Uploading folder contents
Browse files- config.json +29 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- rng_state_3.pth +3 -0
- rng_state_4.pth +3 -0
- rng_state_5.pth +3 -0
- rng_state_6.pth +3 -0
- rng_state_7.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +44 -0
- tokenizer.json +0 -0
- tokenizer_config.json +80 -0
- trainer_state.json +1281 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "model/Qwen1.5-0.5B",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Qwen2ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 5,
|
| 8 |
+
"eos_token_id": 6,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 1024,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 2816,
|
| 13 |
+
"max_position_embeddings": 32768,
|
| 14 |
+
"max_window_layers": 21,
|
| 15 |
+
"model_type": "qwen2",
|
| 16 |
+
"num_attention_heads": 16,
|
| 17 |
+
"num_hidden_layers": 24,
|
| 18 |
+
"num_key_value_heads": 16,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_scaling": null,
|
| 21 |
+
"rope_theta": 1000000.0,
|
| 22 |
+
"sliding_window": null,
|
| 23 |
+
"tie_word_embeddings": true,
|
| 24 |
+
"torch_dtype": "float32",
|
| 25 |
+
"transformers_version": "4.46.1",
|
| 26 |
+
"use_cache": false,
|
| 27 |
+
"use_sliding_window": false,
|
| 28 |
+
"vocab_size": 20000
|
| 29 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 5,
|
| 4 |
+
"eos_token_id": 6,
|
| 5 |
+
"transformers_version": "4.46.1"
|
| 6 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e4edc834ae82dee96de5cec7a0698cfbd6cd8a89cb71a6a9e135a13ebe10408
|
| 3 |
+
size 1315573520
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa801c4131d2307c39aa486a39c3343f0bb21859c5e23ed95c01c3a383c1c45a
|
| 3 |
+
size 2631325370
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6a98455b38671d320b6114d779bc3535c2ba598c8c60384a49f7177c2c09aaa
|
| 3 |
+
size 15984
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f1401148b55aea963bf288c52b44541e8eced34404c6433c20940c4e440f5d1
|
| 3 |
+
size 15984
|
rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e060b4b926a2eb405cf29317ae7498008dd804142dfe5657cbfa87e78502e82
|
| 3 |
+
size 15984
|
rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0ace975974cf3e4b4f28b2061d28dda7ddb4fcebcfc10241ea64ba62e9484ed
|
| 3 |
+
size 15984
|
rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ebcf452e0917700d13fe668a6c22078436282f685a087c2f3b7e866179188954
|
| 3 |
+
size 15984
|
rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7a9ef6a67e912a2ef715a67bec6e1744363033dcceb2c5add87d6bd22eb7464
|
| 3 |
+
size 15984
|
rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc005b8652e9bcf39874d57fe16ea869feb358105c7729fb3c8b7d056d7e5112
|
| 3 |
+
size 15984
|
rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a97f7e926679c826eeb2b45e6e1ce783d3ac028b3692483c9b1e64c48a0c02dc
|
| 3 |
+
size 15984
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9956bd3dbcb5bd3af45e8a4c4422f444d94c6d66587c4bf0347c8ad68a8b4efb
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"mask_token": {
|
| 17 |
+
"content": "[MASK]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"pad_token": {
|
| 24 |
+
"content": "[PAD]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"sep_token": {
|
| 31 |
+
"content": "[SEP]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"unk_token": {
|
| 38 |
+
"content": "[UNK]",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
}
|
| 44 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[UNK]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[PAD]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"5": {
|
| 44 |
+
"content": "<s>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"6": {
|
| 52 |
+
"content": "</s>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"18006": {
|
| 60 |
+
"content": "<|endoftext|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
}
|
| 67 |
+
},
|
| 68 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + '\n' }}{% endif %}{% endfor %}",
|
| 69 |
+
"clean_up_tokenization_spaces": false,
|
| 70 |
+
"cls_token": "[CLS]",
|
| 71 |
+
"eos_token": "<|endoftext|>",
|
| 72 |
+
"mask_token": "[MASK]",
|
| 73 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 74 |
+
"pad_token": "[PAD]",
|
| 75 |
+
"padding_side": "right",
|
| 76 |
+
"sep_token": "[SEP]",
|
| 77 |
+
"split_special_tokens": false,
|
| 78 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 79 |
+
"unk_token": "[UNK]"
|
| 80 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1281 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 23.272232304900182,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 1600,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.14519056261343014,
|
| 13 |
+
"grad_norm": 22.5987491607666,
|
| 14 |
+
"learning_rate": 5.882352941176471e-07,
|
| 15 |
+
"loss": 9.9337,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.29038112522686027,
|
| 20 |
+
"grad_norm": 16.331647872924805,
|
| 21 |
+
"learning_rate": 1.1764705882352942e-06,
|
| 22 |
+
"loss": 9.311,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.4355716878402904,
|
| 27 |
+
"grad_norm": 7.719615936279297,
|
| 28 |
+
"learning_rate": 1.7647058823529414e-06,
|
| 29 |
+
"loss": 8.3271,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.5807622504537205,
|
| 34 |
+
"grad_norm": 4.961643695831299,
|
| 35 |
+
"learning_rate": 2.3529411764705885e-06,
|
| 36 |
+
"loss": 7.6964,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.7259528130671506,
|
| 41 |
+
"grad_norm": 3.091538190841675,
|
| 42 |
+
"learning_rate": 2.9411764705882355e-06,
|
| 43 |
+
"loss": 7.2891,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.8711433756805808,
|
| 48 |
