": 1.8338150289017342e-05,
|
| 499 |
+
"loss": 2.0488,
|
| 500 |
+
"step": 345
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.08428657435279951,
|
| 504 |
+
"grad_norm": 3.2846531867980957,
|
| 505 |
+
"learning_rate": 1.8314065510597304e-05,
|
| 506 |
+
"loss": 2.0876,
|
| 507 |
+
"step": 350
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.08549066827212523,
|
| 511 |
+
"grad_norm": 3.3275203704833984,
|
| 512 |
+
"learning_rate": 1.8289980732177266e-05,
|
| 513 |
+
"loss": 2.0564,
|
| 514 |
+
"step": 355
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.08669476219145093,
|
| 518 |
+
"grad_norm": 3.1368625164031982,
|
| 519 |
+
"learning_rate": 1.8265895953757225e-05,
|
| 520 |
+
"loss": 2.1533,
|
| 521 |
+
"step": 360
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.08789885611077664,
|
| 525 |
+
"grad_norm": 3.3824191093444824,
|
| 526 |
+
"learning_rate": 1.8241811175337188e-05,
|
| 527 |
+
"loss": 2.1821,
|
| 528 |
+
"step": 365
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.08910295003010235,
|
| 532 |
+
"grad_norm": 3.5150134563446045,
|
| 533 |
+
"learning_rate": 1.821772639691715e-05,
|
| 534 |
+
"loss": 2.0292,
|
| 535 |
+
"step": 370
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.09030704394942805,
|
| 539 |
+
"grad_norm": 3.421921730041504,
|
| 540 |
+
"learning_rate": 1.8193641618497112e-05,
|
| 541 |
+
"loss": 1.9862,
|
| 542 |
+
"step": 375
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.09151113786875377,
|
| 546 |
+
"grad_norm": 3.616887092590332,
|
| 547 |
+
"learning_rate": 1.8169556840077075e-05,
|
| 548 |
+
"loss": 2.0158,
|
| 549 |
+
"step": 380
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.09271523178807947,
|
| 553 |
+
"grad_norm": 5.063056945800781,
|
| 554 |
+
"learning_rate": 1.8145472061657034e-05,
|
| 555 |
+
"loss": 2.0579,
|
| 556 |
+
"step": 385
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.09391932570740517,
|
| 560 |
+
"grad_norm": 3.5242559909820557,
|
| 561 |
+
"learning_rate": 1.8121387283236996e-05,
|
| 562 |
+
"loss": 2.0272,
|
| 563 |
+
"step": 390
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.09512341962673089,
|
| 567 |
+
"grad_norm": 3.2852962017059326,
|
| 568 |
+
"learning_rate": 1.809730250481696e-05,
|
| 569 |
+
"loss": 2.077,
|
| 570 |
+
"step": 395
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.09632751354605659,
|
| 574 |
+
"grad_norm": 3.710927963256836,
|
| 575 |
+
"learning_rate": 1.8073217726396917e-05,
|
| 576 |
+
"loss": 2.1271,
|
| 577 |
+
"step": 400
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.09632751354605659,
|
| 581 |
+
"eval_loss": 2.0655810832977295,
|
| 582 |
+
"eval_runtime": 16.3755,
|
| 583 |
+
"eval_samples_per_second": 6.107,
|
| 584 |
+
"eval_steps_per_second": 0.794,
|
| 585 |
+
"step": 400
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.0975316074653823,
|
| 589 |
+
"grad_norm": 3.5019216537475586,
|
| 590 |
+
"learning_rate": 1.804913294797688e-05,
|
| 591 |
+
"loss": 2.1081,
|
| 592 |
+
"step": 405
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.09873570138470801,
|
| 596 |
+
"grad_norm": 3.5533690452575684,
|
| 597 |
+
"learning_rate": 1.8025048169556842e-05,
|
| 598 |
+
"loss": 2.0751,
|
| 599 |
+
"step": 410
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.09993979530403371,
|
| 603 |
+
"grad_norm": 3.4970240592956543,
|
| 604 |
+
"learning_rate": 1.8000963391136804e-05,
|
| 605 |
+
"loss": 2.066,
|
| 606 |
+
"step": 415
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.10114388922335943,
|
| 610 |
+
"grad_norm": 3.0926427841186523,
|
| 611 |
+
"learning_rate": 1.7976878612716763e-05,
|
| 612 |
+
"loss": 2.0516,
|
| 613 |
+
"step": 420
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.10234798314268513,
|
| 617 |
+
"grad_norm": 3.747452974319458,
|
| 618 |
+
"learning_rate": 1.7952793834296726e-05,
|
| 619 |
+
"loss": 2.0721,
|
| 620 |
+
"step": 425
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.10355207706201083,
|
| 624 |
+
"grad_norm": 3.3113677501678467,
|
| 625 |
+
"learning_rate": 1.7928709055876688e-05,
|
| 626 |
+
"loss": 2.1527,
|
| 627 |
+
"step": 430
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.10475617098133655,
|
| 631 |
+
"grad_norm": 3.357912063598633,
|
| 632 |
+
"learning_rate": 1.7904624277456647e-05,
|
| 633 |
+
"loss": 2.0113,
|
| 634 |
+
"step": 435
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.10596026490066225,
|
| 638 |
+
"grad_norm": 3.023893356323242,
|
| 639 |
+
"learning_rate": 1.7880539499036613e-05,
|
| 640 |
+
"loss": 2.1332,
|
| 641 |
+
"step": 440
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.10716435881998795,
|
| 645 |
+
"grad_norm": 3.3027355670928955,
|
| 646 |
+
"learning_rate": 1.785645472061657e-05,
|
| 647 |
+
"loss": 1.9699,
|
| 648 |
+
"step": 445
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.10836845273931367,
|
| 652 |
+
"grad_norm": 5.3524932861328125,
|
| 653 |
+
"learning_rate": 1.7832369942196534e-05,
|
| 654 |
+
"loss": 2.0182,
|
| 655 |
+
"step": 450
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.10957254665863937,
|
| 659 |
+
"grad_norm": 3.200258731842041,
|
| 660 |
+
"learning_rate": 1.7808285163776496e-05,
|
| 661 |
+
"loss": 2.007,
|
| 662 |
+
"step": 455
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.11077664057796509,
|
| 666 |
+
"grad_norm": 3.286268949508667,
|
| 667 |
+
"learning_rate": 1.7784200385356455e-05,
|
| 668 |
+
"loss": 2.0907,
|
| 669 |
+
"step": 460
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.11198073449729079,
|
| 673 |
+
"grad_norm": 3.15291428565979,
|
| 674 |
+
"learning_rate": 1.7760115606936417e-05,
|
| 675 |
+
"loss": 2.0468,
|
| 676 |
+
"step": 465
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.11318482841661649,
|
| 680 |
+
"grad_norm": 3.3798069953918457,
|
| 681 |
+
"learning_rate": 1.773603082851638e-05,
|
| 682 |
+
"loss": 1.9927,
|
| 683 |
+
"step": 470
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.11438892233594221,
|
| 687 |
+
"grad_norm": 3.4220967292785645,
|
| 688 |
+
"learning_rate": 1.771194605009634e-05,
|
| 689 |
+
"loss": 2.1326,
|
| 690 |
+
"step": 475
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.11559301625526791,
|
| 694 |
+
"grad_norm": 3.379628896713257,
|
| 695 |
+
"learning_rate": 1.76878612716763e-05,
|
| 696 |
+
"loss": 1.9202,
|
| 697 |
+
"step": 480
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.11679711017459361,
|
| 701 |
+
"grad_norm": 3.3020846843719482,
|
| 702 |
+
"learning_rate": 1.7663776493256263e-05,
|
| 703 |
+
"loss": 2.1176,
|
| 704 |
+
"step": 485
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.11800120409391933,
|
| 708 |
+
"grad_norm": 3.2711665630340576,
|
| 709 |
+
"learning_rate": 1.7639691714836226e-05,
|
| 710 |
+
"loss": 2.0865,
|
| 711 |
+
"step": 490
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.11920529801324503,
|
| 715 |
+
"grad_norm": 3.239253520965576,
|
| 716 |
+
"learning_rate": 1.7615606936416188e-05,
|
| 717 |
+
"loss": 1.9284,
|
| 718 |
+
"step": 495
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.12040939193257075,
|
| 722 |
+
"grad_norm": 3.4960460662841797,
|
| 723 |
+
"learning_rate": 1.7591522157996147e-05,
|
| 724 |
+
"loss": 2.0088,
|
| 725 |
+
"step": 500
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.12161348585189645,
|
| 729 |
+
"grad_norm": 3.337407350540161,
|
| 730 |
+
"learning_rate": 1.756743737957611e-05,
|
| 731 |
+
"loss": 1.9687,
|
| 732 |
+
"step": 505
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.12281757977122215,
|
| 736 |
+
"grad_norm": 3.534827709197998,
|
| 737 |
+
"learning_rate": 1.754335260115607e-05,
|
| 738 |
+
"loss": 2.0273,
|
| 739 |
+
"step": 510
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 0.12402167369054787,
|
| 743 |
+
"grad_norm": 3.6207938194274902,
|
| 744 |
+
"learning_rate": 1.7519267822736034e-05,
|
| 745 |
+
"loss": 2.0458,
|
| 746 |
+
"step": 515
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.12522576760987358,
|
| 750 |
+
"grad_norm": 3.396012544631958,
|
| 751 |
+
"learning_rate": 1.7495183044315993e-05,
|
| 752 |
+
"loss": 1.9185,
|
| 753 |
+
"step": 520
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.12642986152919927,
|
| 757 |
+
"grad_norm": 3.001236915588379,
|
| 758 |
+
"learning_rate": 1.7471098265895955e-05,
|
| 759 |
+
"loss": 1.9407,
|
| 760 |
+
"step": 525
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.127633955448525,
|
| 764 |
+
"grad_norm": 3.1318376064300537,
|
| 765 |
+
"learning_rate": 1.7447013487475918e-05,
|
| 766 |
+
"loss": 1.8984,
|
| 767 |
+
"step": 530
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.1288380493678507,
|
| 771 |
+
"grad_norm": 3.4541585445404053,
|
| 772 |
+
"learning_rate": 1.7422928709055877e-05,
|
| 773 |
+
"loss": 1.8846,
|
| 774 |
+
"step": 535
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.1300421432871764,
|
| 778 |
+
"grad_norm": 3.311082363128662,
|
| 779 |
+
"learning_rate": 1.739884393063584e-05,
|
| 780 |
+
"loss": 2.0015,
|
| 781 |
+
"step": 540
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 0.1312462372065021,
|
| 785 |
+
"grad_norm": 3.2366561889648438,
|
| 786 |
+
"learning_rate": 1.73747591522158e-05,
|
| 787 |
+
"loss": 2.0176,
|
| 788 |
+
"step": 545
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.13245033112582782,
|
| 792 |
+
"grad_norm": 3.123307943344116,
|
| 793 |
+
"learning_rate": 1.735067437379576e-05,
|
| 794 |
+
"loss": 1.9731,
|
| 795 |
+
"step": 550
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.1336544250451535,
|
| 799 |
+
"grad_norm": 3.776921033859253,
|
| 800 |
+
"learning_rate": 1.7326589595375726e-05,
|
| 801 |
+
"loss": 2.0484,
|
| 802 |
+
"step": 555
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.13485851896447923,
|
| 806 |
+
"grad_norm": 2.959716796875,
|
| 807 |
+
"learning_rate": 1.7302504816955685e-05,
|
| 808 |
+
"loss": 1.9689,
|
| 809 |
+
"step": 560
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.13606261288380495,
|
| 813 |
+
"grad_norm": 3.527384042739868,
|
| 814 |
+
"learning_rate": 1.7278420038535647e-05,
|
| 815 |
+
"loss": 1.9488,
|
| 816 |
+
"step": 565
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 0.13726670680313063,
