Upload folder using huggingface_hub
Browse files- chat_template.jinja +3 -0
- config.json +33 -0
- generation_config.json +10 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +43 -0
- tokenizer.json +0 -0
- tokenizer_config.json +170 -0
- trainer_state.json +734 -0
- training_args.bin +3 -0
- vocab.json +0 -0
chat_template.jinja
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% for message in messages %}{{'<|' + message['role'] + '|>
|
| 2 |
+
' + message['content'] + '<|endoftext|>' + '
|
| 3 |
+
'}}{% endfor %}
|
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": 0,
|
| 10 |
+
"head_dim": 64,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 960,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 2560,
|
| 15 |
+
"is_llama_config": true,
|
| 16 |
+
"max_position_embeddings": 8192,
|
| 17 |
+
"mlp_bias": false,
|
| 18 |
+
"model_type": "llama",
|
| 19 |
+
"num_attention_heads": 15,
|
| 20 |
+
"num_hidden_layers": 32,
|
| 21 |
+
"num_key_value_heads": 5,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"pretraining_tp": 1,
|
| 24 |
+
"rms_norm_eps": 1e-05,
|
| 25 |
+
"rope_interleaved": false,
|
| 26 |
+
"rope_scaling": null,
|
| 27 |
+
"rope_theta": 100000,
|
| 28 |
+
"tie_word_embeddings": true,
|
| 29 |
+
"transformers_version": "4.56.1",
|
| 30 |
+
"unsloth_version": "2025.9.2",
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 49152
|
| 33 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
0
|
| 6 |
+
],
|
| 7 |
+
"max_length": 8192,
|
| 8 |
+
"pad_token_id": 0,
|
| 9 |
+
"transformers_version": "4.56.1"
|
| 10 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9061fe1d3098bc76ec3af8b81f8d68c9de26f3dae4787d2d27452ee7d4c62dce
|
| 3 |
+
size 1447317080
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91f40d4c6d42de07e5e10d3ed27a2513383955374a739423e27bafcf717d8f71
|
| 3 |
+
size 1017266409
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1d565802a8e26c4e8a31328752b7a7fdc186d9401aa008e65697d0ad8c22e33
|
| 3 |
+
size 14645
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f77569c2e850b04af982cc8c1389f1430851448915c593b69e5da36ce05b71d7
|
| 3 |
+
size 1383
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f78b220db08cf1892af4fdc13e39f2a8dc3f27c95fc50a018a62886d39ec1230
|
| 3 |
+
size 1465
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>",
|
| 4 |
+
"<|im_start|>",
|
| 5 |
+
"<|im_end|>",
|
| 6 |
+
"<repo_name>",
|
| 7 |
+
"<reponame>",
|
| 8 |
+
"<file_sep>",
|
| 9 |
+
"<filename>",
|
| 10 |
+
"<gh_stars>",
|
| 11 |
+
"<issue_start>",
|
| 12 |
+
"<issue_comment>",
|
| 13 |
+
"<issue_closed>",
|
| 14 |
+
"<jupyter_start>",
|
| 15 |
+
"<jupyter_text>",
|
| 16 |
+
"<jupyter_code>",
|
| 17 |
+
"<jupyter_output>",
|
| 18 |
+
"<jupyter_script>",
|
| 19 |
+
"<empty_output>"
|
| 20 |
+
],
|
| 21 |
+
"bos_token": {
|
| 22 |
+
"content": "<|endoftext|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false
|
| 27 |
+
},
|
| 28 |
+
"eos_token": {
|
| 29 |
+
"content": "<|endoftext|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false
|
| 34 |
+
},
|
| 35 |
+
"pad_token": "<|endoftext|>",
|
| 36 |
+
"unk_token": {
|
| 37 |
+
"content": "<|endoftext|>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false
|
| 42 |
+
}
|
| 43 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<repo_name>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<reponame>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"5": {
|
| 45 |
+
"content": "<file_sep>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"6": {
