Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- added_tokens.json +28 -0
- chat_template.jinja +13 -0
- config.json +30 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +239 -0
- trainer_state.json +1625 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 2 |
+
{%- set system_message = messages[0]['content'] %}
|
| 3 |
+
{%- set messages = messages[1:] %}
|
| 4 |
+
{%- else %}
|
| 5 |
+
{%- set system_message = 'You are a helpful assistant, that answer STEM questions. Here is the format in which you are supposed to answer: \nBelow you are provided with three example questions and the expected answer format you should give. Just answer with A, B, C, or D.\n\nThe following are multiple choice questions (with answers) about knowledge and skills in advanced master-level STEM courses.\n\nPerformance enhancing synthetic steroids are based on the structure of the hormone:\nA. testosterone.\nB. cortisol.\nC. progesterone.\nD. aldosterone.\nAnswer:A\n\nThe following are multiple choice questions (with answers) about knowledge and skills in advanced master-level STEM courses.\nAsp235Phe in a molecular report indicates that:\nA. asparagine has been replaced by phenylalanine.\nB. phenylalanine has been replaced by asparagine.\nC. aspartic acid has been replaced by phenylalanine.\nD. phenylalanine has been replaced by aspartic acid.\nAnswer:C\n\nThe following are multiple choice questions (with answers) about knowledge and skills in advanced master-level STEM courses.\nThe concept of V/f control of inverters driving induction motors results in:\nA. constant torque operation \nB. speed reversal \nC. reduced magnetic loss \nD. harmonic elimination \nAnswer:A\n\nAnswer the following question in the same way:' %}
|
| 6 |
+
{%- endif %}
|
| 7 |
+
{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}
|
| 8 |
+
{%- for message in messages %}
|
| 9 |
+
{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{%- if add_generation_prompt %}
|
| 12 |
+
{{ '<|im_start|>assistant\n' }}
|
| 13 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151643,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"max_position_embeddings": 32768,
|
| 15 |
+
"max_window_layers": 28,
|
| 16 |
+
"model_type": "qwen3",
|
| 17 |
+
"num_attention_heads": 16,
|
| 18 |
+
"num_hidden_layers": 28,
|
| 19 |
+
"num_key_value_heads": 8,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 1000000,
|
| 23 |
+
"sliding_window": null,
|
| 24 |
+
"tie_word_embeddings": true,
|
| 25 |
+
"torch_dtype": "bfloat16",
|
| 26 |
+
"transformers_version": "4.52.3",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"use_sliding_window": false,
|
| 29 |
+
"vocab_size": 151936
|
| 30 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"eos_token_id": 151643,
|
| 4 |
+
"max_new_tokens": 2048,
|
| 5 |
+
"transformers_version": "4.52.3"
|
| 6 |
+
}
|
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:cae9fb38b5cd7572bca671ebd993033b3c55690ae74ce227f1567c00de2409f3
|
| 3 |
+
size 1192135096
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:322e1f70953507baa30c42a4991d4c48dec2cca979d24af22fca173b78b0c4f0
|
| 3 |
+
size 2384460363
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c0b314d655e9be31e93455deb9fbabd83362b86e9c047746bf9788399d89574
|
| 3 |
+
size 14645
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a142a610e622c0db621d1f04872376e43d9d8e788468c7ecf51eee294b28b92
|
| 3 |
+
size 1465
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|endoftext|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 131072,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"split_special_tokens": false,
|
| 237 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 238 |
+
"unk_token": null
|
| 239 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1625 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 875,
|
| 3 |
+
"best_metric": 0.41610679030418396,
|
| 4 |
+
"best_model_checkpoint": "/home/ricoiban/GEMMA/mnlp_chatsplaining/results_model/try_ft/checkpoint-875",
|
| 5 |
+
"epoch": 0.5460448642266824,
|
| 6 |
+
"eval_steps": 25,
|
| 7 |
+
"global_step": 925,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0029515938606847697,
|
| 14 |
+
"grad_norm": 274.0,
|
| 15 |
+
"learning_rate": 4.800000000000001e-06,
|
| 16 |
+
"loss": 10.7873,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0059031877213695395,
|
| 21 |
+
"grad_norm": 160.0,
|
| 22 |
+
"learning_rate": 1.08e-05,
|
| 23 |
+
"loss": 8.2818,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.00885478158205431,
|
| 28 |
+
"grad_norm": 96.0,
|
| 29 |
+
"learning_rate": 1.6800000000000002e-05,
|
| 30 |
+
"loss": 5.4171,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.011806375442739079,