+
"grad_norm": 2.1008360385894775,
|
| 49 |
+
"learning_rate": 3.529411764705883e-06,
|
| 50 |
+
"loss": 6.9609,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.0181488203266789,
|
| 55 |
+
"grad_norm": 1.4959540367126465,
|
| 56 |
+
"learning_rate": 4.11764705882353e-06,
|
| 57 |
+
"loss": 6.8303,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.1633393829401089,
|
| 62 |
+
"grad_norm": 1.1464451551437378,
|
| 63 |
+
"learning_rate": 4.705882352941177e-06,
|
| 64 |
+
"loss": 6.4138,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.308529945553539,
|
| 69 |
+
"grad_norm": 1.0414376258850098,
|
| 70 |
+
"learning_rate": 5.294117647058824e-06,
|
| 71 |
+
"loss": 6.1729,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.453720508166969,
|
| 76 |
+
"grad_norm": 1.088547945022583,
|
| 77 |
+
"learning_rate": 5.882352941176471e-06,
|
| 78 |
+
"loss": 5.9844,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.453720508166969,
|
| 83 |
+
"eval_loss": 5.881684303283691,
|
| 84 |
+
"eval_runtime": 14.889,
|
| 85 |
+
"eval_samples_per_second": 191.417,
|
| 86 |
+
"eval_steps_per_second": 6.045,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.5989110707803993,
|
| 91 |
+
"grad_norm": 1.8722983598709106,
|
| 92 |
+
"learning_rate": 6.470588235294119e-06,
|
| 93 |
+
"loss": 5.8047,
|
| 94 |
+
"step": 110
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 1.7441016333938295,
|
| 98 |
+
"grad_norm": 2.358875036239624,
|
| 99 |
+
"learning_rate": 7.058823529411766e-06,
|
| 100 |
+
"loss": 5.6561,
|
| 101 |
+
"step": 120
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.8892921960072595,
|
| 105 |
+
"grad_norm": 2.1306469440460205,
|
| 106 |
+
"learning_rate": 7.647058823529411e-06,
|
| 107 |
+
"loss": 5.4932,
|
| 108 |
+
"step": 130
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 2.0362976406533577,
|
| 112 |
+
"grad_norm": 1.8775111436843872,
|
| 113 |
+
"learning_rate": 8.23529411764706e-06,
|
| 114 |
+
"loss": 5.4843,
|
| 115 |
+
"step": 140
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 2.1814882032667877,
|
| 119 |
+
"grad_norm": 2.393399477005005,
|
| 120 |
+
"learning_rate": 8.823529411764707e-06,
|
| 121 |
+
"loss": 5.203,
|
| 122 |
+
"step": 150
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 2.3266787658802177,
|
| 126 |
+
"grad_norm": 1.8098454475402832,
|
| 127 |
+
"learning_rate": 9.411764705882354e-06,
|
| 128 |
+
"loss": 5.0835,
|
| 129 |
+
"step": 160
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 2.471869328493648,
|
| 133 |
+
"grad_norm": 1.7228336334228516,
|
| 134 |
+
"learning_rate": 1e-05,
|
| 135 |
+
"loss": 4.9627,
|
| 136 |
+
"step": 170
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 2.617059891107078,
|
| 140 |
+
"grad_norm": 2.191887378692627,
|
| 141 |
+
"learning_rate": 1.0588235294117648e-05,
|
| 142 |
+
"loss": 4.8249,
|
| 143 |
+
"step": 180
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 2.762250453720508,
|
| 147 |
+
"grad_norm": 2.229368209838867,
|
| 148 |
+
"learning_rate": 1.1176470588235295e-05,
|
| 149 |
+
"loss": 4.7276,
|
| 150 |
+
"step": 190
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 2.907441016333938,
|
| 154 |
+
"grad_norm": 2.7427608966827393,
|
| 155 |
+
"learning_rate": 1.1764705882352942e-05,
|
| 156 |
+
"loss": 4.6183,
|
| 157 |
+
"step": 200
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 2.907441016333938,
|
| 161 |
+
"eval_loss": 4.551872253417969,
|
| 162 |
+
"eval_runtime": 14.875,
|
| 163 |
+
"eval_samples_per_second": 191.597,
|
| 164 |
+
"eval_steps_per_second": 6.05,
|
| 165 |
+
"step": 200
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 3.0544464609800364,
|
| 169 |
+
"grad_norm": 1.6583671569824219,
|
| 170 |
+
"learning_rate": 1.235294117647059e-05,
|
| 171 |
+
"loss": 4.6092,
|
| 172 |
+
"step": 210
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 3.1996370235934664,
|
| 176 |
+
"grad_norm": 1.6920286417007446,
|
| 177 |
+
"learning_rate": 1.2941176470588238e-05,
|
| 178 |
+
"loss": 4.4222,
|
| 179 |
+
"step": 220
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 3.344827586206897,
|
| 183 |
+
"grad_norm": 2.430650472640991,
|
| 184 |
+
"learning_rate": 1.3529411764705885e-05,
|
| 185 |
+
"loss": 4.3312,
|
| 186 |
+
"step": 230
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 3.490018148820327,
|
| 190 |
+
"grad_norm": 1.9790210723876953,
|
| 191 |
+
"learning_rate": 1.4117647058823532e-05,
|
| 192 |
+
"loss": 4.2582,
|
| 193 |
+
"step": 240
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 3.635208711433757,
|
| 197 |
+
"grad_norm": 2.1671459674835205,
|
| 198 |
+
"learning_rate": 1.4705882352941179e-05,
|
| 199 |
+
"loss": 4.1759,
|
| 200 |
+
"step": 250
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 3.780399274047187,
|
| 204 |
+
"grad_norm": 2.1711926460266113,
|
| 205 |
+
"learning_rate": 1.5294117647058822e-05,
|
| 206 |
+
"loss": 4.1042,
|
| 207 |
+
"step": 260
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 3.925589836660617,
|
| 211 |
+
"grad_norm": 3.5840203762054443,
|
| 212 |
+
"learning_rate": 1.5882352941176473e-05,
|
| 213 |
+
"loss": 4.0326,
|
| 214 |
+
"step": 270
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 4.072595281306715,
|
| 218 |
+
"grad_norm": 3.1725780963897705,
|
| 219 |
+
"learning_rate": 1.647058823529412e-05,
|
| 220 |
+
"loss": 4.0802,
|
| 221 |
+
"step": 280
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 4.217785843920145,
|
| 225 |
+
"grad_norm": 3.8986566066741943,
|
| 226 |
+
"learning_rate": 1.7058823529411767e-05,
|
| 227 |
+
"loss": 3.9111,
|
| 228 |
+
"step": 290
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 4.362976406533575,