|
| 53 |
+
"content": "<filename>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"7": {
|
| 61 |
+
"content": "<gh_stars>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"8": {
|
| 69 |
+
"content": "<issue_start>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"9": {
|
| 77 |
+
"content": "<issue_comment>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"10": {
|
| 85 |
+
"content": "<issue_closed>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"11": {
|
| 93 |
+
"content": "<jupyter_start>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"12": {
|
| 101 |
+
"content": "<jupyter_text>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"13": {
|
| 109 |
+
"content": "<jupyter_code>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"14": {
|
| 117 |
+
"content": "<jupyter_output>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"15": {
|
| 125 |
+
"content": "<jupyter_script>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"16": {
|
| 133 |
+
"content": "<empty_output>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
}
|
| 140 |
+
},
|
| 141 |
+
"additional_special_tokens": [
|
| 142 |
+
"<|endoftext|>",
|
| 143 |
+
"<|im_start|>",
|
| 144 |
+
"<|im_end|>",
|
| 145 |
+
"<repo_name>",
|
| 146 |
+
"<reponame>",
|
| 147 |
+
"<file_sep>",
|
| 148 |
+
"<filename>",
|
| 149 |
+
"<gh_stars>",
|
| 150 |
+
"<issue_start>",
|
| 151 |
+
"<issue_comment>",
|
| 152 |
+
"<issue_closed>",
|
| 153 |
+
"<jupyter_start>",
|
| 154 |
+
"<jupyter_text>",
|
| 155 |
+
"<jupyter_code>",
|
| 156 |
+
"<jupyter_output>",
|
| 157 |
+
"<jupyter_script>",
|
| 158 |
+
"<empty_output>"
|
| 159 |
+
],
|
| 160 |
+
"bos_token": "<|endoftext|>",
|
| 161 |
+
"clean_up_tokenization_spaces": false,
|
| 162 |
+
"eos_token": "<|endoftext|>",
|
| 163 |
+
"extra_special_tokens": {},
|
| 164 |
+
"model_max_length": 8192,
|
| 165 |
+
"pad_token": "<|endoftext|>",
|
| 166 |
+
"padding_side": "right",
|
| 167 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 168 |
+
"unk_token": "<|endoftext|>",
|
| 169 |
+
"vocab_size": 49152
|
| 170 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,734 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.5333333333333333,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.005333333333333333,
|
| 14 |
+
"grad_norm": 2.4738848209381104,
|
| 15 |
+
"learning_rate": 8.000000000000001e-06,
|
| 16 |
+
"loss": 1.5025,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.010666666666666666,
|
| 21 |
+
"grad_norm": 1.762861967086792,
|
| 22 |
+
"learning_rate": 1.8e-05,
|
| 23 |
+
"loss": 1.2897,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.016,
|
| 28 |
+
"grad_norm": 1.465779185295105,
|
| 29 |
+
"learning_rate": 1.991919191919192e-05,
|
| 30 |
+
"loss": 1.1928,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.021333333333333333,
|
| 35 |
+
"grad_norm": 1.7229000329971313,
|
| 36 |
+
"learning_rate": 1.981818181818182e-05,
|
| 37 |
+
"loss": 1.0474,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.02666666666666667,
|
| 42 |
+
"grad_norm": 1.2843865156173706,
|
| 43 |
+
"learning_rate": 1.971717171717172e-05,
|
| 44 |
+
"loss": 0.9795,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.032,
|
| 49 |
+
"grad_norm": 1.413460612297058,
|
| 50 |
+
"learning_rate": 1.961616161616162e-05,
|
| 51 |
+
"loss": 1.0109,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.037333333333333336,
|
| 56 |
+
"grad_norm": 1.5748860836029053,
|
| 57 |
+