|
| 35 |
+
"grad_norm": 141.0,
|
| 36 |
+
"learning_rate": 2.2800000000000002e-05,
|
| 37 |
+
"loss": 4.8734,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.01475796930342385,
|
| 42 |
+
"grad_norm": 111.0,
|
| 43 |
+
"learning_rate": 2.88e-05,
|
| 44 |
+
"loss": 4.5143,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.01475796930342385,
|
| 49 |
+
"eval_loss": 4.148748874664307,
|
| 50 |
+
"eval_runtime": 22.5903,
|
| 51 |
+
"eval_samples_per_second": 88.534,
|
| 52 |
+
"eval_steps_per_second": 88.534,
|
| 53 |
+
"step": 25
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.01770956316410862,
|
| 57 |
+
"grad_norm": 234.0,
|
| 58 |
+
"learning_rate": 3.48e-05,
|
| 59 |
+
"loss": 4.0827,
|
| 60 |
+
"step": 30
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.02066115702479339,
|
| 64 |
+
"grad_norm": 173.0,
|
| 65 |
+
"learning_rate": 4.08e-05,
|
| 66 |
+
"loss": 3.624,
|
| 67 |
+
"step": 35
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.023612750885478158,
|
| 71 |
+
"grad_norm": 91.0,
|
| 72 |
+
"learning_rate": 4.6800000000000006e-05,
|
| 73 |
+
"loss": 2.6036,
|
| 74 |
+
"step": 40
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.026564344746162927,
|
| 78 |
+
"grad_norm": 163.0,
|
| 79 |
+
"learning_rate": 5.28e-05,
|
| 80 |
+
"loss": 1.9856,
|
| 81 |
+
"step": 45
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.0295159386068477,
|
| 85 |
+
"grad_norm": 65.0,
|
| 86 |
+
"learning_rate": 5.88e-05,
|
| 87 |
+
"loss": 1.1888,
|
| 88 |
+
"step": 50
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.0295159386068477,
|
| 92 |
+
"eval_loss": 0.8685765862464905,
|
| 93 |
+
"eval_runtime": 22.0353,
|
| 94 |
+
"eval_samples_per_second": 90.764,
|
| 95 |
+
"eval_steps_per_second": 90.764,
|
| 96 |
+
"step": 50
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.032467532467532464,
|
| 100 |
+
"grad_norm": 31.125,
|
| 101 |
+
"learning_rate": 5.9999123594193744e-05,
|
| 102 |
+
"loss": 0.7088,
|
| 103 |
+
"step": 55
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 0.03541912632821724,
|
| 107 |
+
"grad_norm": 25.625,
|
| 108 |
+
"learning_rate": 5.9995563283365586e-05,
|
| 109 |
+
"loss": 0.4428,
|
| 110 |
+
"step": 60
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.03837072018890201,
|
| 114 |
+
"grad_norm": 38.25,
|
| 115 |
+
"learning_rate": 5.998926461693058e-05,
|
| 116 |
+
"loss": 0.7334,
|
| 117 |
+
"step": 65
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.04132231404958678,
|
| 121 |
+
"grad_norm": 13.375,
|
| 122 |
+
"learning_rate": 5.9980228169906714e-05,
|
| 123 |
+
"loss": 0.6483,
|
| 124 |
+
"step": 70
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.04427390791027155,
|
| 128 |
+
"grad_norm": 41.5,
|
| 129 |
+
"learning_rate": 5.9968454767249506e-05,
|
| 130 |
+
"loss": 0.5933,
|
| 131 |
+
"step": 75
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.04427390791027155,
|
| 135 |
+
"eval_loss": 0.6194470524787903,
|
| 136 |
+
"eval_runtime": 22.0585,
|
| 137 |
+
"eval_samples_per_second": 90.668,
|
| 138 |
+
"eval_steps_per_second": 90.668,
|
| 139 |
+
"step": 75
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 0.047225501770956316,
|
| 143 |
+
"grad_norm": 26.0,
|
| 144 |
+
"learning_rate": 5.995394548377669e-05,
|
| 145 |
+
"loss": 0.7882,
|
| 146 |
+
"step": 80
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.050177095631641085,
|
| 150 |
+
"grad_norm": 17.875,
|
| 151 |
+
"learning_rate": 5.993670164407008e-05,
|
| 152 |
+
"loss": 0.6423,
|
| 153 |
+
"step": 85
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.053128689492325853,
|
| 157 |
+
"grad_norm": 19.75,
|
| 158 |
+
"learning_rate": 5.991672482235466e-05,
|
| 159 |
+
"loss": 0.6952,
|
| 160 |
+
"step": 90
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.05608028335301062,
|
| 164 |
+
"grad_norm": 19.875,
|
| 165 |
+
"learning_rate": 5.9894016842354855e-05,
|
| 166 |
+
"loss": 0.6287,
|
| 167 |
+
"step": 95
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.0590318772136954,
|
| 171 |
+
"grad_norm": 19.75,
|
| 172 |
+
"learning_rate": 5.986857977712809e-05,
|
| 173 |
+
"loss": 0.6606,
|
| 174 |
+
"step": 100
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.0590318772136954,
|
| 178 |
+
"eval_loss": 0.5243311524391174,
|
| 179 |
+
"eval_runtime": 22.0497,
|
| 180 |
+
"eval_samples_per_second": 90.704,
|
| 181 |
+
"eval_steps_per_second": 90.704,
|
| 182 |
+
"step": 100
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.06198347107438017,
|
| 186 |
+
"grad_norm": 26.25,
|
| 187 |
+
"learning_rate": 5.9840415948875444e-05,
|
| 188 |
+
"loss": 0.6193,
|
| 189 |
+
"step": 105
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.06493506493506493,
|