|
| 232 |
+
"grad_norm": 3.374891996383667,
|
| 233 |
+
"learning_rate": 1.7647058823529414e-05,
|
| 234 |
+
"loss": 3.8626,
|
| 235 |
+
"step": 300
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 4.362976406533575,
|
| 239 |
+
"eval_loss": 3.839364767074585,
|
| 240 |
+
"eval_runtime": 14.9144,
|
| 241 |
+
"eval_samples_per_second": 191.091,
|
| 242 |
+
"eval_steps_per_second": 6.034,
|
| 243 |
+
"step": 300
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 4.508166969147005,
|
| 247 |
+
"grad_norm": 5.283336639404297,
|
| 248 |
+
"learning_rate": 1.823529411764706e-05,
|
| 249 |
+
"loss": 3.8031,
|
| 250 |
+
"step": 310
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 4.653357531760435,
|
| 254 |
+
"grad_norm": 4.989195346832275,
|
| 255 |
+
"learning_rate": 1.8823529411764708e-05,
|
| 256 |
+
"loss": 3.7691,
|
| 257 |
+
"step": 320
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 4.798548094373865,
|
| 261 |
+
"grad_norm": 4.338991641998291,
|
| 262 |
+
"learning_rate": 1.9411764705882355e-05,
|
| 263 |
+
"loss": 3.7185,
|
| 264 |
+
"step": 330
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 4.943738656987296,
|
| 268 |
+
"grad_norm": 5.136618614196777,
|
| 269 |
+
"learning_rate": 2e-05,
|
| 270 |
+
"loss": 3.6737,
|
| 271 |
+
"step": 340
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 5.090744101633394,
|
| 275 |
+
"grad_norm": 4.936671733856201,
|
| 276 |
+
"learning_rate": 1.9999472984871734e-05,
|
| 277 |
+
"loss": 3.7175,
|
| 278 |
+
"step": 350
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 5.235934664246824,
|
| 282 |
+
"grad_norm": 5.321089744567871,
|
| 283 |
+
"learning_rate": 1.9997891995035914e-05,
|
| 284 |
+
"loss": 3.5934,
|
| 285 |
+
"step": 360
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 5.381125226860254,
|
| 289 |
+
"grad_norm": 5.364513874053955,
|
| 290 |
+
"learning_rate": 1.999525719713366e-05,
|
| 291 |
+
"loss": 3.5399,
|
| 292 |
+
"step": 370
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 5.526315789473684,
|
| 296 |
+
"grad_norm": 4.728522300720215,
|
| 297 |
+
"learning_rate": 1.999156886888064e-05,
|
| 298 |
+
"loss": 3.4985,
|
| 299 |
+
"step": 380
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 5.671506352087114,
|
| 303 |
+
"grad_norm": 3.8172831535339355,
|
| 304 |
+
"learning_rate": 1.998682739903781e-05,
|
| 305 |
+
"loss": 3.4783,
|
| 306 |
+
"step": 390
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 5.816696914700545,
|
| 310 |
+
"grad_norm": 5.241791725158691,
|
| 311 |
+
"learning_rate": 1.9981033287370443e-05,
|
| 312 |
+
"loss": 3.4375,
|
| 313 |
+
"step": 400
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 5.816696914700545,
|
| 317 |
+
"eval_loss": 3.425196647644043,
|
| 318 |
+
"eval_runtime": 14.8876,
|
| 319 |
+
"eval_samples_per_second": 191.435,
|
| 320 |
+
"eval_steps_per_second": 6.045,
|
| 321 |
+
"step": 400
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 5.961887477313975,
|
| 325 |
+
"grad_norm": 5.1964569091796875,
|
| 326 |
+
"learning_rate": 1.9974187144595433e-05,
|
| 327 |
+
"loss": 3.4051,
|
| 328 |
+
"step": 410
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 6.108892921960073,
|
| 332 |
+
"grad_norm": 4.528454780578613,
|
| 333 |
+
"learning_rate": 1.9966289692316944e-05,
|
| 334 |
+
"loss": 3.4574,
|
| 335 |
+
"step": 420
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 6.254083484573503,
|
| 339 |
+
"grad_norm": 5.369091987609863,
|
| 340 |
+
"learning_rate": 1.9957341762950346e-05,
|
| 341 |
+
"loss": 3.3329,
|
| 342 |
+
"step": 430
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 6.399274047186933,
|
| 346 |
+
"grad_norm": 4.877899169921875,
|
| 347 |
+
"learning_rate": 1.9947344299634464e-05,
|
| 348 |
+
"loss": 3.297,
|
| 349 |
+
"step": 440
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 6.544464609800363,
|
| 353 |
+
"grad_norm": 4.93041467666626,
|
| 354 |
+
"learning_rate": 1.993629835613218e-05,
|
| 355 |
+
"loss": 3.265,
|
| 356 |
+
"step": 450
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 6.689655172413794,
|
| 360 |
+
"grad_norm": 4.630007743835449,
|
| 361 |
+
"learning_rate": 1.992420509671936e-05,
|
| 362 |
+
"loss": 3.2344,
|
| 363 |
+
"step": 460
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 6.834845735027224,
|
| 367 |
+
"grad_norm": 5.94407844543457,
|
| 368 |
+
"learning_rate": 1.9911065796062137e-05,
|
| 369 |
+
"loss": 3.1948,
|
| 370 |
+
"step": 470
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 6.980036297640654,
|
| 374 |
+
"grad_norm": 5.310027599334717,
|
| 375 |
+
"learning_rate": 1.9896881839082554e-05,
|
| 376 |
+
"loss": 3.1593,
|
| 377 |
+
"step": 480
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 7.127041742286751,
|
| 381 |
+
"grad_norm": 4.374192714691162,
|
| 382 |
+
"learning_rate": 1.9881654720812594e-05,
|
| 383 |
+
"loss": 3.2061,
|
| 384 |
+
"step": 490
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 7.272232304900181,
|
| 388 |
+
"grad_norm": 5.397394180297852,
|
| 389 |
+
"learning_rate": 1.9865386046236597e-05,
|
| 390 |
+
"loss": 3.1139,
|
| 391 |
+
"step": 500
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 7.272232304900181,
|
| 395 |
+
"eval_loss": 3.0933759212493896,
|
| 396 |
+
"eval_runtime": 14.9156,
|
| 397 |
+
"eval_samples_per_second": 191.074,
|
| 398 |
+
"eval_steps_per_second": 6.034,
|
| 399 |
+
"step": 500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 7.417422867513611,
|
| 403 |
+
"grad_norm": 5.458749294281006,
|
| 404 |
+
"learning_rate": 1.9848077530122083e-05,
|
| 405 |
+
"loss": 3.079,
|
| 406 |
+
"step": 510
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 7.562613430127042,