"learning_rate": 1.9515151515151515e-05,
|
| 58 |
+
"loss": 1.0093,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.042666666666666665,
|
| 63 |
+
"grad_norm": 1.2138009071350098,
|
| 64 |
+
"learning_rate": 1.9414141414141418e-05,
|
| 65 |
+
"loss": 0.9596,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.048,
|
| 70 |
+
"grad_norm": 1.0399284362792969,
|
| 71 |
+
"learning_rate": 1.9313131313131314e-05,
|
| 72 |
+
"loss": 0.9827,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.05333333333333334,
|
| 77 |
+
"grad_norm": 1.0604643821716309,
|
| 78 |
+
"learning_rate": 1.9212121212121213e-05,
|
| 79 |
+
"loss": 0.9304,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.058666666666666666,
|
| 84 |
+
"grad_norm": 0.8343395590782166,
|
| 85 |
+
"learning_rate": 1.9111111111111113e-05,
|
| 86 |
+
"loss": 0.8937,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.064,
|
| 91 |
+
"grad_norm": 1.1488970518112183,
|
| 92 |
+
"learning_rate": 1.9010101010101012e-05,
|
| 93 |
+
"loss": 0.9515,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.06933333333333333,
|
| 98 |
+
"grad_norm": 1.1441693305969238,
|
| 99 |
+
"learning_rate": 1.8909090909090912e-05,
|
| 100 |
+
"loss": 0.915,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.07466666666666667,
|
| 105 |
+
"grad_norm": 1.1136934757232666,
|
| 106 |
+
"learning_rate": 1.8808080808080808e-05,
|
| 107 |
+
"loss": 0.9305,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.08,
|
| 112 |
+
"grad_norm": 1.0539132356643677,
|
| 113 |
+
"learning_rate": 1.8707070707070707e-05,
|
| 114 |
+
"loss": 0.7912,
|
| 115 |
+
"step": 75
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.08533333333333333,
|
| 119 |
+
"grad_norm": 1.0501577854156494,
|
| 120 |
+
"learning_rate": 1.8606060606060607e-05,
|
| 121 |
+
"loss": 0.8899,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.09066666666666667,
|
| 126 |
+
"grad_norm": 0.6856658458709717,
|
| 127 |
+
"learning_rate": 1.8505050505050506e-05,
|
| 128 |
+
"loss": 0.8848,
|
| 129 |
+
"step": 85
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.096,
|
| 133 |
+
"grad_norm": 0.9410535097122192,
|
| 134 |
+
"learning_rate": 1.8404040404040406e-05,
|
| 135 |
+
"loss": 0.8597,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.10133333333333333,
|
| 140 |
+
"grad_norm": 1.2408137321472168,
|
| 141 |
+
"learning_rate": 1.8303030303030305e-05,
|
| 142 |
+
"loss": 1.0193,
|
| 143 |
+
"step": 95
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.10666666666666667,
|
| 147 |
+
"grad_norm": 0.8570374846458435,
|
| 148 |
+
"learning_rate": 1.82020202020202e-05,
|
| 149 |
+
"loss": 0.9621,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.112,
|
| 154 |
+
"grad_norm": 1.2646375894546509,
|
| 155 |
+
"learning_rate": 1.8101010101010104e-05,
|
| 156 |
+
"loss": 0.9349,
|
| 157 |
+
"step": 105
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.11733333333333333,
|
| 161 |
+
"grad_norm": 0.8542080521583557,
|
| 162 |
+
"learning_rate": 1.8e-05,
|
| 163 |
+
"loss": 0.9479,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.12266666666666666,
|
| 168 |
+
"grad_norm": 1.0172573328018188,
|
| 169 |
+
"learning_rate": 1.78989898989899e-05,
|
| 170 |
+
"loss": 0.8842,
|
| 171 |
+
"step": 115
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.128,
|
| 175 |
+
"grad_norm": 1.1216251850128174,
|
| 176 |
+
"learning_rate": 1.77979797979798e-05,
|
| 177 |
+
"loss": 0.9307,
|
| 178 |
+
"step": 120