| 193 |
+
"grad_norm": 9.9375,
|
| 194 |
+
"learning_rate": 5.980952792872975e-05,
|
| 195 |
+
"loss": 0.5167,
|
| 196 |
+
"step": 110
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.0678866587957497,
|
| 200 |
+
"grad_norm": 35.0,
|
| 201 |
+
"learning_rate": 5.9775918536520786e-05,
|
| 202 |
+
"loss": 0.5922,
|
| 203 |
+
"step": 115
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.07083825265643448,
|
| 207 |
+
"grad_norm": 35.25,
|
| 208 |
+
"learning_rate": 5.973959084051791e-05,
|
| 209 |
+
"loss": 0.7114,
|
| 210 |
+
"step": 120
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.07378984651711924,
|
| 214 |
+
"grad_norm": 8.5625,
|
| 215 |
+
"learning_rate": 5.970054815714995e-05,
|
| 216 |
+
"loss": 0.6309,
|
| 217 |
+
"step": 125
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.07378984651711924,
|
| 221 |
+
"eval_loss": 0.644968569278717,
|
| 222 |
+
"eval_runtime": 22.0752,
|
| 223 |
+
"eval_samples_per_second": 90.6,
|
| 224 |
+
"eval_steps_per_second": 90.6,
|
| 225 |
+
"step": 125
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.07674144037780402,
|
| 229 |
+
"grad_norm": 19.375,
|
| 230 |
+
"learning_rate": 5.965879405070235e-05,
|
| 231 |
+
"loss": 0.622,
|
| 232 |
+
"step": 130
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.07969303423848878,
|
| 236 |
+
"grad_norm": 15.4375,
|
| 237 |
+
"learning_rate": 5.961433233299193e-05,
|
| 238 |
+
"loss": 0.5902,
|
| 239 |
+
"step": 135
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.08264462809917356,
|
| 243 |
+
"grad_norm": 19.375,
|
| 244 |
+
"learning_rate": 5.956716706301877e-05,
|
| 245 |
+
"loss": 0.6647,
|
| 246 |
+
"step": 140
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.08559622195985832,
|
| 250 |
+
"grad_norm": 11.0,
|
| 251 |
+
"learning_rate": 5.951730254659569e-05,
|
| 252 |
+
"loss": 0.7817,
|
| 253 |
+
"step": 145
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.0885478158205431,
|
| 257 |
+
"grad_norm": 16.875,
|
| 258 |
+
"learning_rate": 5.946474333595521e-05,
|
| 259 |
+
"loss": 0.6154,
|
| 260 |
+
"step": 150
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.0885478158205431,
|
| 264 |
+
"eval_loss": 0.5631881356239319,
|
| 265 |
+
"eval_runtime": 22.058,
|
| 266 |
+
"eval_samples_per_second": 90.67,
|
| 267 |
+
"eval_steps_per_second": 90.67,
|
| 268 |
+
"step": 150
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.09149940968122787,
|
| 272 |
+
"grad_norm": 17.625,
|
| 273 |
+
"learning_rate": 5.9409494229333904e-05,
|
| 274 |
+
"loss": 0.6532,
|
| 275 |
+
"step": 155
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.09445100354191263,
|
| 279 |
+
"grad_norm": 22.25,
|
| 280 |
+
"learning_rate": 5.935156027053442e-05,
|
| 281 |
+
"loss": 0.6099,
|
| 282 |
+
"step": 160
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.09740259740259741,
|
| 286 |
+
"grad_norm": 25.5,
|
| 287 |
+
"learning_rate": 5.929094674846495e-05,
|
| 288 |
+
"loss": 0.7848,
|
| 289 |
+
"step": 165
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.10035419126328217,
|
| 293 |
+
"grad_norm": 22.0,
|
| 294 |
+
"learning_rate": 5.922765919665644e-05,
|
| 295 |
+
"loss": 0.5597,
|
| 296 |
+
"step": 170
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.10330578512396695,
|
| 300 |
+
"grad_norm": 11.9375,
|
| 301 |
+
"learning_rate": 5.916170339275745e-05,
|
| 302 |
+
"loss": 0.6166,
|
| 303 |
+
"step": 175
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.10330578512396695,
|
| 307 |
+
"eval_loss": 0.5547081828117371,
|
| 308 |
+
"eval_runtime": 22.0339,
|
| 309 |
+
"eval_samples_per_second": 90.769,
|
| 310 |
+
"eval_steps_per_second": 90.769,
|
| 311 |
+
"step": 175
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.10625737898465171,
|
| 315 |
+
"grad_norm": 12.625,
|
| 316 |
+
"learning_rate": 5.909308535800664e-05,
|
| 317 |
+
"loss": 0.5548,
|
| 318 |
+
"step": 180
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.10920897284533648,
|
| 322 |
+
"grad_norm": 32.5,
|
| 323 |
+
"learning_rate": 5.90218113566831e-05,
|
| 324 |
+
"loss": 0.5793,
|
| 325 |
+
"step": 185
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.11216056670602124,
|
| 329 |
+
"grad_norm": 19.0,
|
| 330 |
+
"learning_rate": 5.8947887895534504e-05,
|
| 331 |
+
"loss": 0.8419,
|
| 332 |
+
"step": 190
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.11511216056670602,
|
| 336 |
+
"grad_norm": 12.5625,
|
| 337 |
+
"learning_rate": 5.8871321723183046e-05,
|
| 338 |
+
"loss": 0.6571,
|
| 339 |
+
"step": 195
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.1180637544273908,
|
| 343 |
+
"grad_norm": 18.375,
|
| 344 |
+
"learning_rate": 5.879211982950937e-05,
|
| 345 |
+
"loss": 0.6579,
|
| 346 |
+
"step": 200