|
| 820 |
+
"grad_norm": 3.0703189373016357,
|
| 821 |
+
"learning_rate": 1.725433526011561e-05,
|
| 822 |
+
"loss": 2.1226,
|
| 823 |
+
"step": 570
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 0.13847080072245635,
|
| 827 |
+
"grad_norm": 3.1028363704681396,
|
| 828 |
+
"learning_rate": 1.723025048169557e-05,
|
| 829 |
+
"loss": 1.8966,
|
| 830 |
+
"step": 575
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.13967489464178207,
|
| 834 |
+
"grad_norm": 3.340517044067383,
|
| 835 |
+
"learning_rate": 1.720616570327553e-05,
|
| 836 |
+
"loss": 2.2156,
|
| 837 |
+
"step": 580
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.14087898856110775,
|
| 841 |
+
"grad_norm": 3.2740213871002197,
|
| 842 |
+
"learning_rate": 1.7182080924855493e-05,
|
| 843 |
+
"loss": 1.9445,
|
| 844 |
+
"step": 585
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 0.14208308248043347,
|
| 848 |
+
"grad_norm": 3.240690231323242,
|
| 849 |
+
"learning_rate": 1.7157996146435455e-05,
|
| 850 |
+
"loss": 2.0295,
|
| 851 |
+
"step": 590
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 0.1432871763997592,
|
| 855 |
+
"grad_norm": 3.821340799331665,
|
| 856 |
+
"learning_rate": 1.7133911368015418e-05,
|
| 857 |
+
"loss": 2.1401,
|
| 858 |
+
"step": 595
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.1444912703190849,
|
| 862 |
+
"grad_norm": 3.103550910949707,
|
| 863 |
+
"learning_rate": 1.7109826589595377e-05,
|
| 864 |
+
"loss": 2.1164,
|
| 865 |
+
"step": 600
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.1444912703190849,
|
| 869 |
+
"eval_loss": 2.017059564590454,
|
| 870 |
+
"eval_runtime": 16.4324,
|
| 871 |
+
"eval_samples_per_second": 6.086,
|
| 872 |
+
"eval_steps_per_second": 0.791,
|
| 873 |
+
"step": 600
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.1456953642384106,
|
| 877 |
+
"grad_norm": 3.4971117973327637,
|
| 878 |
+
"learning_rate": 1.708574181117534e-05,
|
| 879 |
+
"loss": 1.9864,
|
| 880 |
+
"step": 605
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.1468994581577363,
|
| 884 |
+
"grad_norm": 3.324803590774536,
|
| 885 |
+
"learning_rate": 1.70616570327553e-05,
|
| 886 |
+
"loss": 2.0402,
|
| 887 |
+
"step": 610
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.14810355207706202,
|
| 891 |
+
"grad_norm": 3.302614450454712,
|
| 892 |
+
"learning_rate": 1.703757225433526e-05,
|
| 893 |
+
"loss": 1.9494,
|
| 894 |
+
"step": 615
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.1493076459963877,
|
| 898 |
+
"grad_norm": 3.3090734481811523,
|
| 899 |
+
"learning_rate": 1.7013487475915223e-05,
|
| 900 |
+
"loss": 2.0748,
|
| 901 |
+
"step": 620
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.15051173991571343,
|
| 905 |
+
"grad_norm": 3.559049129486084,
|
| 906 |
+
"learning_rate": 1.6989402697495185e-05,
|
| 907 |
+
"loss": 1.9038,
|
| 908 |
+
"step": 625
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.15171583383503914,
|
| 912 |
+
"grad_norm": 3.5149178504943848,
|
| 913 |
+
"learning_rate": 1.6965317919075147e-05,
|
| 914 |
+
"loss": 2.0261,
|
| 915 |
+
"step": 630
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.15291992775436483,
|
| 919 |
+
"grad_norm": 3.835693120956421,
|
| 920 |
+
"learning_rate": 1.6941233140655106e-05,
|
| 921 |
+
"loss": 1.9453,
|
| 922 |
+
"step": 635
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.15412402167369055,
|
| 926 |
+
"grad_norm": 3.521132469177246,
|
| 927 |
+
"learning_rate": 1.691714836223507e-05,
|
| 928 |
+
"loss": 2.0138,
|
| 929 |
+
"step": 640
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.15532811559301626,
|
| 933 |
+
"grad_norm": 3.2369840145111084,
|
| 934 |
+
"learning_rate": 1.689306358381503e-05,
|
| 935 |
+
"loss": 2.0285,
|
| 936 |
+
"step": 645
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.15653220951234195,
|
| 940 |
+
"grad_norm": 3.1592392921447754,
|
| 941 |
+
"learning_rate": 1.686897880539499e-05,
|
| 942 |
+
"loss": 1.9912,
|
| 943 |
+
"step": 650
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.15773630343166767,
|
| 947 |
+
"grad_norm": 3.2069106101989746,
|
| 948 |
+
"learning_rate": 1.6844894026974952e-05,
|
| 949 |
+
"loss": 2.0159,
|
| 950 |
+
"step": 655
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.15894039735099338,
|
| 954 |
+
"grad_norm": 3.318230390548706,
|
| 955 |
+
"learning_rate": 1.6820809248554915e-05,
|
| 956 |
+
"loss": 2.0412,
|
| 957 |
+
"step": 660
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.16014449127031907,
|
| 961 |
+
"grad_norm": 3.549443244934082,
|
| 962 |
+
"learning_rate": 1.6796724470134877e-05,
|
| 963 |
+
"loss": 2.0014,
|
| 964 |
+
"step": 665
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.1613485851896448,
|
| 968 |
+
"grad_norm": 3.32999324798584,
|
| 969 |
+
"learning_rate": 1.677263969171484e-05,
|
| 970 |
+
"loss": 2.0303,
|
| 971 |
+
"step": 670
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.1625526791089705,
|
| 975 |
+
"grad_norm": 3.262946367263794,
|
| 976 |
+
"learning_rate": 1.6748554913294798e-05,
|
| 977 |
+
"loss": 1.9883,
|
| 978 |
+
"step": 675
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.16375677302829622,
|
| 982 |
+
"grad_norm": 3.484685182571411,
|
| 983 |
+
"learning_rate": 1.672447013487476e-05,
|
| 984 |
+
"loss": 1.9695,
|
| 985 |
+
"step": 680
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.1649608669476219,
|
| 989 |
+
"grad_norm": 3.4177358150482178,
|
| 990 |
+
"learning_rate": 1.6700385356454723e-05,
|
| 991 |
+
"loss": 2.0088,
|
| 992 |
+
"step": 685
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.16616496086694763,
|
| 996 |
+
"grad_norm": 3.447498321533203,
|
| 997 |
+
"learning_rate": 1.6676300578034682e-05,
|
| 998 |
+
"loss": 2.0813,
|
| 999 |
+
"step": 690
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.16736905478627334,
|
| 1003 |
+
"grad_norm": 3.152740240097046,
|
| 1004 |
+
"learning_rate": 1.6652215799614644e-05,
|
| 1005 |
+
"loss": 1.9988,
|
| 1006 |
+
"step": 695
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.16857314870559903,
|
| 1010 |
+
"grad_norm": 3.8948824405670166,
|
| 1011 |
+
"learning_rate": 1.6628131021194607e-05,
|
| 1012 |
+
"loss": 2.0801,
|
| 1013 |
+
"step": 700
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.16977724262492475,
|
| 1017 |
+
"grad_norm": 3.81358003616333,
|
| 1018 |
+
"learning_rate": 1.660404624277457e-05,
|
| 1019 |
+
"loss": 1.944,
|
| 1020 |
+
"step": 705
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.17098133654425046,
|
| 1024 |
+
"grad_norm": 2.980236053466797,
|
| 1025 |
+
"learning_rate": 1.657996146435453e-05,
|
| 1026 |
+
"loss": 1.9151,
|
| 1027 |
+
"step": 710
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.17218543046357615,
|
| 1031 |
+
"grad_norm": 3.041680335998535,
|
| 1032 |
+
"learning_rate": 1.655587668593449e-05,
|
| 1033 |
+
"loss": 1.9486,
|
| 1034 |
+
"step": 715
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.17338952438290187,
|
| 1038 |
+
"grad_norm": 2.898974657058716,
|
| 1039 |
+
"learning_rate": 1.6531791907514452e-05,
|
| 1040 |
+
"loss": 2.1119,
|
| 1041 |
+
"step": 720
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.17459361830222758,
|
| 1045 |
+
"grad_norm": 3.161224603652954,
|
| 1046 |
+
"learning_rate": 1.6507707129094415e-05,
|
| 1047 |
+
"loss": 2.036,
|
| 1048 |
+
"step": 725
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.17579771222155327,
|
| 1052 |
+
"grad_norm": 3.2449426651000977,
|
| 1053 |
+
"learning_rate": 1.6483622350674374e-05,
|
| 1054 |
+
"loss": 2.0635,
|
| 1055 |
+
"step": 730
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.177001806140879,
|
| 1059 |
+
"grad_norm": 3.2805328369140625,
|
| 1060 |
+
"learning_rate": 1.6459537572254336e-05,
|
| 1061 |
+
"loss": 1.8022,
|
| 1062 |
+
"step": 735
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.1782059000602047,
|
| 1066 |
+
"grad_norm": 3.491149663925171,
|
| 1067 |
+
"learning_rate": 1.64354527938343e-05,
|
| 1068 |
+
"loss": 1.9832,
|
| 1069 |
+
"step": 740
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.1794099939795304,
|
| 1073 |
+
"grad_norm": 3.423267126083374,
|
| 1074 |
+
"learning_rate": 1.641136801541426e-05,
|
| 1075 |
+
"loss": 1.9574,
|
| 1076 |
+
"step": 745
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.1806140878988561,
|
| 1080 |
+
"grad_norm": 3.1914217472076416,
|
| 1081 |
+
"learning_rate": 1.638728323699422e-05,
|
| 1082 |
+
"loss": 1.9283,
|
| 1083 |
+
"step": 750
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.18181818181818182,
|
| 1087 |
+
"grad_norm": 3.2903149127960205,
|
| 1088 |
+
"learning_rate": 1.6363198458574182e-05,
|
| 1089 |
+
"loss": 2.1174,
|
| 1090 |
+
"step": 755
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 0.18302227573750754,
|
| 1094 |
+
"grad_norm": 3.113159656524658,
|
| 1095 |
+
"learning_rate": 1.6339113680154144e-05,
|
| 1096 |
+
"loss": 1.8794,
|
| 1097 |
+
"step": 760
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 0.18422636965683323,
|
| 1101 |
+
"grad_norm": 3.261596918106079,
|
| 1102 |
+
"learning_rate": 1.6315028901734103e-05,
|
| 1103 |
+
"loss": 2.0853,
|
| 1104 |
+
"step": 765
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 0.18543046357615894,
|
| 1108 |
+
"grad_norm": 2.9525296688079834,
|
| 1109 |
+
"learning_rate": 1.629094412331407e-05,
|
| 1110 |
+
"loss": 1.8622,
|
| 1111 |
+
"step": 770
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 0.18663455749548466,
|
| 1115 |
+
"grad_norm": 3.2103638648986816,
|
| 1116 |
+
"learning_rate": 1.6266859344894028e-05,
|
| 1117 |
+
"loss": 2.0536,
|
| 1118 |
+
"step": 775
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 0.18783865141481035,
|
| 1122 |
+
"grad_norm": 3.5312676429748535,
|
| 1123 |
+
"learning_rate": 1.624277456647399e-05,
|
| 1124 |
+
"loss": 1.9387,
|
| 1125 |
+
"step": 780
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.18904274533413606,
|
| 1129 |
+
"grad_norm": 3.277223825454712,
|
| 1130 |
+
"learning_rate": 1.6218689788053953e-05,
|
| 1131 |
+
"loss": 1.9804,
|
| 1132 |
+
"step": 785
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 0.19024683925346178,
|
| 1136 |