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.13333333333333333,
|
| 182 |
+
"grad_norm": 1.1146503686904907,
|
| 183 |
+
"learning_rate": 1.76969696969697e-05,
|
| 184 |
+
"loss": 0.8582,
|
| 185 |
+
"step": 125
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.13866666666666666,
|
| 189 |
+
"grad_norm": 0.9401494860649109,
|
| 190 |
+
"learning_rate": 1.75959595959596e-05,
|
| 191 |
+
"loss": 0.8146,
|
| 192 |
+
"step": 130
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.144,
|
| 196 |
+
"grad_norm": 1.0174555778503418,
|
| 197 |
+
"learning_rate": 1.7494949494949494e-05,
|
| 198 |
+
"loss": 0.8064,
|
| 199 |
+
"step": 135
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.14933333333333335,
|
| 203 |
+
"grad_norm": 0.7621330618858337,
|
| 204 |
+
"learning_rate": 1.7393939393939397e-05,
|
| 205 |
+
"loss": 0.8382,
|
| 206 |
+
"step": 140
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.15466666666666667,
|
| 210 |
+
"grad_norm": 1.1294023990631104,
|
| 211 |
+
"learning_rate": 1.7292929292929293e-05,
|
| 212 |
+
"loss": 0.9458,
|
| 213 |
+
"step": 145
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.16,
|
| 217 |
+
"grad_norm": 0.7517912983894348,
|
| 218 |
+
"learning_rate": 1.7191919191919193e-05,
|
| 219 |
+
"loss": 0.797,
|
| 220 |
+
"step": 150
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.16533333333333333,
|
| 224 |
+
"grad_norm": 1.0522116422653198,
|
| 225 |
+
"learning_rate": 1.7090909090909092e-05,
|
| 226 |
+
"loss": 0.96,
|
| 227 |
+
"step": 155
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.17066666666666666,
|
| 231 |
+
"grad_norm": 0.9202107787132263,
|
| 232 |
+
"learning_rate": 1.6989898989898992e-05,
|
| 233 |
+
"loss": 0.8193,
|
| 234 |
+
"step": 160
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.176,
|
| 238 |
+
"grad_norm": 0.7169008851051331,
|
| 239 |
+
"learning_rate": 1.688888888888889e-05,
|
| 240 |
+
"loss": 0.9014,
|
| 241 |
+
"step": 165
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.18133333333333335,
|
| 245 |
+
"grad_norm": 1.011110782623291,
|
| 246 |
+
"learning_rate": 1.6787878787878787e-05,
|
| 247 |
+
"loss": 0.8433,
|
| 248 |
+
"step": 170
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.18666666666666668,
|
| 252 |
+
"grad_norm": 0.9050607681274414,
|
| 253 |
+
"learning_rate": 1.668686868686869e-05,
|
| 254 |
+
"loss": 0.9545,
|
| 255 |
+
"step": 175
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.192,
|
| 259 |
+
"grad_norm": 0.8567696809768677,
|
| 260 |
+
"learning_rate": 1.6585858585858586e-05,
|
| 261 |
+
"loss": 0.8788,
|
| 262 |
+
"step": 180
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.19733333333333333,
|
| 266 |
+
"grad_norm": 0.8334883451461792,
|
| 267 |
+
"learning_rate": 1.6484848484848486e-05,
|
| 268 |
+
"loss": 0.8851,
|
| 269 |
+
"step": 185
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.20266666666666666,
|
| 273 |
+
"grad_norm": 1.0018478631973267,
|
| 274 |
+
"learning_rate": 1.6383838383838385e-05,
|
| 275 |
+
"loss": 0.9585,
|
| 276 |
+
"step": 190
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.208,
|
| 280 |
+
"grad_norm": 0.9261645078659058,
|
| 281 |
+
"learning_rate": 1.6282828282828285e-05,
|
| 282 |
+
"loss": 0.9198,
|
| 283 |
+
"step": 195
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.21333333333333335,
|
| 287 |
+
"grad_norm": 1.0422159433364868,
|
| 288 |
+
"learning_rate": 1.6181818181818184e-05,
|
| 289 |
+
"loss": 0.8987,
|
| 290 |
+
"step": 200