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.1180637544273908,
|
| 350 |
+
"eval_loss": 0.5850950479507446,
|
| 351 |
+
"eval_runtime": 22.079,
|
| 352 |
+
"eval_samples_per_second": 90.584,
|
| 353 |
+
"eval_steps_per_second": 90.584,
|
| 354 |
+
"step": 200
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.12101534828807556,
|
| 358 |
+
"grad_norm": 20.0,
|
| 359 |
+
"learning_rate": 5.871028944501446e-05,
|
| 360 |
+
"loss": 0.5835,
|
| 361 |
+
"step": 205
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.12396694214876033,
|
| 365 |
+
"grad_norm": 20.25,
|
| 366 |
+
"learning_rate": 5.862583804015953e-05,
|
| 367 |
+
"loss": 0.5418,
|
| 368 |
+
"step": 210
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.1269185360094451,
|
| 372 |
+
"grad_norm": 27.375,
|
| 373 |
+
"learning_rate": 5.853877332468404e-05,
|
| 374 |
+
"loss": 0.6755,
|
| 375 |
+
"step": 215
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.12987012987012986,
|
| 379 |
+
"grad_norm": 29.5,
|
| 380 |
+
"learning_rate": 5.844910324690187e-05,
|
| 381 |
+
"loss": 0.6172,
|
| 382 |
+
"step": 220
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.13282172373081463,
|
| 386 |
+
"grad_norm": 25.375,
|
| 387 |
+
"learning_rate": 5.835683599297568e-05,
|
| 388 |
+
"loss": 0.5844,
|
| 389 |
+
"step": 225
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.13282172373081463,
|
| 393 |
+
"eval_loss": 0.5579066276550293,
|
| 394 |
+
"eval_runtime": 22.0218,
|
| 395 |
+
"eval_samples_per_second": 90.819,
|
| 396 |
+
"eval_steps_per_second": 90.819,
|
| 397 |
+
"step": 225
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.1357733175914994,
|
| 401 |
+
"grad_norm": 16.5,
|
| 402 |
+
"learning_rate": 5.8261979986169596e-05,
|
| 403 |
+
"loss": 0.6147,
|
| 404 |
+
"step": 230
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.13872491145218419,
|
| 408 |
+
"grad_norm": 10.6875,
|
| 409 |
+
"learning_rate": 5.816454388608023e-05,
|
| 410 |
+
"loss": 0.6352,
|
| 411 |
+
"step": 235
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.14167650531286896,
|
| 415 |
+
"grad_norm": 16.125,
|
| 416 |
+
"learning_rate": 5.8064536587846115e-05,
|
| 417 |
+
"loss": 0.7107,
|
| 418 |
+
"step": 240
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.1446280991735537,
|
| 422 |
+
"grad_norm": 23.5,
|
| 423 |
+
"learning_rate": 5.7961967221335674e-05,
|
| 424 |
+
"loss": 0.6752,
|
| 425 |
+
"step": 245
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.14757969303423848,
|
| 429 |
+
"grad_norm": 27.625,
|
| 430 |
+
"learning_rate": 5.7856845150313716e-05,
|
| 431 |
+
"loss": 0.6039,
|
| 432 |
+
"step": 250
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.14757969303423848,
|
| 436 |
+
"eval_loss": 0.5708025693893433,
|
| 437 |
+
"eval_runtime": 22.0736,
|
| 438 |
+
"eval_samples_per_second": 90.606,
|
| 439 |
+
"eval_steps_per_second": 90.606,
|
| 440 |
+
"step": 250
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 0.15053128689492326,
|
| 444 |
+
"grad_norm": 19.375,
|
| 445 |
+
"learning_rate": 5.7749179971586596e-05,
|
| 446 |
+
"loss": 0.6029,
|
| 447 |
+
"step": 255
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.15348288075560804,
|
| 451 |
+
"grad_norm": 24.75,
|
| 452 |
+
"learning_rate": 5.763898151412613e-05,
|
| 453 |
+
"loss": 0.4986,
|
| 454 |
+
"step": 260
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 0.15643447461629278,
|
| 458 |
+
"grad_norm": 36.0,
|
| 459 |
+
"learning_rate": 5.752625983817225e-05,
|
| 460 |
+
"loss": 0.6049,
|
| 461 |
+
"step": 265
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 0.15938606847697756,
|
| 465 |
+
"grad_norm": 22.25,
|
| 466 |
+
"learning_rate": 5.7411025234314634e-05,
|
| 467 |
+
"loss": 0.5895,
|
| 468 |
+
"step": 270
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 0.16233766233766234,
|
| 472 |
+
"grad_norm": 13.0,
|
| 473 |
+
"learning_rate": 5.729328822255319e-05,
|
| 474 |
+
"loss": 0.6957,
|
| 475 |
+
"step": 275
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 0.16233766233766234,
|
| 479 |
+
"eval_loss": 0.5568270087242126,
|
| 480 |
+
"eval_runtime": 22.052,
|
| 481 |
+
"eval_samples_per_second": 90.695,
|
| 482 |
+
"eval_steps_per_second": 90.695,
|
| 483 |
+
"step": 275
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.1652892561983471,
|
| 487 |
+
"grad_norm": 27.75,
|
| 488 |
+
"learning_rate": 5.717305955133773e-05,
|
| 489 |
+
"loss": 0.7125,
|
| 490 |
+
"step": 280
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.1682408500590319,
|
| 494 |
+
"grad_norm": 12.8125,
|
| 495 |
+
"learning_rate": 5.7050350196586686e-05,
|
| 496 |
+
"loss": 0.5977,
|
| 497 |
+
"step": 285
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 0.17119244391971664,