|
| 410 |
+
"grad_norm": 5.029440402984619,
|
| 411 |
+
"learning_rate": 1.982973099683902e-05,
|
| 412 |
+
"loss": 3.0268,
|
| 413 |
+
"step": 520
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 7.707803992740472,
|
| 417 |
+
"grad_norm": 6.583869457244873,
|
| 418 |
+
"learning_rate": 1.9810348380167527e-05,
|
| 419 |
+
"loss": 3.0157,
|
| 420 |
+
"step": 530
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 7.852994555353902,
|
| 424 |
+
"grad_norm": 4.824792861938477,
|
| 425 |
+
"learning_rate": 1.9789931723094046e-05,
|
| 426 |
+
"loss": 2.9801,
|
| 427 |
+
"step": 540
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 7.998185117967332,
|
| 431 |
+
"grad_norm": 6.213143348693848,
|
| 432 |
+
"learning_rate": 1.9768483177596008e-05,
|
| 433 |
+
"loss": 3.0539,
|
| 434 |
+
"step": 550
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 8.14519056261343,
|
| 438 |
+
"grad_norm": 4.015461444854736,
|
| 439 |
+
"learning_rate": 1.9746005004415004e-05,
|
| 440 |
+
"loss": 2.932,
|
| 441 |
+
"step": 560
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 8.29038112522686,
|
| 445 |
+
"grad_norm": 4.033381462097168,
|
| 446 |
+
"learning_rate": 1.9722499572818496e-05,
|
| 447 |
+
"loss": 2.9166,
|
| 448 |
+
"step": 570
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 8.43557168784029,
|
| 452 |
+
"grad_norm": 3.8710265159606934,
|
| 453 |
+
"learning_rate": 1.9697969360350098e-05,
|
| 454 |
+
"loss": 2.8946,
|
| 455 |
+
"step": 580
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 8.58076225045372,
|
| 459 |
+
"grad_norm": 3.5882229804992676,
|
| 460 |
+
"learning_rate": 1.9672416952568416e-05,
|
| 461 |
+
"loss": 2.8624,
|
| 462 |
+
"step": 590
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 8.72595281306715,
|
| 466 |
+
"grad_norm": 4.0660858154296875,
|
| 467 |
+
"learning_rate": 1.9645845042774555e-05,
|
| 468 |
+
"loss": 2.8595,
|
| 469 |
+
"step": 600
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 8.72595281306715,
|
| 473 |
+
"eval_loss": 2.8510355949401855,
|
| 474 |
+
"eval_runtime": 14.8889,
|
| 475 |
+
"eval_samples_per_second": 191.417,
|
| 476 |
+
"eval_steps_per_second": 6.045,
|
| 477 |
+
"step": 600
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 8.87114337568058,
|
| 481 |
+
"grad_norm": 2.8742496967315674,
|
| 482 |
+
"learning_rate": 1.961825643172819e-05,
|
| 483 |
+
"loss": 2.8184,
|
| 484 |
+
"step": 610
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 9.01814882032668,
|
| 488 |
+
"grad_norm": 3.7376978397369385,
|
| 489 |
+
"learning_rate": 1.9589654027352412e-05,
|
| 490 |
+
"loss": 2.8907,
|
| 491 |
+
"step": 620
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 9.163339382940109,
|
| 495 |
+
"grad_norm": 3.3460233211517334,
|
| 496 |
+
"learning_rate": 1.956004084442718e-05,
|
| 497 |
+
"loss": 2.7884,
|
| 498 |
+
"step": 630
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 9.30852994555354,
|
| 502 |
+
"grad_norm": 3.148989200592041,
|
| 503 |
+
"learning_rate": 1.9529420004271568e-05,
|
| 504 |
+
"loss": 2.7853,
|
| 505 |
+
"step": 640
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 9.453720508166969,
|
| 509 |
+
"grad_norm": 3.648300886154175,
|
| 510 |
+
"learning_rate": 1.9497794734414782e-05,
|
| 511 |
+
"loss": 2.7481,
|
| 512 |
+
"step": 650
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 9.5989110707804,
|
| 516 |
+
"grad_norm": 3.3044703006744385,
|
| 517 |
+
"learning_rate": 1.9465168368255946e-05,
|
| 518 |
+
"loss": 2.7365,
|
| 519 |
+
"step": 660
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 9.744101633393829,
|
| 523 |
+
"grad_norm": 3.034123659133911,
|
| 524 |
+
"learning_rate": 1.9431544344712776e-05,
|
| 525 |
+
"loss": 2.7177,
|
| 526 |
+
"step": 670
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 9.88929219600726,
|
| 530 |
+
"grad_norm": 3.021785259246826,
|
| 531 |
+
"learning_rate": 1.9396926207859085e-05,
|
| 532 |
+
"loss": 2.6953,
|
| 533 |
+
"step": 680
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 10.036297640653357,
|
| 537 |
+
"grad_norm": 3.7900452613830566,
|
| 538 |
+
"learning_rate": 1.936131760655124e-05,
|
| 539 |
+
"loss": 2.7471,
|
| 540 |
+
"step": 690
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 10.181488203266788,
|
| 544 |
+
"grad_norm": 2.3373985290527344,
|
| 545 |
+
"learning_rate": 1.932472229404356e-05,
|
| 546 |
+
"loss": 2.671,
|
| 547 |
+
"step": 700
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 10.181488203266788,
|
| 551 |
+
"eval_loss": 2.6855897903442383,
|
| 552 |
+
"eval_runtime": 15.1054,
|
| 553 |
+
"eval_samples_per_second": 188.674,
|
| 554 |
+
"eval_steps_per_second": 5.958,
|
| 555 |
+
"step": 700
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 10.326678765880217,
|
| 559 |
+
"grad_norm": 3.666839599609375,
|
| 560 |
+
"learning_rate": 1.9287144127592704e-05,
|
| 561 |
+
"loss": 2.6597,
|
| 562 |
+
"step": 710
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 10.471869328493648,
|
| 566 |
+
"grad_norm": 2.6193573474884033,
|
| 567 |
+
"learning_rate": 1.924858706805112e-05,
|
| 568 |
+
"loss": 2.6424,
|
| 569 |
+
"step": 720
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 10.617059891107077,
|
| 573 |
+
"grad_norm": 3.3366763591766357,
|
| 574 |
+
"learning_rate": 1.920905517944954e-05,
|
| 575 |
+
"loss": 2.6206,
|
| 576 |
+
"step": 730
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 10.762250453720508,
|
| 580 |
+
"grad_norm": 2.5702297687530518,
|
| 581 |
+
"learning_rate": 1.9168552628568632e-05,
|
| 582 |
+
"loss": 2.6068,
|
| 583 |
+
"step": 740
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 10.907441016333939,