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.21866666666666668,
|
| 294 |
+
"grad_norm": 1.1883363723754883,
|
| 295 |
+
"learning_rate": 1.608080808080808e-05,
|
| 296 |
+
"loss": 0.8344,
|
| 297 |
+
"step": 205
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.224,
|
| 301 |
+
"grad_norm": 1.0698201656341553,
|
| 302 |
+
"learning_rate": 1.5979797979797983e-05,
|
| 303 |
+
"loss": 0.9163,
|
| 304 |
+
"step": 210
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.22933333333333333,
|
| 308 |
+
"grad_norm": 1.002856969833374,
|
| 309 |
+
"learning_rate": 1.587878787878788e-05,
|
| 310 |
+
"loss": 0.8067,
|
| 311 |
+
"step": 215
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.23466666666666666,
|
| 315 |
+
"grad_norm": 0.7221589684486389,
|
| 316 |
+
"learning_rate": 1.577777777777778e-05,
|
| 317 |
+
"loss": 0.7832,
|
| 318 |
+
"step": 220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.24,
|
| 322 |
+
"grad_norm": 0.9534178376197815,
|
| 323 |
+
"learning_rate": 1.5676767676767678e-05,
|
| 324 |
+
"loss": 0.9086,
|
| 325 |
+
"step": 225
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.24533333333333332,
|
| 329 |
+
"grad_norm": 0.768618106842041,
|
| 330 |
+
"learning_rate": 1.5575757575757578e-05,
|
| 331 |
+
"loss": 0.8779,
|
| 332 |
+
"step": 230
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.25066666666666665,
|
| 336 |
+
"grad_norm": 1.1509809494018555,
|
| 337 |
+
"learning_rate": 1.5474747474747477e-05,
|
| 338 |
+
"loss": 0.8655,
|
| 339 |
+
"step": 235
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.256,
|
| 343 |
+
"grad_norm": 1.124725103378296,
|
| 344 |
+
"learning_rate": 1.5373737373737373e-05,
|
| 345 |
+
"loss": 0.9216,
|
| 346 |
+
"step": 240
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.2613333333333333,
|
| 350 |
+
"grad_norm": 1.2690633535385132,
|
| 351 |
+
"learning_rate": 1.5272727272727276e-05,
|
| 352 |
+
"loss": 1.0696,
|
| 353 |
+
"step": 245
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.26666666666666666,
|
| 357 |
+
"grad_norm": 0.8243642449378967,
|
| 358 |
+
"learning_rate": 1.5171717171717172e-05,
|
| 359 |
+
"loss": 0.8819,
|
| 360 |
+
"step": 250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.272,
|
| 364 |
+
"grad_norm": 1.029197335243225,
|
| 365 |
+
"learning_rate": 1.5070707070707072e-05,
|
| 366 |
+
"loss": 0.8729,
|
| 367 |
+
"step": 255
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.2773333333333333,
|
| 371 |
+
"grad_norm": 1.1257883310317993,
|
| 372 |
+
"learning_rate": 1.4969696969696971e-05,
|
| 373 |
+
"loss": 0.8183,
|
| 374 |
+
"step": 260
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.2826666666666667,
|
| 378 |
+
"grad_norm": 1.0707664489746094,
|
| 379 |
+
"learning_rate": 1.486868686868687e-05,
|
| 380 |
+
"loss": 0.9269,
|
| 381 |
+
"step": 265
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.288,
|
| 385 |
+
"grad_norm": 0.7989206314086914,
|
| 386 |
+
"learning_rate": 1.4767676767676769e-05,
|
| 387 |
+
"loss": 0.7724,
|
| 388 |
+
"step": 270
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.29333333333333333,
|
| 392 |
+
"grad_norm": 1.036672830581665,
|
| 393 |
+
"learning_rate": 1.4666666666666666e-05,
|
| 394 |
+
"loss": 0.9049,
|
| 395 |
+
"step": 275
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.2986666666666667,
|
| 399 |
+
"grad_norm": 1.2170835733413696,
|
| 400 |
+
"learning_rate": 1.4565656565656567e-05,
|
| 401 |
+
"loss": 0.8528,
|
| 402 |
+
"step": 280