|
| 501 |
+
"grad_norm": 18.75,
|
| 502 |
+
"learning_rate": 5.692517136068511e-05,
|
| 503 |
+
"loss": 0.5908,
|
| 504 |
+
"step": 290
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.1741440377804014,
|
| 508 |
+
"grad_norm": 24.25,
|
| 509 |
+
"learning_rate": 5.679753447146195e-05,
|
| 510 |
+
"loss": 0.5334,
|
| 511 |
+
"step": 295
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 0.1770956316410862,
|
| 515 |
+
"grad_norm": 11.625,
|
| 516 |
+
"learning_rate": 5.666745118114688e-05,
|
| 517 |
+
"loss": 0.4347,
|
| 518 |
+
"step": 300
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.1770956316410862,
|
| 522 |
+
"eval_loss": 0.5026609301567078,
|
| 523 |
+
"eval_runtime": 22.0534,
|
| 524 |
+
"eval_samples_per_second": 90.689,
|
| 525 |
+
"eval_steps_per_second": 90.689,
|
| 526 |
+
"step": 300
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.18004722550177096,
|
| 530 |
+
"grad_norm": 24.75,
|
| 531 |
+
"learning_rate": 5.6534933365306394e-05,
|
| 532 |
+
"loss": 0.5473,
|
| 533 |
+
"step": 305
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 0.18299881936245574,
|
| 537 |
+
"grad_norm": 27.75,
|
| 538 |
+
"learning_rate": 5.6399993121759797e-05,
|
| 539 |
+
"loss": 0.5315,
|
| 540 |
+
"step": 310
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 0.1859504132231405,
|
| 544 |
+
"grad_norm": 11.3125,
|
| 545 |
+
"learning_rate": 5.626264276947469e-05,
|
| 546 |
+
"loss": 0.4026,
|
| 547 |
+
"step": 315
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 0.18890200708382526,
|
| 551 |
+
"grad_norm": 27.125,
|
| 552 |
+
"learning_rate": 5.612289484744238e-05,
|
| 553 |
+
"loss": 0.55,
|
| 554 |
+
"step": 320
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.19185360094451004,
|
| 558 |
+
"grad_norm": 29.375,
|
| 559 |
+
"learning_rate": 5.5980762113533166e-05,
|
| 560 |
+
"loss": 0.5988,
|
| 561 |
+
"step": 325
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.19185360094451004,
|
| 565 |
+
"eval_loss": 0.5229803919792175,
|
| 566 |
+
"eval_runtime": 22.0483,
|
| 567 |
+
"eval_samples_per_second": 90.71,
|
| 568 |
+
"eval_steps_per_second": 90.71,
|
| 569 |
+
"step": 325
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.19480519480519481,
|
| 573 |
+
"grad_norm": 18.0,
|
| 574 |
+
"learning_rate": 5.5836257543331644e-05,
|
| 575 |
+
"loss": 0.5174,
|
| 576 |
+
"step": 330
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.19775678866587956,
|
| 580 |
+
"grad_norm": 17.75,
|
| 581 |
+
"learning_rate": 5.568939432895213e-05,
|
| 582 |
+
"loss": 0.6662,
|
| 583 |
+
"step": 335
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.20070838252656434,
|
| 587 |
+
"grad_norm": 13.4375,
|
| 588 |
+
"learning_rate": 5.554018587783435e-05,
|
| 589 |
+
"loss": 0.6594,
|
| 590 |
+
"step": 340
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.20365997638724911,
|
| 594 |
+
"grad_norm": 20.125,
|
| 595 |
+
"learning_rate": 5.538864581151943e-05,
|
| 596 |
+
"loss": 0.5776,
|
| 597 |
+
"step": 345
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.2066115702479339,
|
| 601 |
+
"grad_norm": 29.0,
|
| 602 |
+
"learning_rate": 5.523478796440633e-05,
|
| 603 |
+
"loss": 0.6647,
|
| 604 |
+
"step": 350
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.2066115702479339,
|
| 608 |
+
"eval_loss": 0.5277854204177856,
|
| 609 |
+
"eval_runtime": 22.0408,
|
| 610 |
+
"eval_samples_per_second": 90.741,
|
| 611 |
+
"eval_steps_per_second": 90.741,
|
| 612 |
+
"step": 350
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.20956316410861867,
|
| 616 |
+
"grad_norm": 17.625,
|
| 617 |
+
"learning_rate": 5.507862638248896e-05,
|
| 618 |
+
"loss": 0.5446,
|
| 619 |
+
"step": 355
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.21251475796930341,
|
| 623 |
+
"grad_norm": 15.9375,
|
| 624 |
+
"learning_rate": 5.49201753220738e-05,
|
| 625 |
+
"loss": 0.5346,
|
| 626 |
+
"step": 360
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.2154663518299882,
|
| 630 |
+
"grad_norm": 13.8125,
|
| 631 |
+
"learning_rate": 5.475944924847845e-05,
|
| 632 |
+
"loss": 0.4782,
|
| 633 |
+
"step": 365
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.21841794569067297,
|
| 637 |
+
"grad_norm": 46.0,
|
| 638 |
+
"learning_rate": 5.459646283471106e-05,
|
| 639 |
+
"loss": 0.6363,
|
| 640 |
+
"step": 370
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.22136953955135774,
|
| 644 |
+
"grad_norm": 12.625,
|
| 645 |
+
"learning_rate": 5.443123096013083e-05,
|
| 646 |
+
"loss": 0.5603,
|
| 647 |
+
"step": 375
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.22136953955135774,
|
| 651 |
+
"eval_loss": 0.49818602204322815,
|
| 652 |
+
"eval_runtime": 22.0724,