+
"grad_norm": 3.207287549972534,
|
| 1137 |
+
"learning_rate": 1.619460500963391e-05,
|
| 1138 |
+
"loss": 1.8782,
|
| 1139 |
+
"step": 790
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 0.19145093317278747,
|
| 1143 |
+
"grad_norm": 3.401834487915039,
|
| 1144 |
+
"learning_rate": 1.6170520231213874e-05,
|
| 1145 |
+
"loss": 1.9383,
|
| 1146 |
+
"step": 795
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 0.19265502709211318,
|
| 1150 |
+
"grad_norm": 3.5186078548431396,
|
| 1151 |
+
"learning_rate": 1.6146435452793836e-05,
|
| 1152 |
+
"loss": 2.0963,
|
| 1153 |
+
"step": 800
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 0.19265502709211318,
|
| 1157 |
+
"eval_loss": 1.979533076286316,
|
| 1158 |
+
"eval_runtime": 16.4348,
|
| 1159 |
+
"eval_samples_per_second": 6.085,
|
| 1160 |
+
"eval_steps_per_second": 0.791,
|
| 1161 |
+
"step": 800
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.1938591210114389,
|
| 1165 |
+
"grad_norm": 3.0080161094665527,
|
| 1166 |
+
"learning_rate": 1.6122350674373795e-05,
|
| 1167 |
+
"loss": 1.951,
|
| 1168 |
+
"step": 805
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.1950632149307646,
|
| 1172 |
+
"grad_norm": 3.124155044555664,
|
| 1173 |
+
"learning_rate": 1.6098265895953758e-05,
|
| 1174 |
+
"loss": 1.8663,
|
| 1175 |
+
"step": 810
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.1962673088500903,
|
| 1179 |
+
"grad_norm": 3.6262383460998535,
|
| 1180 |
+
"learning_rate": 1.607418111753372e-05,
|
| 1181 |
+
"loss": 1.9478,
|
| 1182 |
+
"step": 815
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.19747140276941602,
|
| 1186 |
+
"grad_norm": 3.3047947883605957,
|
| 1187 |
+
"learning_rate": 1.6050096339113682e-05,
|
| 1188 |
+
"loss": 1.9203,
|
| 1189 |
+
"step": 820
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.1986754966887417,
|
| 1193 |
+
"grad_norm": 3.0261447429656982,
|
| 1194 |
+
"learning_rate": 1.6026011560693645e-05,
|
| 1195 |
+
"loss": 1.8988,
|
| 1196 |
+
"step": 825
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.19987959060806743,
|
| 1200 |
+
"grad_norm": 4.233884334564209,
|
| 1201 |
+
"learning_rate": 1.6001926782273604e-05,
|
| 1202 |
+
"loss": 2.0327,
|
| 1203 |
+
"step": 830
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.20108368452739314,
|
| 1207 |
+
"grad_norm": 2.9169118404388428,
|
| 1208 |
+
"learning_rate": 1.5977842003853566e-05,
|
| 1209 |
+
"loss": 1.9264,
|
| 1210 |
+
"step": 835
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.20228777844671886,
|
| 1214 |
+
"grad_norm": 3.0078282356262207,
|
| 1215 |
+
"learning_rate": 1.5953757225433528e-05,
|
| 1216 |
+
"loss": 1.8821,
|
| 1217 |
+
"step": 840
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.20349187236604455,
|
| 1221 |
+
"grad_norm": 3.4188835620880127,
|
| 1222 |
+
"learning_rate": 1.592967244701349e-05,
|
| 1223 |
+
"loss": 1.933,
|
| 1224 |
+
"step": 845
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.20469596628537026,
|
| 1228 |
+
"grad_norm": 4.739987850189209,
|
| 1229 |
+
"learning_rate": 1.590558766859345e-05,
|
| 1230 |
+
"loss": 1.9182,
|
| 1231 |
+
"step": 850
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.20590006020469598,
|
| 1235 |
+
"grad_norm": 3.1810977458953857,
|
| 1236 |
+
"learning_rate": 1.5881502890173412e-05,
|
| 1237 |
+
"loss": 1.984,
|
| 1238 |
+
"step": 855
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.20710415412402167,
|
| 1242 |
+
"grad_norm": 3.174739360809326,
|
| 1243 |
+
"learning_rate": 1.5857418111753374e-05,
|
| 1244 |
+
"loss": 1.7719,
|
| 1245 |
+
"step": 860
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.20830824804334738,
|
| 1249 |
+
"grad_norm": 3.379767656326294,
|
| 1250 |
+
"learning_rate": 1.5833333333333333e-05,
|
| 1251 |
+
"loss": 1.9481,
|
| 1252 |
+
"step": 865
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.2095123419626731,
|
| 1256 |
+
"grad_norm": 3.3487260341644287,
|
| 1257 |
+
"learning_rate": 1.5809248554913295e-05,
|
| 1258 |
+
"loss": 1.9416,
|
| 1259 |
+
"step": 870
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.2107164358819988,
|
| 1263 |
+
"grad_norm": 3.4879958629608154,
|
| 1264 |
+
"learning_rate": 1.5785163776493258e-05,
|
| 1265 |
+
"loss": 2.0463,
|
| 1266 |
+
"step": 875
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.2119205298013245,
|
| 1270 |
+
"grad_norm": 3.2338194847106934,
|
| 1271 |
+
"learning_rate": 1.5761078998073217e-05,
|
| 1272 |
+
"loss": 1.9441,
|
| 1273 |
+
"step": 880
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.21312462372065022,
|
| 1277 |
+
"grad_norm": 3.122405529022217,
|
| 1278 |
+
"learning_rate": 1.5736994219653182e-05,
|
| 1279 |
+
"loss": 2.0644,
|
| 1280 |
+
"step": 885
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.2143287176399759,
|
| 1284 |
+
"grad_norm": 3.0773510932922363,
|
| 1285 |
+
"learning_rate": 1.571290944123314e-05,
|
| 1286 |
+
"loss": 1.9415,
|
| 1287 |
+
"step": 890
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.21553281155930162,
|
| 1291 |
+
"grad_norm": 3.004040241241455,
|
| 1292 |
+
"learning_rate": 1.5688824662813104e-05,
|
| 1293 |
+
"loss": 1.9305,
|
| 1294 |
+
"step": 895
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.21673690547862734,
|
| 1298 |
+
"grad_norm": 3.547109603881836,
|
| 1299 |
+
"learning_rate": 1.5664739884393066e-05,
|
| 1300 |
+
"loss": 2.1088,
|
| 1301 |
+
"step": 900
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.21794099939795303,
|
| 1305 |
+
"grad_norm": 3.1982204914093018,
|
| 1306 |
+
"learning_rate": 1.5640655105973025e-05,
|
| 1307 |
+
"loss": 1.8667,
|
| 1308 |
+
"step": 905
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.21914509331727874,
|
| 1312 |
+
"grad_norm": 3.381781578063965,
|
| 1313 |
+
"learning_rate": 1.5616570327552987e-05,
|
| 1314 |
+
"loss": 1.9783,
|
| 1315 |
+
"step": 910
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.22034918723660446,
|
| 1319 |
+
"grad_norm": 2.9775896072387695,
|
| 1320 |
+
"learning_rate": 1.559248554913295e-05,
|
| 1321 |
+
"loss": 2.0211,
|
| 1322 |
+
"step": 915
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.22155328115593018,
|
| 1326 |
+
"grad_norm": 2.864551067352295,
|
| 1327 |
+
"learning_rate": 1.5568400770712912e-05,
|
| 1328 |
+
"loss": 1.8579,
|
| 1329 |
+
"step": 920
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.22275737507525586,
|
| 1333 |
+
"grad_norm": 3.0532050132751465,
|
| 1334 |
+
"learning_rate": 1.5544315992292874e-05,
|
| 1335 |
+
"loss": 1.9398,
|
| 1336 |
+
"step": 925
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.22396146899458158,
|
| 1340 |
+
"grad_norm": 2.859631061553955,
|
| 1341 |
+
"learning_rate": 1.5520231213872833e-05,
|
| 1342 |
+
"loss": 1.8625,
|
| 1343 |
+
"step": 930
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.2251655629139073,
|
| 1347 |
+
"grad_norm": 3.1373536586761475,
|
| 1348 |
+
"learning_rate": 1.5496146435452796e-05,
|
| 1349 |
+
"loss": 1.9003,
|
| 1350 |
+
"step": 935
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.22636965683323299,
|
| 1354 |
+
"grad_norm": 3.3248465061187744,
|
| 1355 |
+
"learning_rate": 1.5472061657032758e-05,
|
| 1356 |
+
"loss": 2.0517,
|
| 1357 |
+
"step": 940
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.2275737507525587,
|
| 1361 |
+
"grad_norm": 3.5990936756134033,
|
| 1362 |
+
"learning_rate": 1.5447976878612717e-05,
|
| 1363 |
+
"loss": 1.8975,
|
| 1364 |
+
"step": 945
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.22877784467188442,
|
| 1368 |
+
"grad_norm": 3.4047725200653076,
|
| 1369 |
+
"learning_rate": 1.542389210019268e-05,
|
| 1370 |
+
"loss": 1.9786,
|
| 1371 |
+
"step": 950
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.2299819385912101,
|
| 1375 |
+
"grad_norm": 3.3326022624969482,
|
| 1376 |
+
"learning_rate": 1.539980732177264e-05,
|
| 1377 |
+
"loss": 1.7848,
|
| 1378 |
+
"step": 955
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.23118603251053582,
|
| 1382 |
+
"grad_norm": 3.2942848205566406,
|
| 1383 |
+
"learning_rate": 1.5375722543352604e-05,
|
| 1384 |
+
"loss": 1.8549,
|
| 1385 |
+
"step": 960
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.23239012642986154,
|
| 1389 |
+
"grad_norm": 3.4602601528167725,
|
| 1390 |
+
"learning_rate": 1.5351637764932563e-05,
|
| 1391 |
+
"loss": 1.917,
|
| 1392 |
+
"step": 965
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.23359422034918723,
|
| 1396 |
+
"grad_norm": 3.591327428817749,
|
| 1397 |
+
"learning_rate": 1.5327552986512525e-05,
|
| 1398 |
+
"loss": 1.9457,
|
| 1399 |
+
"step": 970
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.23479831426851294,
|
| 1403 |
+
"grad_norm": 3.215808868408203,
|
| 1404 |
+
"learning_rate": 1.5303468208092487e-05,
|
| 1405 |
+
"loss": 1.9261,
|
| 1406 |
+
"step": 975
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.23600240818783866,
|
| 1410 |
+
"grad_norm": 3.5032927989959717,
|
| 1411 |
+
"learning_rate": 1.5279383429672446e-05,
|
| 1412 |
+
"loss": 1.967,
|
| 1413 |
+
"step": 980
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.23720650210716435,
|
| 1417 |
+
"grad_norm": 3.1476144790649414,
|
| 1418 |
+
"learning_rate": 1.525529865125241e-05,
|
| 1419 |
+
"loss": 2.0448,
|
| 1420 |
+
"step": 985
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.23841059602649006,
|
| 1424 |
+
"grad_norm": 3.046126365661621,
|
| 1425 |
+
"learning_rate": 1.5231213872832371e-05,
|
| 1426 |
+
"loss": 1.9086,
|
| 1427 |
+
"step": 990
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.23961468994581578,
|
| 1431 |
+
"grad_norm": 3.0403099060058594,
|
| 1432 |
+
"learning_rate": 1.5207129094412332e-05,
|
| 1433 |
+
"loss": 1.9671,
|
| 1434 |
+
"step": 995
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.2408187838651415,
|
| 1438 |
+
"grad_norm": 3.524573802947998,
|
| 1439 |
+
"learning_rate": 1.5183044315992294e-05,
|
| 1440 |
+
"loss": 1.9532,
|
| 1441 |
+
"step": 1000
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.2408187838651415,
|
| 1445 |
+
"eval_loss": 1.9571956396102905,
|
| 1446 |
+
"eval_runtime": 16.4441,
|
| 1447 |
+
"eval_samples_per_second": 6.081,
|
| 1448 |
+
"eval_steps_per_second": 0.791,