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.304,
|
| 406 |
+
"grad_norm": 0.8174688816070557,
|
| 407 |
+
"learning_rate": 1.4464646464646465e-05,
|
| 408 |
+
"loss": 0.814,
|
| 409 |
+
"step": 285
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.30933333333333335,
|
| 413 |
+
"grad_norm": 1.1070367097854614,
|
| 414 |
+
"learning_rate": 1.4363636363636365e-05,
|
| 415 |
+
"loss": 0.8746,
|
| 416 |
+
"step": 290
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.31466666666666665,
|
| 420 |
+
"grad_norm": 0.904995322227478,
|
| 421 |
+
"learning_rate": 1.4262626262626264e-05,
|
| 422 |
+
"loss": 0.917,
|
| 423 |
+
"step": 295
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.32,
|
| 427 |
+
"grad_norm": 0.7519875764846802,
|
| 428 |
+
"learning_rate": 1.4161616161616164e-05,
|
| 429 |
+
"loss": 0.7766,
|
| 430 |
+
"step": 300
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.3253333333333333,
|
| 434 |
+
"grad_norm": 0.8368961215019226,
|
| 435 |
+
"learning_rate": 1.4060606060606061e-05,
|
| 436 |
+
"loss": 0.8573,
|
| 437 |
+
"step": 305
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.33066666666666666,
|
| 441 |
+
"grad_norm": 0.9424313306808472,
|
| 442 |
+
"learning_rate": 1.3959595959595963e-05,
|
| 443 |
+
"loss": 0.8728,
|
| 444 |
+
"step": 310
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.336,
|
| 448 |
+
"grad_norm": 1.1850807666778564,
|
| 449 |
+
"learning_rate": 1.385858585858586e-05,
|
| 450 |
+
"loss": 0.8281,
|
| 451 |
+
"step": 315
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.3413333333333333,
|
| 455 |
+
"grad_norm": 0.765692949295044,
|
| 456 |
+
"learning_rate": 1.3757575757575758e-05,
|
| 457 |
+
"loss": 0.9035,
|
| 458 |
+
"step": 320
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.3466666666666667,
|
| 462 |
+
"grad_norm": 1.218376636505127,
|
| 463 |
+
"learning_rate": 1.3656565656565656e-05,
|
| 464 |
+
"loss": 0.8927,
|
| 465 |
+
"step": 325
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.352,
|
| 469 |
+
"grad_norm": 0.9827937483787537,
|
| 470 |
+
"learning_rate": 1.3555555555555557e-05,
|
| 471 |
+
"loss": 0.9812,
|
| 472 |
+
"step": 330
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.35733333333333334,
|
| 476 |
+
"grad_norm": 0.7617772221565247,
|
| 477 |
+
"learning_rate": 1.3454545454545455e-05,
|
| 478 |
+
"loss": 0.8899,
|
| 479 |
+
"step": 335
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.3626666666666667,
|
| 483 |
+
"grad_norm": 1.2161617279052734,
|
| 484 |
+
"learning_rate": 1.3353535353535354e-05,
|
| 485 |
+
"loss": 0.8615,
|
| 486 |
+
"step": 340
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.368,
|
| 490 |
+
"grad_norm": 1.0964343547821045,
|
| 491 |
+
"learning_rate": 1.3252525252525254e-05,
|
| 492 |
+
"loss": 0.8452,
|
| 493 |
+
"step": 345
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.37333333333333335,
|
| 497 |
+
"grad_norm": 1.0064449310302734,
|
| 498 |
+
"learning_rate": 1.3151515151515153e-05,
|
| 499 |
+
"loss": 0.7828,
|
| 500 |
+
"step": 350
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.37866666666666665,
|
| 504 |
+
"grad_norm": 1.4947946071624756,
|
| 505 |
+
"learning_rate": 1.3050505050505051e-05,
|
| 506 |
+
"loss": 0.8614,
|
| 507 |
+
"step": 355
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.384,
|
| 511 |
+
"grad_norm": 0.8540753722190857,
|
| 512 |
+
"learning_rate": 1.2949494949494949e-05,
|
| 513 |
+
"loss": 0.947,
|
| 514 |
+
"step": 360