|
| 653 |
+
"eval_samples_per_second": 90.611,
|
| 654 |
+
"eval_steps_per_second": 90.611,
|
| 655 |
+
"step": 375
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.2243211334120425,
|
| 659 |
+
"grad_norm": 25.125,
|
| 660 |
+
"learning_rate": 5.426376870908959e-05,
|
| 661 |
+
"loss": 0.6536,
|
| 662 |
+
"step": 380
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.22727272727272727,
|
| 666 |
+
"grad_norm": 17.25,
|
| 667 |
+
"learning_rate": 5.409409136955476e-05,
|
| 668 |
+
"loss": 0.5464,
|
| 669 |
+
"step": 385
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.23022432113341204,
|
| 673 |
+
"grad_norm": 23.375,
|
| 674 |
+
"learning_rate": 5.3922214431713654e-05,
|
| 675 |
+
"loss": 0.5587,
|
| 676 |
+
"step": 390
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.23317591499409682,
|
| 680 |
+
"grad_norm": 10.75,
|
| 681 |
+
"learning_rate": 5.3748153586559385e-05,
|
| 682 |
+
"loss": 0.5231,
|
| 683 |
+
"step": 395
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.2361275088547816,
|
| 687 |
+
"grad_norm": 19.875,
|
| 688 |
+
"learning_rate": 5.357192472445835e-05,
|
| 689 |
+
"loss": 0.503,
|
| 690 |
+
"step": 400
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.2361275088547816,
|
| 694 |
+
"eval_loss": 0.4984550178050995,
|
| 695 |
+
"eval_runtime": 22.074,
|
| 696 |
+
"eval_samples_per_second": 90.604,
|
| 697 |
+
"eval_steps_per_second": 90.604,
|
| 698 |
+
"step": 400
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.23907910271546634,
|
| 702 |
+
"grad_norm": 20.125,
|
| 703 |
+
"learning_rate": 5.339354393369962e-05,
|
| 704 |
+
"loss": 0.4524,
|
| 705 |
+
"step": 405
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.24203069657615112,
|
| 709 |
+
"grad_norm": 11.375,
|
| 710 |
+
"learning_rate": 5.321302749902615e-05,
|
| 711 |
+
"loss": 0.492,
|
| 712 |
+
"step": 410
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 0.2449822904368359,
|
| 716 |
+
"grad_norm": 20.75,
|
| 717 |
+
"learning_rate": 5.303039190014818e-05,
|
| 718 |
+
"loss": 0.4989,
|
| 719 |
+
"step": 415
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.24793388429752067,
|
| 723 |
+
"grad_norm": 14.0,
|
| 724 |
+
"learning_rate": 5.284565381023873e-05,
|
| 725 |
+
"loss": 0.6195,
|
| 726 |
+
"step": 420
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 0.25088547815820544,
|
| 730 |
+
"grad_norm": 25.125,
|
| 731 |
+
"learning_rate": 5.265883009441147e-05,
|
| 732 |
+
"loss": 0.5687,
|
| 733 |
+
"step": 425
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.25088547815820544,
|
| 737 |
+
"eval_loss": 0.4847257137298584,
|
| 738 |
+
"eval_runtime": 22.029,
|
| 739 |
+
"eval_samples_per_second": 90.789,
|
| 740 |
+
"eval_steps_per_second": 90.789,
|
| 741 |
+
"step": 425
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.2538370720188902,
|
| 745 |
+
"grad_norm": 16.75,
|
| 746 |
+
"learning_rate": 5.2469937808181055e-05,
|
| 747 |
+
"loss": 0.4048,
|
| 748 |
+
"step": 430
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 0.256788665879575,
|
| 752 |
+
"grad_norm": 39.75,
|
| 753 |
+
"learning_rate": 5.227899419590614e-05,
|
| 754 |
+
"loss": 0.5483,
|
| 755 |
+
"step": 435
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 0.2597402597402597,
|
| 759 |
+
"grad_norm": 15.125,
|
| 760 |
+
"learning_rate": 5.208601668921508e-05,
|
| 761 |
+
"loss": 0.4843,
|
| 762 |
+
"step": 440
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.2626918536009445,
|
| 766 |
+
"grad_norm": 15.5,
|
| 767 |
+
"learning_rate": 5.1891022905414546e-05,
|
| 768 |
+
"loss": 0.6146,
|
| 769 |
+
"step": 445
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 0.26564344746162927,
|
| 773 |
+
"grad_norm": 22.875,
|
| 774 |
+
"learning_rate": 5.169403064588125e-05,
|
| 775 |
+
"loss": 0.4279,
|
| 776 |
+
"step": 450
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 0.26564344746162927,
|
| 780 |
+
"eval_loss": 0.48101305961608887,
|
| 781 |
+
"eval_runtime": 22.0566,
|
| 782 |
+
"eval_samples_per_second": 90.676,
|
| 783 |
+
"eval_steps_per_second": 90.676,
|
| 784 |
+
"step": 450
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 0.26859504132231404,
|
| 788 |
+
"grad_norm": 28.625,
|
| 789 |
+
"learning_rate": 5.1495057894436757e-05,
|
| 790 |
+
"loss": 0.5749,
|
| 791 |
+
"step": 455
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 0.2715466351829988,
|
| 795 |
+
"grad_norm": 20.5,
|
| 796 |
+
"learning_rate": 5.1294122815705773e-05,
|
| 797 |
+
"loss": 0.4963,
|
| 798 |
+
"step": 460
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 0.2744982290436836,
|
| 802 |
+
"grad_norm": 22.25,
|
| 803 |
+
"learning_rate": 5.109124375345781e-05,
|
| 804 |
+
"loss": 0.4213,
|
| 805 |
+