|
| 1449 |
+
"step": 1000
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.24202287778446718,
|
| 1453 |
+
"grad_norm": 3.518422842025757,
|
| 1454 |
+
"learning_rate": 1.5158959537572255e-05,
|
| 1455 |
+
"loss": 1.9851,
|
| 1456 |
+
"step": 1005
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 0.2432269717037929,
|
| 1460 |
+
"grad_norm": 3.0476677417755127,
|
| 1461 |
+
"learning_rate": 1.5134874759152215e-05,
|
| 1462 |
+
"loss": 2.0102,
|
| 1463 |
+
"step": 1010
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 0.24443106562311862,
|
| 1467 |
+
"grad_norm": 2.7093968391418457,
|
| 1468 |
+
"learning_rate": 1.511078998073218e-05,
|
| 1469 |
+
"loss": 1.8704,
|
| 1470 |
+
"step": 1015
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 0.2456351595424443,
|
| 1474 |
+
"grad_norm": 2.8607966899871826,
|
| 1475 |
+
"learning_rate": 1.508670520231214e-05,
|
| 1476 |
+
"loss": 1.9948,
|
| 1477 |
+
"step": 1020
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 0.24683925346177002,
|
| 1481 |
+
"grad_norm": 3.224783182144165,
|
| 1482 |
+
"learning_rate": 1.50626204238921e-05,
|
| 1483 |
+
"loss": 1.9097,
|
| 1484 |
+
"step": 1025
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 0.24804334738109574,
|
| 1488 |
+
"grad_norm": 3.199155807495117,
|
| 1489 |
+
"learning_rate": 1.5038535645472063e-05,
|
| 1490 |
+
"loss": 2.0205,
|
| 1491 |
+
"step": 1030
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 0.24924744130042142,
|
| 1495 |
+
"grad_norm": 3.12842059135437,
|
| 1496 |
+
"learning_rate": 1.5014450867052024e-05,
|
| 1497 |
+
"loss": 1.8666,
|
| 1498 |
+
"step": 1035
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 0.25045153521974717,
|
| 1502 |
+
"grad_norm": 3.7331671714782715,
|
| 1503 |
+
"learning_rate": 1.4990366088631986e-05,
|
| 1504 |
+
"loss": 1.913,
|
| 1505 |
+
"step": 1040
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 0.25165562913907286,
|
| 1509 |
+
"grad_norm": 3.0594935417175293,
|
| 1510 |
+
"learning_rate": 1.4966281310211948e-05,
|
| 1511 |
+
"loss": 2.0016,
|
| 1512 |
+
"step": 1045
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 0.25285972305839854,
|
| 1516 |
+
"grad_norm": 3.166200637817383,
|
| 1517 |
+
"learning_rate": 1.4942196531791909e-05,
|
| 1518 |
+
"loss": 1.9481,
|
| 1519 |
+
"step": 1050
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 0.2540638169777243,
|
| 1523 |
+
"grad_norm": 3.08423113822937,
|
| 1524 |
+
"learning_rate": 1.4918111753371871e-05,
|
| 1525 |
+
"loss": 1.9168,
|
| 1526 |
+
"step": 1055
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 0.25526791089705,
|
| 1530 |
+
"grad_norm": 3.7309155464172363,
|
| 1531 |
+
"learning_rate": 1.4894026974951832e-05,
|
| 1532 |
+
"loss": 1.9698,
|
| 1533 |
+
"step": 1060
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 0.25647200481637566,
|
| 1537 |
+
"grad_norm": 3.5642640590667725,
|
| 1538 |
+
"learning_rate": 1.4869942196531793e-05,
|
| 1539 |
+
"loss": 2.0914,
|
| 1540 |
+
"step": 1065
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"epoch": 0.2576760987357014,
|
| 1544 |
+
"grad_norm": 3.201970338821411,
|
| 1545 |
+
"learning_rate": 1.4845857418111755e-05,
|
| 1546 |
+
"loss": 1.9358,
|
| 1547 |
+
"step": 1070
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 0.2588801926550271,
|
| 1551 |
+
"grad_norm": 3.19600510597229,
|
| 1552 |
+
"learning_rate": 1.4821772639691716e-05,
|
| 1553 |
+
"loss": 1.9028,
|
| 1554 |
+
"step": 1075
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 0.2600842865743528,
|
| 1558 |
+
"grad_norm": 2.8048558235168457,
|
| 1559 |
+
"learning_rate": 1.4797687861271676e-05,
|
| 1560 |
+
"loss": 1.9104,
|
| 1561 |
+
"step": 1080
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 0.26128838049367853,
|
| 1565 |
+
"grad_norm": 3.3447604179382324,
|
| 1566 |
+
"learning_rate": 1.477360308285164e-05,
|
| 1567 |
+
"loss": 1.9683,
|
| 1568 |
+
"step": 1085
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 0.2624924744130042,
|
| 1572 |
+
"grad_norm": 3.2456166744232178,
|
| 1573 |
+
"learning_rate": 1.4749518304431601e-05,
|
| 1574 |
+
"loss": 1.9469,
|
| 1575 |
+
"step": 1090
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 0.2636965683323299,
|
| 1579 |
+
"grad_norm": 4.318637847900391,
|
| 1580 |
+
"learning_rate": 1.4725433526011562e-05,
|
| 1581 |
+
"loss": 1.9199,
|
| 1582 |
+
"step": 1095
|
| 1583 |
+
},
|
| 1584 |
+
{
|
| 1585 |
+
"epoch": 0.26490066225165565,
|
| 1586 |
+
"grad_norm": 3.258910655975342,
|
| 1587 |
+
"learning_rate": 1.4701348747591524e-05,
|
| 1588 |
+
"loss": 1.9996,
|
| 1589 |
+
"step": 1100
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"epoch": 0.26610475617098134,
|
| 1593 |
+
"grad_norm": 3.2944164276123047,
|
| 1594 |
+
"learning_rate": 1.4677263969171484e-05,
|
| 1595 |
+
"loss": 1.9373,
|
| 1596 |
+
"step": 1105
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 0.267308850090307,
|
| 1600 |
+
"grad_norm": 2.938908815383911,
|
| 1601 |
+
"learning_rate": 1.4653179190751445e-05,
|
| 1602 |
+
"loss": 1.8301,
|
| 1603 |
+
"step": 1110
|
| 1604 |
+
},
|
| 1605 |
+
{
|
| 1606 |
+
"epoch": 0.26851294400963277,
|
| 1607 |
+
"grad_norm": 3.38433575630188,
|
| 1608 |
+
"learning_rate": 1.4629094412331407e-05,
|
| 1609 |
+
"loss": 2.0615,
|
| 1610 |
+
"step": 1115
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 0.26971703792895846,
|
| 1614 |
+
"grad_norm": 2.9752516746520996,
|
| 1615 |
+
"learning_rate": 1.4605009633911368e-05,
|
| 1616 |
+
"loss": 2.0132,
|
| 1617 |
+
"step": 1120
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 0.27092113184828415,
|
| 1621 |
+
"grad_norm": 2.9489858150482178,
|
| 1622 |
+
"learning_rate": 1.458092485549133e-05,
|
| 1623 |
+
"loss": 1.9319,
|
| 1624 |
+
"step": 1125
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 0.2721252257676099,
|
| 1628 |
+
"grad_norm": 3.231663465499878,
|
| 1629 |
+
"learning_rate": 1.4556840077071293e-05,
|
| 1630 |
+
"loss": 1.8924,
|
| 1631 |
+
"step": 1130
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 0.2733293196869356,
|
| 1635 |
+
"grad_norm": 3.2028298377990723,
|
| 1636 |
+
"learning_rate": 1.4532755298651253e-05,
|
| 1637 |
+
"loss": 1.9836,
|
| 1638 |
+
"step": 1135
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 0.27453341360626127,
|
| 1642 |
+
"grad_norm": 3.348498582839966,
|
| 1643 |
+
"learning_rate": 1.4508670520231216e-05,
|
| 1644 |
+
"loss": 2.0908,
|
| 1645 |
+
"step": 1140
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 0.275737507525587,
|
| 1649 |
+
"grad_norm": 3.1415324211120605,
|
| 1650 |
+
"learning_rate": 1.4484585741811176e-05,
|
| 1651 |
+
"loss": 2.043,
|
| 1652 |
+
"step": 1145
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 0.2769416014449127,
|
| 1656 |
+
"grad_norm": 2.9878766536712646,
|
| 1657 |
+
"learning_rate": 1.4460500963391137e-05,
|
| 1658 |
+
"loss": 1.9536,
|
| 1659 |
+
"step": 1150
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 0.2781456953642384,
|
| 1663 |
+
"grad_norm": 3.9880380630493164,
|
| 1664 |
+
"learning_rate": 1.4436416184971101e-05,
|
| 1665 |
+
"loss": 1.7441,
|
| 1666 |
+
"step": 1155
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 0.27934978928356413,
|
| 1670 |
+
"grad_norm": 3.2457761764526367,
|
| 1671 |
+
"learning_rate": 1.4412331406551062e-05,
|
| 1672 |
+
"loss": 2.0117,
|
| 1673 |
+
"step": 1160
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 0.2805538832028898,
|
| 1677 |
+
"grad_norm": 2.9482262134552,
|
| 1678 |
+
"learning_rate": 1.4388246628131022e-05,
|
| 1679 |
+
"loss": 1.9502,
|
| 1680 |
+
"step": 1165
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 0.2817579771222155,
|
| 1684 |
+
"grad_norm": 3.3882107734680176,
|
| 1685 |
+
"learning_rate": 1.4364161849710985e-05,
|
| 1686 |
+
"loss": 1.9861,
|
| 1687 |
+
"step": 1170
|
| 1688 |
+
},
|
| 1689 |
+
{
|
| 1690 |
+
"epoch": 0.28296207104154125,
|
| 1691 |
+
"grad_norm": 3.379577398300171,
|
| 1692 |
+
"learning_rate": 1.4340077071290945e-05,
|
| 1693 |
+
"loss": 2.0115,
|
| 1694 |
+
"step": 1175
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 0.28416616496086694,
|
| 1698 |
+
"grad_norm": 3.02996826171875,
|
| 1699 |
+
"learning_rate": 1.4315992292870906e-05,
|
| 1700 |
+
"loss": 1.9103,
|
| 1701 |
+
"step": 1180
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 0.28537025888019263,
|
| 1705 |
+
"grad_norm": 2.9293081760406494,
|
| 1706 |
+
"learning_rate": 1.4291907514450868e-05,
|
| 1707 |
+
"loss": 1.9432,
|
| 1708 |
+
"step": 1185
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 0.2865743527995184,
|
| 1712 |
+
"grad_norm": 3.3768506050109863,
|
| 1713 |
+
"learning_rate": 1.4267822736030829e-05,
|
| 1714 |
+
"loss": 1.8372,
|
| 1715 |
+
"step": 1190
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 0.28777844671884406,
|
| 1719 |
+
"grad_norm": 3.0163660049438477,
|
| 1720 |
+
"learning_rate": 1.424373795761079e-05,
|
| 1721 |
+
"loss": 1.7784,
|
| 1722 |
+
"step": 1195
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 0.2889825406381698,
|
| 1726 |
+
"grad_norm": 3.591684103012085,
|
| 1727 |
+
"learning_rate": 1.4219653179190754e-05,
|
| 1728 |
+
"loss": 1.9951,
|
| 1729 |
+
"step": 1200
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 0.2889825406381698,
|
| 1733 |
+
"eval_loss": 1.9316246509552002,
|
| 1734 |
+
"eval_runtime": 16.3758,
|
| 1735 |
+
"eval_samples_per_second": 6.107,
|
| 1736 |
+
"eval_steps_per_second": 0.794,
|
| 1737 |
+
"step": 1200
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 0.2901866345574955,
|
| 1741 |
+
"grad_norm": 3.3553686141967773,
|
| 1742 |
+
"learning_rate": 1.4195568400770714e-05,
|
| 1743 |
+
"loss": 1.8822,
|
| 1744 |
+
"step": 1205
|
| 1745 |
+
},
|
| 1746 |
+
{
|
| 1747 |
+
"epoch": 0.2913907284768212,
|
| 1748 |
+
"grad_norm": 3.1767303943634033,
|
| 1749 |
+
"learning_rate": 1.4171483622350675e-05,
|
| 1750 |
+
"loss": 1.9386,
|
| 1751 |
+
"step": 1210
|
| 1752 |
+
},
|
| 1753 |
+
{
|
| 1754 |
+
"epoch": 0.2925948223961469,
|
| 1755 |
+
"grad_norm": 3.6845219135284424,
|
| 1756 |
+
"learning_rate": 1.4147398843930637e-05,
|
| 1757 |
+
"loss": 1.8512,
|
| 1758 |
+
"step": 1215
|