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.3893333333333333,
|
| 518 |
+
"grad_norm": 1.0984326601028442,
|
| 519 |
+
"learning_rate": 1.284848484848485e-05,
|
| 520 |
+
"loss": 0.83,
|
| 521 |
+
"step": 365
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.39466666666666667,
|
| 525 |
+
"grad_norm": 1.2395354509353638,
|
| 526 |
+
"learning_rate": 1.2747474747474748e-05,
|
| 527 |
+
"loss": 0.8367,
|
| 528 |
+
"step": 370
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.4,
|
| 532 |
+
"grad_norm": 1.0039360523223877,
|
| 533 |
+
"learning_rate": 1.2646464646464647e-05,
|
| 534 |
+
"loss": 0.8774,
|
| 535 |
+
"step": 375
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.4053333333333333,
|
| 539 |
+
"grad_norm": 0.863132655620575,
|
| 540 |
+
"learning_rate": 1.2545454545454547e-05,
|
| 541 |
+
"loss": 0.9715,
|
| 542 |
+
"step": 380
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.4106666666666667,
|
| 546 |
+
"grad_norm": 1.2156693935394287,
|
| 547 |
+
"learning_rate": 1.2444444444444446e-05,
|
| 548 |
+
"loss": 0.9005,
|
| 549 |
+
"step": 385
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.416,
|
| 553 |
+
"grad_norm": 1.049648642539978,
|
| 554 |
+
"learning_rate": 1.2343434343434344e-05,
|
| 555 |
+
"loss": 0.7847,
|
| 556 |
+
"step": 390
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.42133333333333334,
|
| 560 |
+
"grad_norm": 1.1432439088821411,
|
| 561 |
+
"learning_rate": 1.2242424242424242e-05,
|
| 562 |
+
"loss": 0.9426,
|
| 563 |
+
"step": 395
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.4266666666666667,
|
| 567 |
+
"grad_norm": 1.164472222328186,
|
| 568 |
+
"learning_rate": 1.2141414141414143e-05,
|
| 569 |
+
"loss": 0.7819,
|
| 570 |
+
"step": 400
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.432,
|
| 574 |
+
"grad_norm": 1.2343779802322388,
|
| 575 |
+
"learning_rate": 1.2040404040404041e-05,
|
| 576 |
+
"loss": 0.9257,
|
| 577 |
+
"step": 405
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.43733333333333335,
|
| 581 |
+
"grad_norm": 0.9872158169746399,
|
| 582 |
+
"learning_rate": 1.193939393939394e-05,
|
| 583 |
+
"loss": 0.8634,
|
| 584 |
+
"step": 410
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.44266666666666665,
|
| 588 |
+
"grad_norm": 1.0840346813201904,
|
| 589 |
+
"learning_rate": 1.183838383838384e-05,
|
| 590 |
+
"loss": 0.8683,
|
| 591 |
+
"step": 415
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.448,
|
| 595 |
+
"grad_norm": 0.9825693964958191,
|
| 596 |
+
"learning_rate": 1.1737373737373738e-05,
|
| 597 |
+
"loss": 0.8948,
|
| 598 |
+
"step": 420
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.4533333333333333,
|
| 602 |
+
"grad_norm": 1.0183353424072266,
|
| 603 |
+
"learning_rate": 1.1636363636363637e-05,
|
| 604 |
+
"loss": 0.8223,
|
| 605 |
+
"step": 425
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.45866666666666667,
|
| 609 |
+
"grad_norm": 1.3394027948379517,
|
| 610 |
+
"learning_rate": 1.1535353535353537e-05,
|
| 611 |
+
"loss": 0.9228,
|
| 612 |
+
"step": 430
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.464,
|
| 616 |
+
"grad_norm": 1.4407519102096558,
|
| 617 |
+
"learning_rate": 1.1434343434343436e-05,
|
| 618 |
+
"loss": 0.9024,
|
| 619 |
+
"step": 435
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.4693333333333333,
|
| 623 |
+
"grad_norm": 0.9945356249809265,
|
| 624 |
+
"learning_rate": 1.1333333333333334e-05,
|
| 625 |
+
"loss": 0.9539,
|
| 626 |
+
"step": 440