"step": 465
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 0.27744982290436837,
|
| 809 |
+
"grad_norm": 18.125,
|
| 810 |
+
"learning_rate": 5.0886439228932576e-05,
|
| 811 |
+
"loss": 0.5002,
|
| 812 |
+
"step": 470
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.28040141676505315,
|
| 816 |
+
"grad_norm": 34.0,
|
| 817 |
+
"learning_rate": 5.067972793914911e-05,
|
| 818 |
+
"loss": 0.5136,
|
| 819 |
+
"step": 475
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.28040141676505315,
|
| 823 |
+
"eval_loss": 0.5137303471565247,
|
| 824 |
+
"eval_runtime": 22.0698,
|
| 825 |
+
"eval_samples_per_second": 90.621,
|
| 826 |
+
"eval_steps_per_second": 90.621,
|
| 827 |
+
"step": 475
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 0.2833530106257379,
|
| 831 |
+
"grad_norm": 15.0,
|
| 832 |
+
"learning_rate": 5.047112875519892e-05,
|
| 833 |
+
"loss": 0.5162,
|
| 834 |
+
"step": 480
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 0.28630460448642264,
|
| 838 |
+
"grad_norm": 38.0,
|
| 839 |
+
"learning_rate": 5.02606607205232e-05,
|
| 840 |
+
"loss": 0.4831,
|
| 841 |
+
"step": 485
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.2892561983471074,
|
| 845 |
+
"grad_norm": 26.5,
|
| 846 |
+
"learning_rate": 5.004834304917425e-05,
|
| 847 |
+
"loss": 0.5147,
|
| 848 |
+
"step": 490
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 0.2922077922077922,
|
| 852 |
+
"grad_norm": 37.0,
|
| 853 |
+
"learning_rate": 4.983419512406151e-05,
|
| 854 |
+
"loss": 0.553,
|
| 855 |
+
"step": 495
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.29515938606847697,
|
| 859 |
+
"grad_norm": 23.625,
|
| 860 |
+
"learning_rate": 4.9618236495181936e-05,
|
| 861 |
+
"loss": 0.3999,
|
| 862 |
+
"step": 500
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 0.29515938606847697,
|
| 866 |
+
"eval_loss": 0.5061969757080078,
|
| 867 |
+
"eval_runtime": 22.0382,
|
| 868 |
+
"eval_samples_per_second": 90.752,
|
| 869 |
+
"eval_steps_per_second": 90.752,
|
| 870 |
+
"step": 500
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.29811097992916175,
|
| 874 |
+
"grad_norm": 13.75,
|
| 875 |
+
"learning_rate": 4.9400486877835325e-05,
|
| 876 |
+
"loss": 0.4205,
|
| 877 |
+
"step": 505
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.3010625737898465,
|
| 881 |
+
"grad_norm": 22.5,
|
| 882 |
+
"learning_rate": 4.91809661508244e-05,
|
| 883 |
+
"loss": 0.5904,
|
| 884 |
+
"step": 510
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.3040141676505313,
|
| 888 |
+
"grad_norm": 16.75,
|
| 889 |
+
"learning_rate": 4.895969435464009e-05,
|
| 890 |
+
"loss": 0.5749,
|
| 891 |
+
"step": 515
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.3069657615112161,
|
| 895 |
+
"grad_norm": 10.8125,
|
| 896 |
+
"learning_rate": 4.873669168963196e-05,
|
| 897 |
+
"loss": 0.5841,
|
| 898 |
+
"step": 520
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.30991735537190085,
|
| 902 |
+
"grad_norm": 14.25,
|
| 903 |
+
"learning_rate": 4.851197851416409e-05,
|
| 904 |
+
"loss": 0.5454,
|
| 905 |
+
"step": 525
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.30991735537190085,
|
| 909 |
+
"eval_loss": 0.6045746207237244,
|
| 910 |
+
"eval_runtime": 22.0653,
|
| 911 |
+
"eval_samples_per_second": 90.64,
|
| 912 |
+
"eval_steps_per_second": 90.64,
|
| 913 |
+
"step": 525
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.31286894923258557,
|
| 917 |
+
"grad_norm": 12.4375,
|
| 918 |
+
"learning_rate": 4.828557534275651e-05,
|
| 919 |
+
"loss": 0.4654,
|
| 920 |
+
"step": 530
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.31582054309327035,
|
| 924 |
+
"grad_norm": 28.125,
|
| 925 |
+
"learning_rate": 4.8057502844212406e-05,
|
| 926 |
+
"loss": 0.5669,
|
| 927 |
+
"step": 535
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.3187721369539551,
|
| 931 |
+
"grad_norm": 17.625,
|
| 932 |
+
"learning_rate": 4.78277818397312e-05,
|
| 933 |
+
"loss": 0.3907,
|
| 934 |
+
"step": 540
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.3217237308146399,
|
| 938 |
+
"grad_norm": 12.625,
|
| 939 |
+
"learning_rate": 4.7596433301007775e-05,
|
| 940 |
+
"loss": 0.508,
|
| 941 |
+
"step": 545
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.3246753246753247,
|
| 945 |
+
"grad_norm": 26.75,
|
| 946 |
+
"learning_rate": 4.736347834831789e-05,
|
| 947 |
+
"loss": 0.408,
|
| 948 |
+
"step": 550
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.3246753246753247,
|
| 952 |
+
"eval_loss": 0.48477041721343994,
|
| 953 |
+
"eval_runtime": 22.0413,
|
| 954 |
+
"eval_samples_per_second": 90.739,
|
| 955 |
+
"eval_steps_per_second": 90.739,
|
| 956 |
+
"step": 550
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 0.32762691853600945,