| 1759 |
+
},
|
| 1760 |
+
{
|
| 1761 |
+
"epoch": 0.2937989163154726,
|
| 1762 |
+
"grad_norm": 3.189955949783325,
|
| 1763 |
+
"learning_rate": 1.4123314065510598e-05,
|
| 1764 |
+
"loss": 1.9804,
|
| 1765 |
+
"step": 1220
|
| 1766 |
+
},
|
| 1767 |
+
{
|
| 1768 |
+
"epoch": 0.2950030102347983,
|
| 1769 |
+
"grad_norm": 3.7629036903381348,
|
| 1770 |
+
"learning_rate": 1.4099229287090558e-05,
|
| 1771 |
+
"loss": 1.9759,
|
| 1772 |
+
"step": 1225
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 0.29620710415412405,
|
| 1776 |
+
"grad_norm": 3.6975581645965576,
|
| 1777 |
+
"learning_rate": 1.4075144508670523e-05,
|
| 1778 |
+
"loss": 2.0106,
|
| 1779 |
+
"step": 1230
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 0.29741119807344973,
|
| 1783 |
+
"grad_norm": 3.1638119220733643,
|
| 1784 |
+
"learning_rate": 1.4051059730250483e-05,
|
| 1785 |
+
"loss": 1.9846,
|
| 1786 |
+
"step": 1235
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 0.2986152919927754,
|
| 1790 |
+
"grad_norm": 3.2830159664154053,
|
| 1791 |
+
"learning_rate": 1.4026974951830444e-05,
|
| 1792 |
+
"loss": 2.0757,
|
| 1793 |
+
"step": 1240
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 0.29981938591210117,
|
| 1797 |
+
"grad_norm": 3.1656594276428223,
|
| 1798 |
+
"learning_rate": 1.4002890173410406e-05,
|
| 1799 |
+
"loss": 1.9831,
|
| 1800 |
+
"step": 1245
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 0.30102347983142685,
|
| 1804 |
+
"grad_norm": 3.056269407272339,
|
| 1805 |
+
"learning_rate": 1.3978805394990367e-05,
|
| 1806 |
+
"loss": 1.897,
|
| 1807 |
+
"step": 1250
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 0.30222757375075254,
|
| 1811 |
+
"grad_norm": 3.1246907711029053,
|
| 1812 |
+
"learning_rate": 1.3954720616570329e-05,
|
| 1813 |
+
"loss": 1.9663,
|
| 1814 |
+
"step": 1255
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 0.3034316676700783,
|
| 1818 |
+
"grad_norm": 2.964416980743408,
|
| 1819 |
+
"learning_rate": 1.393063583815029e-05,
|
| 1820 |
+
"loss": 2.0476,
|
| 1821 |
+
"step": 1260
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 0.304635761589404,
|
| 1825 |
+
"grad_norm": 3.241818904876709,
|
| 1826 |
+
"learning_rate": 1.390655105973025e-05,
|
| 1827 |
+
"loss": 2.0771,
|
| 1828 |
+
"step": 1265
|
| 1829 |
+
},
|
| 1830 |
+
{
|
| 1831 |
+
"epoch": 0.30583985550872966,
|
| 1832 |
+
"grad_norm": 3.29571795463562,
|
| 1833 |
+
"learning_rate": 1.3882466281310214e-05,
|
| 1834 |
+
"loss": 2.0502,
|
| 1835 |
+
"step": 1270
|
| 1836 |
+
},
|
| 1837 |
+
{
|
| 1838 |
+
"epoch": 0.3070439494280554,
|
| 1839 |
+
"grad_norm": 3.6429920196533203,
|
| 1840 |
+
"learning_rate": 1.3858381502890175e-05,
|
| 1841 |
+
"loss": 2.0583,
|
| 1842 |
+
"step": 1275
|
| 1843 |
+
},
|
| 1844 |
+
{
|
| 1845 |
+
"epoch": 0.3082480433473811,
|
| 1846 |
+
"grad_norm": 3.16072416305542,
|
| 1847 |
+
"learning_rate": 1.3834296724470136e-05,
|
| 1848 |
+
"loss": 1.8808,
|
| 1849 |
+
"step": 1280
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 0.3094521372667068,
|
| 1853 |
+
"grad_norm": 3.2263102531433105,
|
| 1854 |
+
"learning_rate": 1.3810211946050098e-05,
|
| 1855 |
+
"loss": 1.8824,
|
| 1856 |
+
"step": 1285
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 0.3106562311860325,
|
| 1860 |
+
"grad_norm": 3.2608978748321533,
|
| 1861 |
+
"learning_rate": 1.3786127167630059e-05,
|
| 1862 |
+
"loss": 1.8209,
|
| 1863 |
+
"step": 1290
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 0.3118603251053582,
|
| 1867 |
+
"grad_norm": 3.1739134788513184,
|
| 1868 |
+
"learning_rate": 1.376204238921002e-05,
|
| 1869 |
+
"loss": 2.0042,
|
| 1870 |
+
"step": 1295
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"epoch": 0.3130644190246839,
|
| 1874 |
+
"grad_norm": 3.8513424396514893,
|
| 1875 |
+
"learning_rate": 1.3737957610789983e-05,
|
| 1876 |
+
"loss": 1.9969,
|
| 1877 |
+
"step": 1300
|
| 1878 |
+
},
|
| 1879 |
+
{
|
| 1880 |
+
"epoch": 0.31426851294400965,
|
| 1881 |
+
"grad_norm": 2.987257957458496,
|
| 1882 |
+
"learning_rate": 1.3713872832369944e-05,
|
| 1883 |
+
"loss": 1.8387,
|
| 1884 |
+
"step": 1305
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"epoch": 0.31547260686333534,
|
| 1888 |
+
"grad_norm": 3.1317367553710938,
|
| 1889 |
+
"learning_rate": 1.3689788053949905e-05,
|
| 1890 |
+
"loss": 2.0304,
|
| 1891 |
+
"step": 1310
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 0.316676700782661,
|
| 1895 |
+
"grad_norm": 3.459153413772583,
|
| 1896 |
+
"learning_rate": 1.3665703275529867e-05,
|
| 1897 |
+
"loss": 1.977,
|
| 1898 |
+
"step": 1315
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 0.31788079470198677,
|
| 1902 |
+
"grad_norm": 3.1578195095062256,
|
| 1903 |
+
"learning_rate": 1.3641618497109828e-05,
|
| 1904 |
+
"loss": 1.8042,
|
| 1905 |
+
"step": 1320
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 0.31908488862131246,
|
| 1909 |
+
"grad_norm": 3.375023126602173,
|
| 1910 |
+
"learning_rate": 1.3617533718689788e-05,
|
| 1911 |
+
"loss": 1.8485,
|
| 1912 |
+
"step": 1325
|
| 1913 |
+
},
|
| 1914 |
+
{
|
| 1915 |
+
"epoch": 0.32028898254063815,
|
| 1916 |
+
"grad_norm": 3.1867401599884033,
|
| 1917 |
+
"learning_rate": 1.359344894026975e-05,
|
| 1918 |
+
"loss": 1.9303,
|
| 1919 |
+
"step": 1330
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 0.3214930764599639,
|
| 1923 |
+
"grad_norm": 3.303433418273926,
|
| 1924 |
+
"learning_rate": 1.3569364161849711e-05,
|
| 1925 |
+
"loss": 1.8925,
|
| 1926 |
+
"step": 1335
|
| 1927 |
+
},
|
| 1928 |
+
{
|
| 1929 |
+
"epoch": 0.3226971703792896,
|
| 1930 |
+
"grad_norm": 2.990525960922241,
|
| 1931 |
+
"learning_rate": 1.3545279383429672e-05,
|
| 1932 |
+
"loss": 1.8612,
|
| 1933 |
+
"step": 1340
|
| 1934 |
+
},
|
| 1935 |
+
{
|
| 1936 |
+
"epoch": 0.32390126429861527,
|
| 1937 |
+
"grad_norm": 3.570690155029297,
|
| 1938 |
+
"learning_rate": 1.3521194605009636e-05,
|
| 1939 |
+
"loss": 1.9175,
|
| 1940 |
+
"step": 1345
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 0.325105358217941,
|
| 1944 |
+
"grad_norm": 3.3581953048706055,
|
| 1945 |
+
"learning_rate": 1.3497109826589597e-05,
|
| 1946 |
+
"loss": 2.0293,
|
| 1947 |
+
"step": 1350
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 0.3263094521372667,
|
| 1951 |
+
"grad_norm": 3.111626148223877,
|
| 1952 |
+
"learning_rate": 1.3473025048169559e-05,
|
| 1953 |
+
"loss": 1.9314,
|
| 1954 |
+
"step": 1355
|
| 1955 |
+
},
|
| 1956 |
+
{
|
| 1957 |
+
"epoch": 0.32751354605659244,
|
| 1958 |
+
"grad_norm": 2.8977465629577637,
|
| 1959 |
+
"learning_rate": 1.344894026974952e-05,
|
| 1960 |
+
"loss": 1.9008,
|
| 1961 |
+
"step": 1360
|
| 1962 |
+
},
|
| 1963 |
+
{
|
| 1964 |
+
"epoch": 0.32871763997591813,
|
| 1965 |
+
"grad_norm": 3.2835822105407715,
|
| 1966 |
+
"learning_rate": 1.342485549132948e-05,
|
| 1967 |
+
"loss": 1.8344,
|
| 1968 |
+
"step": 1365
|
| 1969 |
+
},
|
| 1970 |
+
{
|
| 1971 |
+
"epoch": 0.3299217338952438,
|
| 1972 |
+
"grad_norm": 3.041848659515381,
|
| 1973 |
+
"learning_rate": 1.3400770712909442e-05,
|
| 1974 |
+
"loss": 2.0046,
|
| 1975 |
+
"step": 1370
|
| 1976 |
+
},
|
| 1977 |
+
{
|
| 1978 |
+
"epoch": 0.33112582781456956,
|
| 1979 |
+
"grad_norm": 3.252289295196533,
|
| 1980 |
+
"learning_rate": 1.3376685934489405e-05,
|
| 1981 |
+
"loss": 2.015,
|
| 1982 |
+
"step": 1375
|
| 1983 |
+
},
|
| 1984 |
+
{
|
| 1985 |
+
"epoch": 0.33232992173389525,
|
| 1986 |
+
"grad_norm": 3.0157580375671387,
|
| 1987 |
+
"learning_rate": 1.3352601156069365e-05,
|
| 1988 |
+
"loss": 1.7938,
|
| 1989 |
+
"step": 1380
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 0.33353401565322094,
|
| 1993 |
+
"grad_norm": 3.2034637928009033,
|
| 1994 |
+
"learning_rate": 1.3328516377649328e-05,
|
| 1995 |
+
"loss": 1.7438,
|
| 1996 |
+
"step": 1385
|
| 1997 |
+
},
|
| 1998 |
+
{
|
| 1999 |
+
"epoch": 0.3347381095725467,
|
| 2000 |
+
"grad_norm": 2.962069034576416,
|
| 2001 |
+
"learning_rate": 1.3304431599229288e-05,
|
| 2002 |
+
"loss": 1.8915,
|
| 2003 |
+
"step": 1390
|
| 2004 |
+
},
|
| 2005 |
+
{
|
| 2006 |
+
"epoch": 0.33594220349187237,
|
| 2007 |
+
"grad_norm": 3.4406933784484863,
|
| 2008 |
+
"learning_rate": 1.3280346820809249e-05,
|
| 2009 |
+
"loss": 1.7684,
|
| 2010 |
+
"step": 1395
|
| 2011 |
+
},
|
| 2012 |
+
{
|
| 2013 |
+
"epoch": 0.33714629741119806,
|
| 2014 |
+
"grad_norm": 3.531928062438965,
|
| 2015 |
+
"learning_rate": 1.3256262042389211e-05,
|
| 2016 |
+
"loss": 1.8796,
|
| 2017 |
+
"step": 1400
|
| 2018 |
+
},
|
| 2019 |
+
{
|
| 2020 |
+
"epoch": 0.33714629741119806,
|
| 2021 |
+
"eval_loss": 1.9124047756195068,
|
| 2022 |
+
"eval_runtime": 16.4823,
|
| 2023 |
+
"eval_samples_per_second": 6.067,
|
| 2024 |
+
"eval_steps_per_second": 0.789,
|
| 2025 |
+
"step": 1400
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.3383503913305238,
|
| 2029 |
+
"grad_norm": 3.052105665206909,
|
| 2030 |
+
"learning_rate": 1.3232177263969172e-05,
|
| 2031 |
+
"loss": 1.8796,
|
| 2032 |
+
"step": 1405
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 0.3395544852498495,
|
| 2036 |
+
"grad_norm": 3.317544460296631,
|
| 2037 |
+
"learning_rate": 1.3208092485549133e-05,
|
| 2038 |
+
"loss": 1.975,
|
| 2039 |
+
"step": 1410
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.3407585791691752,
|
| 2043 |
+
"grad_norm": 3.8019814491271973,
|
| 2044 |
+
"learning_rate": 1.3184007707129097e-05,
|
| 2045 |
+
"loss": 1.8014,
|
| 2046 |
+
"step": 1415
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 0.3419626730885009,
|
| 2050 |
+
"grad_norm": 3.2202208042144775,
|
| 2051 |
+
"learning_rate": 1.3159922928709057e-05,
|
| 2052 |
+
"loss": 2.0098,
|
| 2053 |
+
"step": 1420
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.3431667670078266,
|
| 2057 |
+
"grad_norm": 3.2262189388275146,
|
| 2058 |
+
"learning_rate": 1.3135838150289018e-05,
|
| 2059 |
+
"loss": 1.758,
|
| 2060 |
+
"step": 1425
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 0.3443708609271523,
|
| 2064 |
+
"grad_norm": 3.03486704826355,
|
| 2065 |
+
"learning_rate": 1.311175337186898e-05,
|
| 2066 |
+
"loss": 1.9254,
|
| 2067 |
+
"step": 1430
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.34557495484647804,