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.4746666666666667,
|
| 630 |
+
"grad_norm": 0.9333862066268921,
|
| 631 |
+
"learning_rate": 1.1232323232323232e-05,
|
| 632 |
+
"loss": 0.9207,
|
| 633 |
+
"step": 445
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.48,
|
| 637 |
+
"grad_norm": 1.0179983377456665,
|
| 638 |
+
"learning_rate": 1.1131313131313133e-05,
|
| 639 |
+
"loss": 0.8696,
|
| 640 |
+
"step": 450
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.48533333333333334,
|
| 644 |
+
"grad_norm": 0.9237622022628784,
|
| 645 |
+
"learning_rate": 1.103030303030303e-05,
|
| 646 |
+
"loss": 0.8386,
|
| 647 |
+
"step": 455
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.49066666666666664,
|
| 651 |
+
"grad_norm": 1.4150505065917969,
|
| 652 |
+
"learning_rate": 1.092929292929293e-05,
|
| 653 |
+
"loss": 0.8134,
|
| 654 |
+
"step": 460
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.496,
|
| 658 |
+
"grad_norm": 1.1595478057861328,
|
| 659 |
+
"learning_rate": 1.082828282828283e-05,
|
| 660 |
+
"loss": 0.9826,
|
| 661 |
+
"step": 465
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.5013333333333333,
|
| 665 |
+
"grad_norm": 0.8624115586280823,
|
| 666 |
+
"learning_rate": 1.0727272727272729e-05,
|
| 667 |
+
"loss": 0.8796,
|
| 668 |
+
"step": 470
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.5066666666666667,
|
| 672 |
+
"grad_norm": 1.2092162370681763,
|
| 673 |
+
"learning_rate": 1.0626262626262627e-05,
|
| 674 |
+
"loss": 0.8048,
|
| 675 |
+
"step": 475
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.512,
|
| 679 |
+
"grad_norm": 0.9284762740135193,
|
| 680 |
+
"learning_rate": 1.0525252525252525e-05,
|
| 681 |
+
"loss": 0.8682,
|
| 682 |
+
"step": 480
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.5173333333333333,
|
| 686 |
+
"grad_norm": 0.9929215908050537,
|
| 687 |
+
"learning_rate": 1.0424242424242426e-05,
|
| 688 |
+
"loss": 0.8049,
|
| 689 |
+
"step": 485
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.5226666666666666,
|
| 693 |
+
"grad_norm": 0.8166928291320801,
|
| 694 |
+
"learning_rate": 1.0323232323232324e-05,
|
| 695 |
+
"loss": 0.8942,
|
| 696 |
+
"step": 490
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.528,
|
| 700 |
+
"grad_norm": 1.2903831005096436,
|
| 701 |
+
"learning_rate": 1.0222222222222223e-05,
|
| 702 |
+
"loss": 0.8789,
|
| 703 |
+
"step": 495
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.5333333333333333,
|
| 707 |
+
"grad_norm": 1.0434647798538208,
|
| 708 |
+
"learning_rate": 1.0121212121212122e-05,
|
| 709 |
+
"loss": 0.8461,
|
| 710 |
+
"step": 500
|
| 711 |
+
}
|
| 712 |
+
],
|
| 713 |
+
"logging_steps": 5,
|
| 714 |
+
"max_steps": 1000,
|
| 715 |
+
"num_input_tokens_seen": 0,
|
| 716 |
+
"num_train_epochs": 2,
|
| 717 |
+
"save_steps": 500,
|
| 718 |
+
"stateful_callbacks": {
|
| 719 |
+
"TrainerControl": {
|
| 720 |
+
"args": {
|
| 721 |
+
"should_epoch_stop": false,
|
| 722 |
+
"should_evaluate": false,
|
| 723 |
+
"should_log": false,
|
| 724 |
+
"should_save": true,
|
| 725 |
+
"should_training_stop": false
|
| 726 |
+
},
|
| 727 |
+
"attributes": {}
|
| 728 |
+
}
|
| 729 |
+
},
|
| 730 |
+
"total_flos": 2991742779801600.0,
|
| 731 |
+
"train_batch_size": 1,
|
| 732 |
+
"trial_name": null,
|
| 733 |
+
"trial_params": null
|
| 734 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae3d23346b0392d354b6fd466087a3a3f738c614ddfd19d25400d6beb0f42ba2
|
| 3 |
+
size 6289
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|