|
| 587 |
+
"grad_norm": 4.158718109130859,
|
| 588 |
+
"learning_rate": 1.9127083684499805e-05,
|
| 589 |
+
"loss": 2.6103,
|
| 590 |
+
"step": 750
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 11.054446460980037,
|
| 594 |
+
"grad_norm": 2.952253818511963,
|
| 595 |
+
"learning_rate": 1.9084652718195237e-05,
|
| 596 |
+
"loss": 2.666,
|
| 597 |
+
"step": 760
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 11.199637023593466,
|
| 601 |
+
"grad_norm": 3.0563578605651855,
|
| 602 |
+
"learning_rate": 1.9041264202007158e-05,
|
| 603 |
+
"loss": 2.5752,
|
| 604 |
+
"step": 770
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 11.344827586206897,
|
| 608 |
+
"grad_norm": 3.01377272605896,
|
| 609 |
+
"learning_rate": 1.8996922709216456e-05,
|
| 610 |
+
"loss": 2.5711,
|
| 611 |
+
"step": 780
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 11.490018148820326,
|
| 615 |
+
"grad_norm": 2.676931142807007,
|
| 616 |
+
"learning_rate": 1.8951632913550625e-05,
|
| 617 |
+
"loss": 2.5482,
|
| 618 |
+
"step": 790
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 11.635208711433757,
|
| 622 |
+
"grad_norm": 2.5490481853485107,
|
| 623 |
+
"learning_rate": 1.8905399588691165e-05,
|
| 624 |
+
"loss": 2.5373,
|
| 625 |
+
"step": 800
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 11.635208711433757,
|
| 629 |
+
"eval_loss": 2.5524280071258545,
|
| 630 |
+
"eval_runtime": 14.8872,
|
| 631 |
+
"eval_samples_per_second": 191.439,
|
| 632 |
+
"eval_steps_per_second": 6.045,
|
| 633 |
+
"step": 800
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 11.780399274047188,
|
| 637 |
+
"grad_norm": 3.0705935955047607,
|
| 638 |
+
"learning_rate": 1.8858227607770398e-05,
|
| 639 |
+
"loss": 2.528,
|
| 640 |
+
"step": 810
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 11.925589836660617,
|
| 644 |
+
"grad_norm": 2.3048040866851807,
|
| 645 |
+
"learning_rate": 1.8810121942857848e-05,
|
| 646 |
+
"loss": 2.517,
|
| 647 |
+
"step": 820
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 12.072595281306715,
|
| 651 |
+
"grad_norm": 2.1240074634552,
|
| 652 |
+
"learning_rate": 1.8761087664436137e-05,
|
| 653 |
+
"loss": 2.5742,
|
| 654 |
+
"step": 830
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 12.217785843920145,
|
| 658 |
+
"grad_norm": 3.5343940258026123,
|
| 659 |
+
"learning_rate": 1.8711129940866577e-05,
|
| 660 |
+
"loss": 2.5046,
|
| 661 |
+
"step": 840
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 12.362976406533575,
|
| 665 |
+
"grad_norm": 2.78930926322937,
|
| 666 |
+
"learning_rate": 1.866025403784439e-05,
|
| 667 |
+
"loss": 2.4962,
|
| 668 |
+
"step": 850
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 12.508166969147005,
|
| 672 |
+
"grad_norm": 2.7689406871795654,
|
| 673 |
+
"learning_rate": 1.860846531784368e-05,
|
| 674 |
+
"loss": 2.4728,
|
| 675 |
+
"step": 860
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 12.653357531760436,
|
| 679 |
+
"grad_norm": 2.76344895362854,
|
| 680 |
+
"learning_rate": 1.8555769239552232e-05,
|
| 681 |
+
"loss": 2.4663,
|
| 682 |
+
"step": 870
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 12.798548094373865,
|
| 686 |
+
"grad_norm": 2.473503828048706,
|
| 687 |
+
"learning_rate": 1.8502171357296144e-05,
|
| 688 |
+
"loss": 2.4568,
|
| 689 |
+
"step": 880
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 12.943738656987296,
|
| 693 |
+
"grad_norm": 3.0922844409942627,
|
| 694 |
+
"learning_rate": 1.8447677320454367e-05,
|
| 695 |
+
"loss": 2.4562,
|
| 696 |
+
"step": 890
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 13.090744101633394,
|
| 700 |
+
"grad_norm": 3.1442785263061523,
|
| 701 |
+
"learning_rate": 1.839229287286327e-05,
|
| 702 |
+
"loss": 2.5069,
|
| 703 |
+
"step": 900
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 13.090744101633394,
|
| 707 |
+
"eval_loss": 2.458808183670044,
|
| 708 |
+
"eval_runtime": 14.8914,
|
| 709 |
+
"eval_samples_per_second": 191.385,
|
| 710 |
+
"eval_steps_per_second": 6.044,
|
| 711 |
+
"step": 900
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 13.235934664246823,
|
| 715 |
+
"grad_norm": 2.646357536315918,
|
| 716 |
+
"learning_rate": 1.8336023852211197e-05,
|
| 717 |
+
"loss": 2.4391,
|
| 718 |
+
"step": 910
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 13.381125226860254,
|
| 722 |
+
"grad_norm": 2.668268918991089,
|
| 723 |
+
"learning_rate": 1.827887618942318e-05,
|
| 724 |
+
"loss": 2.4319,
|
| 725 |
+
"step": 920
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 13.526315789473685,
|
| 729 |
+
"grad_norm": 2.6600754261016846,
|
| 730 |
+
"learning_rate": 1.8220855908035783e-05,
|
| 731 |
+
"loss": 2.4136,
|
| 732 |
+
"step": 930
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 13.671506352087114,
|
| 736 |
+
"grad_norm": 3.3083410263061523,
|
| 737 |
+
"learning_rate": 1.816196912356222e-05,
|
| 738 |
+
"loss": 2.4137,
|
| 739 |
+
"step": 940
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 13.816696914700545,
|
| 743 |
+
"grad_norm": 3.797403573989868,
|
| 744 |
+
"learning_rate": 1.8102222042847735e-05,
|
| 745 |
+
"loss": 2.4063,
|
| 746 |
+
"step": 950
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 13.961887477313974,
|
| 750 |
+
"grad_norm": 3.599175214767456,
|
| 751 |
+
"learning_rate": 1.8041620963415418e-05,
|
| 752 |
+
"loss": 2.3988,
|
| 753 |
+
"step": 960
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 14.108892921960072,
|
| 757 |
+
"grad_norm": 4.192938327789307,
|
| 758 |
+
"learning_rate": 1.7980172272802398e-05,
|
| 759 |
+
"loss": 2.452,
|
| 760 |
+
"step": 970
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 14.254083484573503,