|
| 2071 |
+
"grad_norm": 3.063431978225708,
|
| 2072 |
+
"learning_rate": 1.3087668593448941e-05,
|
| 2073 |
+
"loss": 1.9091,
|
| 2074 |
+
"step": 1435
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 0.34677904876580373,
|
| 2078 |
+
"grad_norm": 3.082839012145996,
|
| 2079 |
+
"learning_rate": 1.3063583815028902e-05,
|
| 2080 |
+
"loss": 1.951,
|
| 2081 |
+
"step": 1440
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.3479831426851294,
|
| 2085 |
+
"grad_norm": 3.692833662033081,
|
| 2086 |
+
"learning_rate": 1.3039499036608864e-05,
|
| 2087 |
+
"loss": 1.9771,
|
| 2088 |
+
"step": 1445
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 0.34918723660445516,
|
| 2092 |
+
"grad_norm": 3.4902002811431885,
|
| 2093 |
+
"learning_rate": 1.3015414258188825e-05,
|
| 2094 |
+
"loss": 1.8954,
|
| 2095 |
+
"step": 1450
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.35039133052378085,
|
| 2099 |
+
"grad_norm": 2.9592397212982178,
|
| 2100 |
+
"learning_rate": 1.2991329479768787e-05,
|
| 2101 |
+
"loss": 1.8791,
|
| 2102 |
+
"step": 1455
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 0.35159542444310654,
|
| 2106 |
+
"grad_norm": 3.3300886154174805,
|
| 2107 |
+
"learning_rate": 1.296724470134875e-05,
|
| 2108 |
+
"loss": 1.9712,
|
| 2109 |
+
"step": 1460
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.3527995183624323,
|
| 2113 |
+
"grad_norm": 3.206303834915161,
|
| 2114 |
+
"learning_rate": 1.294315992292871e-05,
|
| 2115 |
+
"loss": 1.8155,
|
| 2116 |
+
"step": 1465
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.354003612281758,
|
| 2120 |
+
"grad_norm": 3.2186410427093506,
|
| 2121 |
+
"learning_rate": 1.2919075144508672e-05,
|
| 2122 |
+
"loss": 1.8583,
|
| 2123 |
+
"step": 1470
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.35520770620108366,
|
| 2127 |
+
"grad_norm": 3.482147216796875,
|
| 2128 |
+
"learning_rate": 1.2894990366088633e-05,
|
| 2129 |
+
"loss": 1.8233,
|
| 2130 |
+
"step": 1475
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 0.3564118001204094,
|
| 2134 |
+
"grad_norm": 3.317288637161255,
|
| 2135 |
+
"learning_rate": 1.2870905587668594e-05,
|
| 2136 |
+
"loss": 2.0094,
|
| 2137 |
+
"step": 1480
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.3576158940397351,
|
| 2141 |
+
"grad_norm": 2.962334632873535,
|
| 2142 |
+
"learning_rate": 1.2846820809248558e-05,
|
| 2143 |
+
"loss": 2.0041,
|
| 2144 |
+
"step": 1485
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 0.3588199879590608,
|
| 2148 |
+
"grad_norm": 3.1497514247894287,
|
| 2149 |
+
"learning_rate": 1.2822736030828518e-05,
|
| 2150 |
+
"loss": 1.8808,
|
| 2151 |
+
"step": 1490
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.3600240818783865,
|
| 2155 |
+
"grad_norm": 3.3814947605133057,
|
| 2156 |
+
"learning_rate": 1.2798651252408479e-05,
|
| 2157 |
+
"loss": 1.8085,
|
| 2158 |
+
"step": 1495
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 0.3612281757977122,
|
| 2162 |
+
"grad_norm": 3.426969051361084,
|
| 2163 |
+
"learning_rate": 1.2774566473988441e-05,
|
| 2164 |
+
"loss": 1.8659,
|
| 2165 |
+
"step": 1500
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.3624322697170379,
|
| 2169 |
+
"grad_norm": 2.9899697303771973,
|
| 2170 |
+
"learning_rate": 1.2750481695568402e-05,
|
| 2171 |
+
"loss": 1.8327,
|
| 2172 |
+
"step": 1505
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 0.36363636363636365,
|
| 2176 |
+
"grad_norm": 3.3430888652801514,
|
| 2177 |
+
"learning_rate": 1.2726396917148362e-05,
|
| 2178 |
+
"loss": 1.8923,
|
| 2179 |
+
"step": 1510
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.36484045755568933,
|
| 2183 |
+
"grad_norm": 3.001516342163086,
|
| 2184 |
+
"learning_rate": 1.2702312138728325e-05,
|
| 2185 |
+
"loss": 1.9374,
|
| 2186 |
+
"step": 1515
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.3660445514750151,
|
| 2190 |
+
"grad_norm": 3.1876020431518555,
|
| 2191 |
+
"learning_rate": 1.2678227360308285e-05,
|
| 2192 |
+
"loss": 1.9921,
|
| 2193 |
+
"step": 1520
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.36724864539434077,
|
| 2197 |
+
"grad_norm": 3.2372751235961914,
|
| 2198 |
+
"learning_rate": 1.2654142581888246e-05,
|
| 2199 |
+
"loss": 1.7351,
|
| 2200 |
+
"step": 1525
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 0.36845273931366646,
|
| 2204 |
+
"grad_norm": 3.10359525680542,
|
| 2205 |
+
"learning_rate": 1.263005780346821e-05,
|
| 2206 |
+
"loss": 1.9056,
|
| 2207 |
+
"step": 1530
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 0.3696568332329922,
|
| 2211 |
+
"grad_norm": 3.0910706520080566,
|
| 2212 |
+
"learning_rate": 1.260597302504817e-05,
|
| 2213 |
+
"loss": 1.7916,
|
| 2214 |
+
"step": 1535
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 0.3708609271523179,
|
| 2218 |
+
"grad_norm": 3.0096778869628906,
|
| 2219 |
+
"learning_rate": 1.2581888246628131e-05,
|
| 2220 |
+
"loss": 1.8056,
|
| 2221 |
+
"step": 1540
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.3720650210716436,
|
| 2225 |
+
"grad_norm": 2.8062777519226074,
|
| 2226 |
+
"learning_rate": 1.2557803468208094e-05,
|
| 2227 |
+
"loss": 1.855,
|
| 2228 |
+
"step": 1545
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 0.3732691149909693,
|
| 2232 |
+
"grad_norm": 3.287958860397339,
|
| 2233 |
+
"learning_rate": 1.2533718689788054e-05,
|
| 2234 |
+
"loss": 1.9238,
|
| 2235 |
+
"step": 1550
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.374473208910295,
|
| 2239 |
+
"grad_norm": 3.459998607635498,
|
| 2240 |
+
"learning_rate": 1.2509633911368015e-05,
|
| 2241 |
+
"loss": 1.9554,
|
| 2242 |
+
"step": 1555
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 0.3756773028296207,
|
| 2246 |
+
"grad_norm": 3.3246283531188965,
|
| 2247 |
+
"learning_rate": 1.2485549132947979e-05,
|
| 2248 |
+
"loss": 1.8773,
|
| 2249 |
+
"step": 1560
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.37688139674894644,
|
| 2253 |
+
"grad_norm": 3.058595895767212,
|
| 2254 |
+
"learning_rate": 1.246146435452794e-05,
|
| 2255 |
+
"loss": 1.923,
|
| 2256 |
+
"step": 1565
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 0.37808549066827213,
|
| 2260 |
+
"grad_norm": 2.9321656227111816,
|
| 2261 |
+
"learning_rate": 1.2437379576107902e-05,
|
| 2262 |
+
"loss": 1.9403,
|
| 2263 |
+
"step": 1570
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.3792895845875978,
|
| 2267 |
+
"grad_norm": 3.1878929138183594,
|
| 2268 |
+
"learning_rate": 1.2413294797687863e-05,
|
| 2269 |
+
"loss": 1.9703,
|
| 2270 |
+
"step": 1575
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 0.38049367850692356,
|
| 2274 |
+
"grad_norm": 3.411778450012207,
|
| 2275 |
+
"learning_rate": 1.2389210019267823e-05,
|
| 2276 |
+
"loss": 1.8681,
|
| 2277 |
+
"step": 1580
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.38169777242624925,
|
| 2281 |
+
"grad_norm": 2.9784305095672607,
|
| 2282 |
+
"learning_rate": 1.2365125240847786e-05,
|
| 2283 |
+
"loss": 1.8222,
|
| 2284 |
+
"step": 1585
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 0.38290186634557494,
|
| 2288 |
+
"grad_norm": 3.037580728530884,
|
| 2289 |
+
"learning_rate": 1.2341040462427746e-05,
|
| 2290 |
+
"loss": 1.9808,
|
| 2291 |
+
"step": 1590
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.3841059602649007,
|
| 2295 |
+
"grad_norm": 2.867035388946533,
|
| 2296 |
+
"learning_rate": 1.2316955684007707e-05,
|
| 2297 |
+
"loss": 1.7734,
|
| 2298 |
+
"step": 1595
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 0.38531005418422637,
|
| 2302 |
+
"grad_norm": 2.8721401691436768,
|
| 2303 |
+
"learning_rate": 1.2292870905587671e-05,
|
| 2304 |
+
"loss": 1.8227,
|
| 2305 |
+
"step": 1600
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.38531005418422637,
|
| 2309 |
+
"eval_loss": 1.8952380418777466,
|
| 2310 |
+
"eval_runtime": 16.4306,
|
| 2311 |
+
"eval_samples_per_second": 6.086,
|
| 2312 |
+
"eval_steps_per_second": 0.791,
|
| 2313 |
+
"step": 1600
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 0.38651414810355206,
|
| 2317 |
+
"grad_norm": 3.3023080825805664,
|
| 2318 |
+
"learning_rate": 1.2268786127167632e-05,
|
| 2319 |
+
"loss": 2.0716,
|
| 2320 |
+
"step": 1605
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 0.3877182420228778,
|
| 2324 |
+
"grad_norm": 3.0930209159851074,
|
| 2325 |
+
"learning_rate": 1.2244701348747592e-05,
|
| 2326 |
+
"loss": 2.1265,
|
| 2327 |
+
"step": 1610
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 0.3889223359422035,
|
| 2331 |
+
"grad_norm": 2.944687843322754,
|
| 2332 |
+
"learning_rate": 1.2220616570327555e-05,
|
| 2333 |
+
"loss": 1.8317,
|
| 2334 |
+
"step": 1615
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 0.3901264298615292,
|
| 2338 |
+
"grad_norm": 3.4099764823913574,
|
| 2339 |
+
"learning_rate": 1.2196531791907515e-05,
|
| 2340 |
+
"loss": 1.9413,
|
| 2341 |
+
"step": 1620
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 0.3913305237808549,
|
| 2345 |
+
"grad_norm": 4.778016567230225,
|
| 2346 |
+
"learning_rate": 1.2172447013487476e-05,
|
| 2347 |
+
"loss": 1.9718,
|
| 2348 |
+
"step": 1625
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 0.3925346177001806,
|
| 2352 |
+
"grad_norm": 3.0482661724090576,
|
| 2353 |
+
"learning_rate": 1.214836223506744e-05,
|
| 2354 |
+
"loss": 1.7691,
|
| 2355 |
+
"step": 1630
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 0.3937387116195063,
|
| 2359 |
+
"grad_norm": 3.1143486499786377,
|
| 2360 |
+
"learning_rate": 1.21242774566474e-05,
|
| 2361 |
+
"loss": 1.8427,
|
| 2362 |
+
"step": 1635
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 0.39494280553883204,
|
| 2366 |
+
"grad_norm": 3.4189348220825195,
|
| 2367 |
+
"learning_rate": 1.2100192678227361e-05,
|
| 2368 |
+
"loss": 1.7502,
|
| 2369 |
+
"step": 1640
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 0.39614689945815773,
|
| 2373 |
+
"grad_norm": 2.9873223304748535,
|
| 2374 |
+
"learning_rate": 1.2076107899807323e-05,
|
| 2375 |
+
"loss": 1.9207,
|
| 2376 |
+
"step": 1645
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 0.3973509933774834,
|
| 2380 |
+
"grad_norm": 3.051147699356079,
|
| 2381 |
+
"learning_rate": 1.2052023121387284e-05,
|
| 2382 |
+
"loss": 1.8523,
|
| 2383 |
+
"step": 1650
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 0.39855508729680916,
|
| 2387 |
+
"grad_norm": 3.375426769256592,
|
| 2388 |
+
"learning_rate": 1.2027938342967245e-05,
|
| 2389 |
+
"loss": 1.9916,
|
| 2390 |
+
"step": 1655
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 0.39975918121613485,
|
| 2394 |
+
"grad_norm": 3.345398426055908,
|
| 2395 |
+
"learning_rate": 1.2003853564547207e-05,
|
| 2396 |
+
"loss": 1.8303,
|
| 2397 |
+
"step": 1660
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 0.40096327513546054,
|
| 2401 |
+
"grad_norm": 3.3531017303466797,
|
| 2402 |
+
"learning_rate": 1.1979768786127168e-05,
|
| 2403 |
+
"loss": 1.8113,
|
| 2404 |
+
"step": 1665
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 0.4021673690547863,
|
| 2408 |
+
"grad_norm": 3.656094551086426,
|
| 2409 |
+
"learning_rate": 1.1955684007707128e-05,
|
| 2410 |
+
"loss": 1.8728,
|
| 2411 |
+
"step": 1670
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 0.40337146297411197,
|
| 2415 |
+
"grad_norm": 3.184237241744995,
|
| 2416 |
+
"learning_rate": 1.1931599229287092e-05,
|
| 2417 |
+
"loss": 1.8423,
|
| 2418 |
+
"step": 1675
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 0.4045755568934377,
|
| 2422 |
+
"grad_norm": 3.013655662536621,
|
| 2423 |
+
"learning_rate": 1.1907514450867053e-05,
|
| 2424 |
+
"loss": 2.019,
|
| 2425 |
+
"step": 1680
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 0.4057796508127634,
|
| 2429 |
+
"grad_norm": 3.0090904235839844,
|
| 2430 |
+
"learning_rate": 1.1883429672447015e-05,
|
| 2431 |
+
"loss": 1.9982,
|
| 2432 |
+
"step": 1685
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 0.4069837447320891,
|
| 2436 |
+
"grad_norm": 2.8152971267700195,
|
| 2437 |
+
"learning_rate": 1.1859344894026976e-05,
|
| 2438 |
+
"loss": 1.8038,
|
| 2439 |
+
"step": 1690
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 0.40818783865141484,
|
| 2443 |
+
"grad_norm": 3.1558475494384766,
|
| 2444 |
+
"learning_rate": 1.1835260115606937e-05,
|
| 2445 |
+
"loss": 1.904,
|
| 2446 |
+
"step": 1695
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 0.4093919325707405,
|
| 2450 |
+
"grad_norm": 3.0803842544555664,
|
| 2451 |
+
"learning_rate": 1.1811175337186899e-05,
|
| 2452 |
+
"loss": 1.9563,
|
| 2453 |
+
"step": 1700
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 0.4105960264900662,
|
| 2457 |
+
"grad_norm": 3.41733717918396,
|
| 2458 |
+
"learning_rate": 1.1787090558766861e-05,
|
| 2459 |
+
"loss": 1.8821,
|
| 2460 |
+
"step": 1705
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 0.41180012040939196,
|
| 2464 |
+
"grad_norm": 3.818134069442749,
|
| 2465 |
+
"learning_rate": 1.1763005780346822e-05,
|
| 2466 |
+
"loss": 2.038,
|
| 2467 |
+
"step": 1710
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 0.41300421432871764,
|
| 2471 |
+
"grad_norm": 2.931730270385742,
|
| 2472 |
+
"learning_rate": 1.1738921001926784e-05,
|
| 2473 |
+
"loss": 1.7836,
|
| 2474 |
+
"step": 1715
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 0.41420830824804333,
|
| 2478 |
+
"grad_norm": 3.2240729331970215,
|
| 2479 |
+
"learning_rate": 1.1714836223506745e-05,
|
| 2480 |
+
"loss": 1.8985,
|
| 2481 |
+
"step": 1720
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 0.4154124021673691,
|
| 2485 |
+
"grad_norm": 3.0868842601776123,
|
| 2486 |
+
"learning_rate": 1.1690751445086706e-05,
|
| 2487 |
+
"loss": 1.9309,
|
| 2488 |
+
"step": 1725
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 0.41661649608669477,
|
| 2492 |
+
"grad_norm": 3.2010886669158936,
|
| 2493 |
+
"learning_rate": 1.1666666666666668e-05,
|
| 2494 |
+
"loss": 1.9058,
|
| 2495 |
+
"step": 1730
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 0.41782059000602045,
|
| 2499 |
+
"grad_norm": 3.248377799987793,
|
| 2500 |
+
"learning_rate": 1.1642581888246629e-05,
|
| 2501 |
+
"loss": 1.9333,
|
| 2502 |
+
"step": 1735
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 0.4190246839253462,
|
| 2506 |
+
"grad_norm": 3.792973756790161,
|
| 2507 |
+
"learning_rate": 1.161849710982659e-05,
|
| 2508 |
+
"loss": 1.7065,
|
| 2509 |
+
"step": 1740
|
| 2510 |
+
},
|
| 2511 |
+
{
|
| 2512 |
+
"epoch": 0.4202287778446719,
|
| 2513 |
+
"grad_norm": 3.1620492935180664,
|
| 2514 |
+
"learning_rate": 1.1594412331406553e-05,
|
| 2515 |
+
"loss": 1.9736,
|
| 2516 |
+
"step": 1745
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 0.4214328717639976,
|
| 2520 |
+
"grad_norm": 3.8951566219329834,
|
| 2521 |
+
"learning_rate": 1.1570327552986514e-05,
|
| 2522 |
+
"loss": 1.9916,
|
| 2523 |
+
"step": 1750
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 0.4226369656833233,
|
| 2527 |
+
"grad_norm": 3.2940852642059326,
|
| 2528 |
+
"learning_rate": 1.1546242774566474e-05,
|
| 2529 |
+
"loss": 1.8398,
|
| 2530 |
+
"step": 1755
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 0.423841059602649,
|
| 2534 |
+
"grad_norm": 3.4238831996917725,
|
| 2535 |
+
"learning_rate": 1.1522157996146437e-05,
|
| 2536 |
+
"loss": 1.903,
|
| 2537 |
+
"step": 1760
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 0.4250451535219747,
|
| 2541 |
+
"grad_norm": 3.1505134105682373,
|
| 2542 |
+
"learning_rate": 1.1498073217726397e-05,
|
| 2543 |
+
"loss": 1.8617,
|
| 2544 |
+
"step": 1765
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 0.42624924744130044,
|
| 2548 |
+
"grad_norm": 3.1795570850372314,
|
| 2549 |
+
"learning_rate": 1.1473988439306358e-05,
|
| 2550 |
+
"loss": 1.7612,
|
| 2551 |
+
"step": 1770
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 0.4274533413606261,
|
| 2555 |
+
"grad_norm": 3.108771324157715,
|
| 2556 |
+
"learning_rate": 1.144990366088632e-05,
|
| 2557 |
+
"loss": 1.7434,
|
| 2558 |
+
"step": 1775
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 0.4286574352799518,
|
| 2562 |
+
"grad_norm": 3.026624917984009,
|
| 2563 |
+
"learning_rate": 1.1425818882466281e-05,
|
| 2564 |
+
"loss": 2.0082,
|
| 2565 |
+
"step": 1780
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 0.42986152919927756,
|
| 2569 |
+
"grad_norm": 3.0684778690338135,
|
| 2570 |
+
"learning_rate": 1.1401734104046245e-05,
|
| 2571 |
+
"loss": 1.9998,
|
| 2572 |
+
"step": 1785
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 0.43106562311860325,
|
| 2576 |
+
"grad_norm": 3.261258840560913,
|
| 2577 |
+
"learning_rate": 1.1377649325626206e-05,
|
| 2578 |
+
"loss": 1.9306,
|
| 2579 |
+
"step": 1790
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 0.43226971703792894,
|
| 2583 |
+
"grad_norm": 3.167187452316284,
|
| 2584 |
+
"learning_rate": 1.1353564547206166e-05,
|
| 2585 |
+
"loss": 1.7516,
|
| 2586 |
+
"step": 1795
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 0.4334738109572547,
|
| 2590 |
+
"grad_norm": 2.8481147289276123,
|
| 2591 |
+
"learning_rate": 1.1329479768786129e-05,
|
| 2592 |
+
"loss": 1.9046,
|
| 2593 |
+
"step": 1800
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 0.4334738109572547,
|
| 2597 |
+
"eval_loss": 1.8845782279968262,
|
| 2598 |
+
"eval_runtime": 16.4138,
|
| 2599 |
+
"eval_samples_per_second": 6.092,
|
| 2600 |
+
"eval_steps_per_second": 0.792,
|
| 2601 |
+
"step": 1800
|
| 2602 |
+
},
|
| 2603 |
+
{
|
| 2604 |
+
"epoch": 0.43467790487658037,
|
| 2605 |
+
"grad_norm": 3.374049663543701,
|
| 2606 |
+
"learning_rate": 1.130539499036609e-05,
|
| 2607 |
+
"loss": 1.799,
|
| 2608 |
+
"step": 1805
|
| 2609 |
+
},
|
| 2610 |
+
{
|
| 2611 |
+
"epoch": 0.43588199879590606,
|
| 2612 |
+
"grad_norm": 3.0791234970092773,
|
| 2613 |
+
"learning_rate": 1.128131021194605e-05,
|
| 2614 |
+
"loss": 1.8862,
|
| 2615 |
+
"step": 1810
|
| 2616 |
+
},
|
| 2617 |
+
{
|
| 2618 |
+
"epoch": 0.4370860927152318,
|
| 2619 |
+
"grad_norm": 3.2381889820098877,
|
| 2620 |
+
"learning_rate": 1.1257225433526014e-05,
|
| 2621 |
+
"loss": 1.8981,
|
| 2622 |
+
"step": 1815
|
| 2623 |
+
},
|
| 2624 |
+
{
|
| 2625 |
+
"epoch": 0.4382901866345575,
|
| 2626 |
+
"grad_norm": 3.3203744888305664,
|
| 2627 |
+
"learning_rate": 1.1233140655105975e-05,
|
| 2628 |
+
"loss": 1.9926,
|
| 2629 |
+
"step": 1820
|
| 2630 |
+
},
|
| 2631 |
+
{
|
| 2632 |
+
"epoch": 0.4394942805538832,
|
| 2633 |
+
"grad_norm": 3.075920581817627,
|
| 2634 |
+
"learning_rate": 1.1209055876685935e-05,
|
| 2635 |
+
"loss": 1.8543,
|
| 2636 |
+
"step": 1825
|
| 2637 |
+
},
|
| 2638 |
+
{
|
| 2639 |
+
"epoch": 0.4406983744732089,
|
| 2640 |
+
"grad_norm": 3.020115852355957,
|
| 2641 |
+
"learning_rate": 1.1184971098265898e-05,
|
| 2642 |
+
"loss": 1.9877,
|
| 2643 |
+
"step": 1830
|
| 2644 |
+
},
|
| 2645 |
+
{
|
| 2646 |
+
"epoch": 0.4419024683925346,
|
| 2647 |
+
"grad_norm": 3.152524471282959,
|
| 2648 |
+
"learning_rate": 1.1160886319845858e-05,
|
| 2649 |
+
"loss": 1.9152,
|
| 2650 |
+
"step": 1835
|
| 2651 |
+
},
|
| 2652 |
+
{
|
| 2653 |
+
"epoch": 0.44310656231186035,
|
| 2654 |
+
"grad_norm": 3.2993345260620117,
|
| 2655 |
+
"learning_rate": 1.1136801541425819e-05,
|
| 2656 |
+
"loss": 1.8089,
|
| 2657 |
+
"step": 1840
|
| 2658 |
+
},
|
| 2659 |
+
{
|
| 2660 |
+
"epoch": 0.44431065623118604,
|
| 2661 |
+
"grad_norm": 3.579181671142578,
|
| 2662 |
+
"learning_rate": 1.1112716763005781e-05,
|
| 2663 |
+
"loss": 1.9076,
|
| 2664 |
+
"step": 1845
|
| 2665 |
+
},
|
| 2666 |
+
{
|
| 2667 |
+
"epoch": 0.44551475015051173,
|
| 2668 |
+
"grad_norm": 3.3042211532592773,
|
| 2669 |
+
"learning_rate": 1.1088631984585742e-05,
|
| 2670 |
+
"loss": 1.8324,
|
| 2671 |
+
"step": 1850
|
| 2672 |
+
},
|
| 2673 |
+
{
|
| 2674 |
+
"epoch": 0.4467188440698375,
|
| 2675 |
+
"grad_norm": 3.5857417583465576,
|
| 2676 |
+
"learning_rate": 1.1064547206165703e-05,
|
| 2677 |
+
"loss": 1.7684,
|
| 2678 |
+
"step": 1855
|
| 2679 |
+
},
|
| 2680 |
+
{
|
| 2681 |
+
"epoch": 0.44792293798916316,
|
| 2682 |
+
"grad_norm": 3.2090542316436768,
|
| 2683 |
+
"learning_rate": 1.1040462427745667e-05,
|
| 2684 |
+
"loss": 1.7793,
|
| 2685 |
+
"step": 1860
|
| 2686 |
+
},
|
| 2687 |
+
{
|
| 2688 |
+
"epoch": 0.44912703190848885,
|
| 2689 |
+
"grad_norm": 3.0961151123046875,
|
| 2690 |
+
"learning_rate": 1.1016377649325627e-05,
|
| 2691 |
+
"loss": 1.8414,