|
| 764 |
+
"grad_norm": 4.492245197296143,
|
| 765 |
+
"learning_rate": 1.7917882447886585e-05,
|
| 766 |
+
"loss": 2.3884,
|
| 767 |
+
"step": 980
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 14.399274047186934,
|
| 771 |
+
"grad_norm": 3.3529608249664307,
|
| 772 |
+
"learning_rate": 1.785475805420399e-05,
|
| 773 |
+
"loss": 2.379,
|
| 774 |
+
"step": 990
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 14.544464609800363,
|
| 778 |
+
"grad_norm": 3.170184850692749,
|
| 779 |
+
"learning_rate": 1.7790805745256703e-05,
|
| 780 |
+
"loss": 2.3716,
|
| 781 |
+
"step": 1000
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 14.544464609800363,
|
| 785 |
+
"eval_loss": 2.3836851119995117,
|
| 786 |
+
"eval_runtime": 14.94,
|
| 787 |
+
"eval_samples_per_second": 190.763,
|
| 788 |
+
"eval_steps_per_second": 6.024,
|
| 789 |
+
"step": 1000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 14.689655172413794,
|
| 793 |
+
"grad_norm": 2.9663002490997314,
|
| 794 |
+
"learning_rate": 1.772603226181159e-05,
|
| 795 |
+
"loss": 2.3473,
|
| 796 |
+
"step": 1010
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 14.834845735027223,
|
| 800 |
+
"grad_norm": 4.165375232696533,
|
| 801 |
+
"learning_rate": 1.766044443118978e-05,
|
| 802 |
+
"loss": 2.3599,
|
| 803 |
+
"step": 1020
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 14.980036297640654,
|
| 807 |
+
"grad_norm": 4.470517158508301,
|
| 808 |
+
"learning_rate": 1.7594049166547073e-05,
|
| 809 |
+
"loss": 2.3509,
|
| 810 |
+
"step": 1030
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 15.127041742286751,
|
| 814 |
+
"grad_norm": 4.556570529937744,
|
| 815 |
+
"learning_rate": 1.7526853466145248e-05,
|
| 816 |
+
"loss": 2.408,
|
| 817 |
+
"step": 1040
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 15.272232304900182,
|
| 821 |
+
"grad_norm": 5.301922798156738,
|
| 822 |
+
"learning_rate": 1.7458864412614436e-05,
|
| 823 |
+
"loss": 2.3295,
|
| 824 |
+
"step": 1050
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 15.417422867513611,
|
| 828 |
+
"grad_norm": 4.635037422180176,
|
| 829 |
+
"learning_rate": 1.7390089172206594e-05,
|
| 830 |
+
"loss": 2.3307,
|
| 831 |
+
"step": 1060
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 15.562613430127042,
|
| 835 |
+
"grad_norm": 4.69865083694458,
|
| 836 |
+
"learning_rate": 1.7320534994040148e-05,
|
| 837 |
+
"loss": 2.3145,
|
| 838 |
+
"step": 1070
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 15.707803992740471,
|
| 842 |
+
"grad_norm": 3.920423984527588,
|
| 843 |
+
"learning_rate": 1.725020920933593e-05,
|
| 844 |
+
"loss": 2.3157,
|
| 845 |
+
"step": 1080
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 15.852994555353902,
|
| 849 |
+
"grad_norm": 4.361971378326416,
|
| 850 |
+
"learning_rate": 1.717911923064442e-05,
|
| 851 |
+
"loss": 2.3078,
|
| 852 |
+
"step": 1090
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 15.998185117967331,
|
| 856 |
+
"grad_norm": 7.068411350250244,
|
| 857 |
+
"learning_rate": 1.710727255106447e-05,
|
| 858 |
+
"loss": 2.3586,
|
| 859 |
+
"step": 1100
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 15.998185117967331,
|
| 863 |
+
"eval_loss": 2.3172919750213623,
|
| 864 |
+
"eval_runtime": 14.8891,
|
| 865 |
+
"eval_samples_per_second": 191.415,
|
| 866 |
+
"eval_steps_per_second": 6.045,
|
| 867 |
+
"step": 1100
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 16.14519056261343,
|
| 871 |
+
"grad_norm": 4.1981329917907715,
|
| 872 |
+
"learning_rate": 1.70346767434535e-05,
|
| 873 |
+
"loss": 2.3117,
|
| 874 |
+
"step": 1110
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 16.29038112522686,
|
| 878 |
+
"grad_norm": 3.4976508617401123,
|
| 879 |
+
"learning_rate": 1.696133945962927e-05,
|
| 880 |
+
"loss": 2.305,
|
| 881 |
+
"step": 1120
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 16.43557168784029,
|
| 885 |
+
"grad_norm": 4.435906410217285,
|
| 886 |
+
"learning_rate": 1.6887268429563387e-05,
|
| 887 |
+
"loss": 2.2863,
|
| 888 |
+
"step": 1130
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 16.58076225045372,
|
| 892 |
+
"grad_norm": 4.972898483276367,
|
| 893 |
+
"learning_rate": 1.681247146056654e-05,
|
| 894 |
+
"loss": 2.2743,
|
| 895 |
+
"step": 1140
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 16.72595281306715,
|
| 899 |
+
"grad_norm": 4.645566940307617,
|
| 900 |
+
"learning_rate": 1.6736956436465573e-05,
|
| 901 |
+
"loss": 2.27,
|
| 902 |
+
"step": 1150
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 16.87114337568058,
|
| 906 |
+
"grad_norm": 3.4692468643188477,
|
| 907 |
+
"learning_rate": 1.6660731316772503e-05,
|
| 908 |
+
"loss": 2.2665,
|
| 909 |
+
"step": 1160
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 17.01814882032668,
|
| 913 |
+
"grad_norm": 5.320245265960693,
|
| 914 |
+
"learning_rate": 1.6583804135845582e-05,
|
| 915 |
+
"loss": 2.3195,
|
| 916 |
+
"step": 1170
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 17.16333938294011,
|
| 920 |
+
"grad_norm": 4.651059150695801,
|
| 921 |
+
"learning_rate": 1.650618300204242e-05,
|
| 922 |
+
"loss": 2.2719,
|
| 923 |
+
"step": 1180
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 17.308529945553538,
|
| 927 |
+
"grad_norm": 3.385852098464966,
|
| 928 |
+
"learning_rate": 1.6427876096865394e-05,
|
| 929 |
+
"loss": 2.2618,
|
| 930 |
+
"step": 1190
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 17.45372050816697,
|
| 934 |
+
"grad_norm": 4.4722771644592285,
|
| 935 |
+
"learning_rate": 1.634889167409923e-05,
|
| 936 |
+
"loss": 2.2455,
|
| 937 |
+
"step": 1200