|
| 2692 |
+
"step": 1865
|
| 2693 |
+
},
|
| 2694 |
+
{
|
| 2695 |
+
"epoch": 0.4503311258278146,
|
| 2696 |
+
"grad_norm": 3.3767356872558594,
|
| 2697 |
+
"learning_rate": 1.0992292870905588e-05,
|
| 2698 |
+
"loss": 1.8577,
|
| 2699 |
+
"step": 1870
|
| 2700 |
+
},
|
| 2701 |
+
{
|
| 2702 |
+
"epoch": 0.4515352197471403,
|
| 2703 |
+
"grad_norm": 3.22123122215271,
|
| 2704 |
+
"learning_rate": 1.096820809248555e-05,
|
| 2705 |
+
"loss": 1.8515,
|
| 2706 |
+
"step": 1875
|
| 2707 |
+
},
|
| 2708 |
+
{
|
| 2709 |
+
"epoch": 0.45273931366646597,
|
| 2710 |
+
"grad_norm": 3.1328110694885254,
|
| 2711 |
+
"learning_rate": 1.094412331406551e-05,
|
| 2712 |
+
"loss": 1.8725,
|
| 2713 |
+
"step": 1880
|
| 2714 |
+
},
|
| 2715 |
+
{
|
| 2716 |
+
"epoch": 0.4539434075857917,
|
| 2717 |
+
"grad_norm": 3.3135077953338623,
|
| 2718 |
+
"learning_rate": 1.0920038535645471e-05,
|
| 2719 |
+
"loss": 1.8706,
|
| 2720 |
+
"step": 1885
|
| 2721 |
+
},
|
| 2722 |
+
{
|
| 2723 |
+
"epoch": 0.4551475015051174,
|
| 2724 |
+
"grad_norm": 2.829827308654785,
|
| 2725 |
+
"learning_rate": 1.0895953757225436e-05,
|
| 2726 |
+
"loss": 1.8184,
|
| 2727 |
+
"step": 1890
|
| 2728 |
+
},
|
| 2729 |
+
{
|
| 2730 |
+
"epoch": 0.4563515954244431,
|
| 2731 |
+
"grad_norm": 3.203533411026001,
|
| 2732 |
+
"learning_rate": 1.0871868978805396e-05,
|
| 2733 |
+
"loss": 1.8289,
|
| 2734 |
+
"step": 1895
|
| 2735 |
+
},
|
| 2736 |
+
{
|
| 2737 |
+
"epoch": 0.45755568934376883,
|
| 2738 |
+
"grad_norm": 3.491577386856079,
|
| 2739 |
+
"learning_rate": 1.0847784200385358e-05,
|
| 2740 |
+
"loss": 1.888,
|
| 2741 |
+
"step": 1900
|
| 2742 |
+
},
|
| 2743 |
+
{
|
| 2744 |
+
"epoch": 0.4587597832630945,
|
| 2745 |
+
"grad_norm": 3.2121121883392334,
|
| 2746 |
+
"learning_rate": 1.0823699421965319e-05,
|
| 2747 |
+
"loss": 1.8264,
|
| 2748 |
+
"step": 1905
|
| 2749 |
+
},
|
| 2750 |
+
{
|
| 2751 |
+
"epoch": 0.4599638771824202,
|
| 2752 |
+
"grad_norm": 3.110546827316284,
|
| 2753 |
+
"learning_rate": 1.079961464354528e-05,
|
| 2754 |
+
"loss": 1.9191,
|
| 2755 |
+
"step": 1910
|
| 2756 |
+
},
|
| 2757 |
+
{
|
| 2758 |
+
"epoch": 0.46116797110174595,
|
| 2759 |
+
"grad_norm": 4.177798748016357,
|
| 2760 |
+
"learning_rate": 1.0775529865125242e-05,
|
| 2761 |
+
"loss": 1.8732,
|
| 2762 |
+
"step": 1915
|
| 2763 |
+
},
|
| 2764 |
+
{
|
| 2765 |
+
"epoch": 0.46237206502107164,
|
| 2766 |
+
"grad_norm": 3.107978582382202,
|
| 2767 |
+
"learning_rate": 1.0751445086705203e-05,
|
| 2768 |
+
"loss": 1.9634,
|
| 2769 |
+
"step": 1920
|
| 2770 |
+
},
|
| 2771 |
+
{
|
| 2772 |
+
"epoch": 0.46357615894039733,
|
| 2773 |
+
"grad_norm": 3.661637783050537,
|
| 2774 |
+
"learning_rate": 1.0727360308285163e-05,
|
| 2775 |
+
"loss": 1.7731,
|
| 2776 |
+
"step": 1925
|
| 2777 |
+
},
|
| 2778 |
+
{
|
| 2779 |
+
"epoch": 0.4647802528597231,
|
| 2780 |
+
"grad_norm": 3.32905912399292,
|
| 2781 |
+
"learning_rate": 1.0703275529865127e-05,
|
| 2782 |
+
"loss": 1.8689,
|
| 2783 |
+
"step": 1930
|
| 2784 |
+
},
|
| 2785 |
+
{
|
| 2786 |
+
"epoch": 0.46598434677904876,
|
| 2787 |
+
"grad_norm": 3.348806381225586,
|
| 2788 |
+
"learning_rate": 1.0679190751445088e-05,
|
| 2789 |
+
"loss": 2.0132,
|
| 2790 |
+
"step": 1935
|
| 2791 |
+
},
|
| 2792 |
+
{
|
| 2793 |
+
"epoch": 0.46718844069837445,
|
| 2794 |
+
"grad_norm": 3.625046730041504,
|
| 2795 |
+
"learning_rate": 1.0655105973025049e-05,
|
| 2796 |
+
"loss": 1.9329,
|
| 2797 |
+
"step": 1940
|
| 2798 |
+
},
|
| 2799 |
+
{
|
| 2800 |
+
"epoch": 0.4683925346177002,
|
| 2801 |
+
"grad_norm": 2.9613242149353027,
|
| 2802 |
+
"learning_rate": 1.0631021194605011e-05,
|
| 2803 |
+
"loss": 1.8133,
|
| 2804 |
+
"step": 1945
|
| 2805 |
+
},
|
| 2806 |
+
{
|
| 2807 |
+
"epoch": 0.4695966285370259,
|
| 2808 |
+
"grad_norm": 3.4370510578155518,
|
| 2809 |
+
"learning_rate": 1.0606936416184972e-05,
|
| 2810 |
+
"loss": 1.8325,
|
| 2811 |
+
"step": 1950
|
| 2812 |
+
},
|
| 2813 |
+
{
|
| 2814 |
+
"epoch": 0.4708007224563516,
|
| 2815 |
+
"grad_norm": 3.0052490234375,
|
| 2816 |
+
"learning_rate": 1.0582851637764932e-05,
|
| 2817 |
+
"loss": 1.7397,
|
| 2818 |
+
"step": 1955
|
| 2819 |
+
},
|
| 2820 |
+
{
|
| 2821 |
+
"epoch": 0.4720048163756773,
|
| 2822 |
+
"grad_norm": 3.4657671451568604,
|
| 2823 |
+
"learning_rate": 1.0558766859344896e-05,
|
| 2824 |
+
"loss": 1.8374,
|
| 2825 |
+
"step": 1960
|
| 2826 |
+
},
|
| 2827 |
+
{
|
| 2828 |
+
"epoch": 0.473208910295003,
|
| 2829 |
+
"grad_norm": 3.1156861782073975,
|
| 2830 |
+
"learning_rate": 1.0534682080924857e-05,
|
| 2831 |
+
"loss": 1.9296,
|
| 2832 |
+
"step": 1965
|
| 2833 |
+
},
|
| 2834 |
+
{
|
| 2835 |
+
"epoch": 0.4744130042143287,
|
| 2836 |
+
"grad_norm": 2.908092498779297,
|
| 2837 |
+
"learning_rate": 1.0510597302504818e-05,
|
| 2838 |
+
"loss": 1.9279,
|
| 2839 |
+
"step": 1970
|
| 2840 |
+
},
|
| 2841 |
+
{
|
| 2842 |
+
"epoch": 0.47561709813365444,
|
| 2843 |
+
"grad_norm": 3.2144057750701904,
|
| 2844 |
+
"learning_rate": 1.048651252408478e-05,
|
| 2845 |
+
"loss": 1.6978,
|
| 2846 |
+
"step": 1975
|
| 2847 |
+
},
|
| 2848 |
+
{
|
| 2849 |
+
"epoch": 0.4768211920529801,
|
| 2850 |
+
"grad_norm": 3.2203619480133057,
|
| 2851 |
+
"learning_rate": 1.046242774566474e-05,
|
| 2852 |
+
"loss": 1.7573,
|
| 2853 |
+
"step": 1980
|
| 2854 |
+
},
|
| 2855 |
+
{
|
| 2856 |
+
"epoch": 0.4780252859723058,
|
| 2857 |
+
"grad_norm": 3.258633613586426,
|
| 2858 |
+
"learning_rate": 1.0438342967244701e-05,
|
| 2859 |
+
"loss": 1.747,
|
| 2860 |
+
"step": 1985
|
| 2861 |
+
},
|
| 2862 |
+
{
|
| 2863 |
+
"epoch": 0.47922937989163156,
|
| 2864 |
+
"grad_norm": 3.7678489685058594,
|
| 2865 |
+
"learning_rate": 1.0414258188824664e-05,
|
| 2866 |
+
"loss": 1.8558,
|
| 2867 |
+
"step": 1990
|
| 2868 |
+
},
|
| 2869 |
+
{
|
| 2870 |
+
"epoch": 0.48043347381095725,
|
| 2871 |
+
"grad_norm": 3.226168155670166,
|
| 2872 |
+
"learning_rate": 1.0390173410404624e-05,
|
| 2873 |
+
"loss": 1.8387,
|
| 2874 |
+
"step": 1995
|
| 2875 |
+
},
|
| 2876 |
+
{
|
| 2877 |
+
"epoch": 0.481637567730283,
|
| 2878 |
+
"grad_norm": 2.9940948486328125,
|
| 2879 |
+
"learning_rate": 1.0366088631984585e-05,
|
| 2880 |
+
"loss": 1.8159,
|
| 2881 |
+
"step": 2000
|
| 2882 |
+
},
|
| 2883 |
+
{
|
| 2884 |
+
"epoch": 0.481637567730283,
|
| 2885 |
+
"eval_loss": 1.871155858039856,
|
| 2886 |
+
"eval_runtime": 16.4315,
|
| 2887 |
+
"eval_samples_per_second": 6.086,
|
| 2888 |
+
"eval_steps_per_second": 0.791,
|
| 2889 |
+
"step": 2000
|
| 2890 |
+
}
|
| 2891 |
+
],
|
| 2892 |
+
"logging_steps": 5,
|
| 2893 |
+
"max_steps": 4152,
|
| 2894 |
+
"num_input_tokens_seen": 0,
|
| 2895 |
+
"num_train_epochs": 1,
|
| 2896 |
+
"save_steps": 500,
|
| 2897 |
+
"stateful_callbacks": {
|
| 2898 |
+
"TrainerControl": {
|
| 2899 |
+
"args": {
|
| 2900 |
+
"should_epoch_stop": false,
|
| 2901 |
+
"should_evaluate": false,
|
| 2902 |
+
"should_log": false,
|
| 2903 |
+
"should_save": true,
|
| 2904 |
+
"should_training_stop": false
|
| 2905 |
+
},
|
| 2906 |
+
"attributes": {}
|
| 2907 |
+
}
|
| 2908 |
+
},
|
| 2909 |
+
"total_flos": 2105914563722736.0,
|
| 2910 |
+
"train_batch_size": 1,
|
| 2911 |
+
"trial_name": null,
|
| 2912 |
+
"trial_params": null
|
| 2913 |
+
}
|
checkpoint-2000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd020aa9333054ccbd44f2f69522647a4bdda52101c5b015e38e78115982722b
|
| 3 |
+
size 5816
|
checkpoint-500/added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|im_end|>": 32000,
|
| 3 |
+
"<|im_start|>": 32001
|
| 4 |
+
}
|
checkpoint-500/config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Felladrin/Minueza-32M-Chat",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MistralForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 32000,
|
| 9 |
+
"head_dim": 26,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 312,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 1092,
|
| 14 |
+
"max_position_embeddings": 2048,
|
| 15 |
+
"model_type": "mistral",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 10,
|
| 18 |
+
"num_key_value_heads": 4,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_theta": 10000.0,
|
| 21 |
+
"sliding_window": 1024,
|
| 22 |
+
"tie_word_embeddings": false,
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.48.1",
|
| 25 |
+
"use_cache": false,
|
| 26 |
+
"vocab_size": 32002
|
| 27 |
+
}
|
checkpoint-500/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 32000,
|
| 5 |
+
"transformers_version": "4.48.1"
|
| 6 |
+
}
|
checkpoint-500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f78022fd000efe193d3842c20c125accf0e08f56767a1083341549b1632cbad5
|
| 3 |
+
size 131181272
|
checkpoint-500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c45fba25104663249b410ca2e7dcb1da25da0a206f56b5a1ed7e4b8faa977ae
|
| 3 |
+
size 262419258
|
checkpoint-500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
|
| 3 |
+
size 14244
|
checkpoint-500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19108033ec901a824f3cecb198c7800f1aa950cde6adc4b84b88b2b0d1248717
|
| 3 |
+
size 1064
|
checkpoint-500/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|im_end|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|im_end|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
checkpoint-500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-500/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
checkpoint-500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "<|im_end|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"32001": {
|
| 39 |
+
"content": "<|im_start|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
}
|
| 46 |
+
},
|
| 47 |
+
"additional_special_tokens": [],
|
| 48 |
+
"bos_token": "<s>",
|
| 49 |
+
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 50 |
+
"clean_up_tokenization_spaces": false,
|
| 51 |
+
"eos_token": "<|im_end|>",
|
| 52 |
+
"extra_special_tokens": {},
|
| 53 |
+
"legacy": true,
|
| 54 |
+
"model_max_length": 2048,
|
| 55 |
+
"pad_token": "<|im_end|>",
|
| 56 |
+
"sp_model_kwargs": {},
|
| 57 |
+
"spaces_between_special_tokens": false,
|
| 58 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 59 |
+
"unk_token": "<unk>",
|
| 60 |
+
"use_default_system_prompt": false
|
| 61 |
+
}
|