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 17.45372050816697,
|
| 941 |
+
"eval_loss": 2.266216516494751,
|
| 942 |
+
"eval_runtime": 14.8832,
|
| 943 |
+
"eval_samples_per_second": 191.491,
|
| 944 |
+
"eval_steps_per_second": 6.047,
|
| 945 |
+
"step": 1200
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 17.5989110707804,
|
| 949 |
+
"grad_norm": 4.48843240737915,
|
| 950 |
+
"learning_rate": 1.626923805894107e-05,
|
| 951 |
+
"loss": 2.2325,
|
| 952 |
+
"step": 1210
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 17.74410163339383,
|
| 956 |
+
"grad_norm": 4.738080978393555,
|
| 957 |
+
"learning_rate": 1.6188923647122946e-05,
|
| 958 |
+
"loss": 2.2342,
|
| 959 |
+
"step": 1220
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 17.88929219600726,
|
| 963 |
+
"grad_norm": 3.4513983726501465,
|
| 964 |
+
"learning_rate": 1.610795690402688e-05,
|
| 965 |
+
"loss": 2.2307,
|
| 966 |
+
"step": 1230
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 18.03629764065336,
|
| 970 |
+
"grad_norm": 5.09975528717041,
|
| 971 |
+
"learning_rate": 1.6026346363792565e-05,
|
| 972 |
+
"loss": 2.2732,
|
| 973 |
+
"step": 1240
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 18.181488203266788,
|
| 977 |
+
"grad_norm": 4.678542613983154,
|
| 978 |
+
"learning_rate": 1.594410062841787e-05,
|
| 979 |
+
"loss": 2.2163,
|
| 980 |
+
"step": 1250
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 18.326678765880217,
|
| 984 |
+
"grad_norm": 4.759681701660156,
|
| 985 |
+
"learning_rate": 1.5861228366852148e-05,
|
| 986 |
+
"loss": 2.2162,
|
| 987 |
+
"step": 1260
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 18.471869328493646,
|
| 991 |
+
"grad_norm": 4.229626178741455,
|
| 992 |
+
"learning_rate": 1.5777738314082514e-05,
|
| 993 |
+
"loss": 2.2111,
|
| 994 |
+
"step": 1270
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 18.61705989110708,
|
| 998 |
+
"grad_norm": 3.9783313274383545,
|
| 999 |
+
"learning_rate": 1.5693639270213138e-05,
|
| 1000 |
+
"loss": 2.2148,
|
| 1001 |
+
"step": 1280
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 18.762250453720508,
|
| 1005 |
+
"grad_norm": 5.122952461242676,
|
| 1006 |
+
"learning_rate": 1.56089400995377e-05,
|
| 1007 |
+
"loss": 2.1918,
|
| 1008 |
+
"step": 1290
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 18.907441016333937,
|
| 1012 |
+
"grad_norm": 4.5258893966674805,
|
| 1013 |
+
"learning_rate": 1.552364972960506e-05,
|
| 1014 |
+
"loss": 2.1982,
|
| 1015 |
+
"step": 1300
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 18.907441016333937,
|
| 1019 |
+
"eval_loss": 2.218618392944336,
|
| 1020 |
+
"eval_runtime": 14.9173,
|
| 1021 |
+
"eval_samples_per_second": 191.053,
|
| 1022 |
+
"eval_steps_per_second": 6.033,
|
| 1023 |
+
"step": 1300
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 19.054446460980035,
|
| 1027 |
+
"grad_norm": 3.5518476963043213,
|
| 1028 |
+
"learning_rate": 1.5437777150278268e-05,
|
| 1029 |
+
"loss": 2.241,
|
| 1030 |
+
"step": 1310
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 19.199637023593468,
|
| 1034 |
+
"grad_norm": 3.2547390460968018,
|
| 1035 |
+
"learning_rate": 1.5351331412787004e-05,
|
| 1036 |
+
"loss": 2.1769,
|
| 1037 |
+
"step": 1320
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 19.344827586206897,
|
| 1041 |
+
"grad_norm": 4.707066535949707,
|
| 1042 |
+
"learning_rate": 1.526432162877356e-05,
|
| 1043 |
+
"loss": 2.1888,
|
| 1044 |
+
"step": 1330
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 19.490018148820326,
|
| 1048 |
+
"grad_norm": 3.84458327293396,
|
| 1049 |
+
"learning_rate": 1.5176756969332428e-05,
|
| 1050 |
+
"loss": 2.1845,
|
| 1051 |
+
"step": 1340
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 19.635208711433755,
|
| 1055 |
+
"grad_norm": 3.817499876022339,
|
| 1056 |
+
"learning_rate": 1.5088646664043652e-05,
|
| 1057 |
+
"loss": 2.1694,
|
| 1058 |
+
"step": 1350
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 19.780399274047188,
|
| 1062 |
+
"grad_norm": 3.213623285293579,
|
| 1063 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 1064 |
+
"loss": 2.1732,
|
| 1065 |
+
"step": 1360
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 19.925589836660617,
|
| 1069 |
+
"grad_norm": 3.957732677459717,
|
| 1070 |
+
"learning_rate": 1.4910826320828085e-05,
|
| 1071 |
+
"loss": 2.1611,
|
| 1072 |
+
"step": 1370
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 20.072595281306715,
|
| 1076 |
+
"grad_norm": 4.165735244750977,
|
| 1077 |
+
"learning_rate": 1.4821135025703491e-05,
|
| 1078 |
+
"loss": 2.2287,
|
| 1079 |
+
"step": 1380
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 20.217785843920144,
|
| 1083 |
+
"grad_norm": 4.221045017242432,
|
| 1084 |
+
"learning_rate": 1.4730935568360103e-05,
|
| 1085 |
+
"loss": 2.1643,
|
| 1086 |
+
"step": 1390
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 20.362976406533576,
|
| 1090 |
+
"grad_norm": 3.8451671600341797,
|
| 1091 |
+
"learning_rate": 1.4640237456093636e-05,
|
| 1092 |
+
"loss": 2.1391,
|
| 1093 |
+
"step": 1400
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 20.362976406533576,
|
| 1097 |
+
"eval_loss": 2.1760454177856445,
|
| 1098 |
+
"eval_runtime": 14.8981,
|
| 1099 |
+
"eval_samples_per_second": 191.3,
|
| 1100 |
+
"eval_steps_per_second": 6.041,
|
| 1101 |
+
"step": 1400
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 20.508166969147005,
|
| 1105 |
+
"grad_norm": 3.5534346103668213,
|
| 1106 |
+
"learning_rate": 1.4549050248759546e-05,
|
| 1107 |
+
"loss": 2.1447,
|
| 1108 |
+
"step": 1410
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 20.653357531760435,
|
| 1112 |
+
"grad_norm": 3.4696710109710693,
|
| 1113 |
+
"learning_rate": 1.4457383557765385e-05,
|
| 1114 |
+
"loss": 2.1429,
|
| 1115 |
+
"step": 1420
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 20.798548094373867,
|
| 1119 |
+
"grad_norm": 3.365741491317749,
|
| 1120 |
+
"learning_rate": 1.4365247045057732e-05,
|
| 1121 |
+
"loss": 2.1362,
|
| 1122 |
+
"step": 1430
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 20.943738656987296,
|
| 1126 |
+
"grad_norm": 3.3320400714874268,
|
| 1127 |
+
"learning_rate": 1.427265042210381e-05,
|
| 1128 |
+
"loss": 2.1331,
|
| 1129 |
+
"step": 1440
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 21.090744101633394,
|
| 1133 |
+
"grad_norm": 3.987398624420166,
|
| 1134 |
+
"learning_rate": 1.4179603448867836e-05,
|
| 1135 |
+
"loss": 2.1908,
|
| 1136 |
+
"step": 1450
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 21.235934664246823,
|
| 1140 |
+
"grad_norm": 2.9857592582702637,
|
| 1141 |
+
"learning_rate": 1.4086115932782316e-05,
|
| 1142 |
+
"loss": 2.116,
|
| 1143 |
+
"step": 1460
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 21.381125226860256,
|
| 1147 |
+
"grad_norm": 3.6675405502319336,
|
| 1148 |
+
"learning_rate": 1.399219772771431e-05,
|
| 1149 |
+
"loss": 2.1191,
|
| 1150 |
+
"step": 1470
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 21.526315789473685,
|
| 1154 |
+
"grad_norm": 3.398852586746216,
|
| 1155 |
+
"learning_rate": 1.3897858732926794e-05,
|
| 1156 |
+
"loss": 2.1145,
|
| 1157 |
+
"step": 1480
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 21.671506352087114,
|
| 1161 |
+
"grad_norm": 4.064932346343994,
|
| 1162 |
+
"learning_rate": 1.3803108892035259e-05,
|
| 1163 |
+
"loss": 2.1189,
|
| 1164 |
+
"step": 1490
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 21.816696914700543,
|
| 1168 |
+
"grad_norm": 4.461515426635742,
|
| 1169 |
+
"learning_rate": 1.3707958191959609e-05,
|
| 1170 |
+
"loss": 2.118,
|
| 1171 |
+
"step": 1500
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 21.816696914700543,
|
| 1175 |
+
"eval_loss": 2.1411948204040527,
|
| 1176 |
+
"eval_runtime": 14.8907,
|
| 1177 |
+
"eval_samples_per_second": 191.395,
|
| 1178 |
+
"eval_steps_per_second": 6.044,
|
| 1179 |
+
"step": 1500
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 21.961887477313976,
|
| 1183 |
+
"grad_norm": 4.643894195556641,
|
| 1184 |
+
"learning_rate": 1.3612416661871532e-05,
|
| 1185 |
+
"loss": 2.1139,
|
| 1186 |
+
"step": 1510
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 22.108892921960074,
|
| 1190 |
+
"grad_norm": 3.617164134979248,
|
| 1191 |
+
"learning_rate": 1.3516494372137368e-05,
|
| 1192 |
+
"loss": 2.1598,
|
| 1193 |
+
"step": 1520
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 22.254083484573503,
|
| 1197 |
+
"grad_norm": 4.053228855133057,
|
| 1198 |
+
"learning_rate": 1.342020143325669e-05,
|
| 1199 |
+
"loss": 2.1049,
|
| 1200 |
+
"step": 1530
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 22.399274047186932,
|
| 1204 |
+
"grad_norm": 3.701639175415039,
|
| 1205 |
+
"learning_rate": 1.3323547994796597e-05,
|
| 1206 |
+
"loss": 2.0949,
|
| 1207 |
+
"step": 1540
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 22.544464609800364,
|
| 1211 |
+
"grad_norm": 4.151967525482178,
|
| 1212 |
+
"learning_rate": 1.322654424432195e-05,
|
| 1213 |
+
"loss": 2.0972,
|
| 1214 |
+
"step": 1550
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 22.689655172413794,
|
| 1218 |
+
"grad_norm": 3.0913383960723877,
|
| 1219 |
+
"learning_rate": 1.3129200406321545e-05,
|
| 1220 |
+
"loss": 2.0929,
|
| 1221 |
+
"step": 1560
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 22.834845735027223,
|
| 1225 |
+
"grad_norm": 3.61426043510437,
|
| 1226 |
+
"learning_rate": 1.3031526741130435e-05,
|
| 1227 |
+
"loss": 2.0796,
|
| 1228 |
+
"step": 1570
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 22.980036297640652,
|
| 1232 |
+
"grad_norm": 2.2186896800994873,
|
| 1233 |
+
"learning_rate": 1.2933533543848462e-05,
|
| 1234 |
+
"loss": 2.0845,
|
| 1235 |
+
"step": 1580
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 23.12704174228675,
|
| 1239 |
+
"grad_norm": 3.799440860748291,
|
| 1240 |
+
"learning_rate": 1.283523114325511e-05,
|
| 1241 |
+
"loss": 2.1387,
|
| 1242 |
+
"step": 1590
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 23.272232304900182,
|
| 1246 |
+
"grad_norm": 4.307620048522949,
|
| 1247 |
+
"learning_rate": 1.2736629900720832e-05,
|
| 1248 |
+
"loss": 2.0764,
|
| 1249 |
+
"step": 1600
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 23.272232304900182,
|
| 1253 |
+
"eval_loss": 2.099868059158325,
|
| 1254 |
+
"eval_runtime": 14.8905,
|
| 1255 |
+
"eval_samples_per_second": 191.397,
|
| 1256 |
+
"eval_steps_per_second": 6.044,
|
| 1257 |
+
"step": 1600
|
| 1258 |
+
}
|
| 1259 |
+
],
|
| 1260 |
+
"logging_steps": 10,
|
| 1261 |
+
"max_steps": 3400,
|
| 1262 |
+
"num_input_tokens_seen": 0,
|
| 1263 |
+
"num_train_epochs": 50,
|
| 1264 |
+
"save_steps": 100,
|
| 1265 |
+
"stateful_callbacks": {
|
| 1266 |
+
"TrainerControl": {
|
| 1267 |
+
"args": {
|
| 1268 |
+
"should_epoch_stop": false,
|
| 1269 |
+
"should_evaluate": false,
|
| 1270 |
+
"should_log": false,
|
| 1271 |
+
"should_save": true,
|
| 1272 |
+
"should_training_stop": false
|
| 1273 |
+
},
|
| 1274 |
+
"attributes": {}
|
| 1275 |
+
}
|
| 1276 |
+
},
|
| 1277 |
+
"total_flos": 4.967214202780385e+19,
|
| 1278 |
+
"train_batch_size": 16,
|
| 1279 |
+
"trial_name": null,
|
| 1280 |
+
"trial_params": null
|
| 1281 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6eec04d1d56b269424c3ab400560656b088b5b099c39e11a7e857195594dec18
|
| 3 |
+
size 5368
|