|
| 960 |
+
"grad_norm": 32.25,
|
| 961 |
+
"learning_rate": 4.712893824859008e-05,
|
| 962 |
+
"loss": 0.3498,
|
| 963 |
+
"step": 555
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.3305785123966942,
|
| 967 |
+
"grad_norm": 21.25,
|
| 968 |
+
"learning_rate": 4.6892834413464163e-05,
|
| 969 |
+
"loss": 0.6738,
|
| 970 |
+
"step": 560
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 0.333530106257379,
|
| 974 |
+
"grad_norm": 23.0,
|
| 975 |
+
"learning_rate": 4.6655188397336515e-05,
|
| 976 |
+
"loss": 0.4393,
|
| 977 |
+
"step": 565
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 0.3364817001180638,
|
| 981 |
+
"grad_norm": 13.625,
|
| 982 |
+
"learning_rate": 4.641602189539235e-05,
|
| 983 |
+
"loss": 0.5021,
|
| 984 |
+
"step": 570
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 0.33943329397874855,
|
| 988 |
+
"grad_norm": 16.5,
|
| 989 |
+
"learning_rate": 4.617535674162509e-05,
|
| 990 |
+
"loss": 0.5409,
|
| 991 |
+
"step": 575
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 0.33943329397874855,
|
| 995 |
+
"eval_loss": 0.4802681505680084,
|
| 996 |
+
"eval_runtime": 22.041,
|
| 997 |
+
"eval_samples_per_second": 90.74,
|
| 998 |
+
"eval_steps_per_second": 90.74,
|
| 999 |
+
"step": 575
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.34238488783943327,
|
| 1003 |
+
"grad_norm": 18.0,
|
| 1004 |
+
"learning_rate": 4.59332149068431e-05,
|
| 1005 |
+
"loss": 0.4619,
|
| 1006 |
+
"step": 580
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.34533648170011805,
|
| 1010 |
+
"grad_norm": 19.25,
|
| 1011 |
+
"learning_rate": 4.5689618496664e-05,
|
| 1012 |
+
"loss": 0.5019,
|
| 1013 |
+
"step": 585
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.3482880755608028,
|
| 1017 |
+
"grad_norm": 17.25,
|
| 1018 |
+
"learning_rate": 4.544458974949646e-05,
|
| 1019 |
+
"loss": 0.3654,
|
| 1020 |
+
"step": 590
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.3512396694214876,
|
| 1024 |
+
"grad_norm": 25.625,
|
| 1025 |
+
"learning_rate": 4.519815103451012e-05,
|
| 1026 |
+
"loss": 0.6236,
|
| 1027 |
+
"step": 595
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.3541912632821724,
|
| 1031 |
+
"grad_norm": 30.125,
|
| 1032 |
+
"learning_rate": 4.4950324849593455e-05,
|
| 1033 |
+
"loss": 0.4846,
|
| 1034 |
+
"step": 600
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.3541912632821724,
|
| 1038 |
+
"eval_loss": 0.47454240918159485,
|
| 1039 |
+
"eval_runtime": 22.0763,
|
| 1040 |
+
"eval_samples_per_second": 90.595,
|
| 1041 |
+
"eval_steps_per_second": 90.595,
|
| 1042 |
+
"step": 600
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 0.35714285714285715,
|
| 1046 |
+
"grad_norm": 17.75,
|
| 1047 |
+
"learning_rate": 4.470113381929984e-05,
|
| 1048 |
+
"loss": 0.5738,
|
| 1049 |
+
"step": 605
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 0.3600944510035419,
|
| 1053 |
+
"grad_norm": 16.0,
|
| 1054 |
+
"learning_rate": 4.445060069278218e-05,
|
| 1055 |
+
"loss": 0.3647,
|
| 1056 |
+
"step": 610
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 0.3630460448642267,
|
| 1060 |
+
"grad_norm": 12.3125,
|
| 1061 |
+
"learning_rate": 4.419874834171601e-05,
|
| 1062 |
+
"loss": 0.4772,
|
| 1063 |
+
"step": 615
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 0.3659976387249115,
|
| 1067 |
+
"grad_norm": 12.4375,
|
| 1068 |
+
"learning_rate": 4.3945599758211594e-05,
|
| 1069 |
+
"loss": 0.4309,
|
| 1070 |
+
"step": 620
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 0.3689492325855962,
|
| 1074 |
+
"grad_norm": 15.4375,
|
| 1075 |
+
"learning_rate": 4.369117805271482e-05,
|
| 1076 |
+
"loss": 0.3699,
|
| 1077 |
+
"step": 625
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 0.3689492325855962,
|
| 1081 |
+
"eval_loss": 0.5046902298927307,
|
| 1082 |
+
"eval_runtime": 22.0518,
|
| 1083 |
+
"eval_samples_per_second": 90.696,
|
| 1084 |
+
"eval_steps_per_second": 90.696,
|
| 1085 |
+
"step": 625
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 0.371900826446281,
|
| 1089 |
+
"grad_norm": 26.5,
|
| 1090 |
+
"learning_rate": 4.343550645189751e-05,
|
| 1091 |
+
"loss": 0.4449,
|
| 1092 |
+
"step": 630
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 0.37485242030696575,
|
| 1096 |
+
"grad_norm": 21.125,
|
| 1097 |
+
"learning_rate": 4.317860829653692e-05,
|
| 1098 |
+
"loss": 0.2902,
|
| 1099 |
+
"step": 635
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 0.3778040141676505,
|
| 1103 |
+
"grad_norm": 28.875,
|
| 1104 |
+
"learning_rate": 4.292050703938496e-05,
|
| 1105 |
+
"loss": 0.5582,
|
| 1106 |
+
"step": 640
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 0.3807556080283353,
|
| 1110 |
+
"grad_norm": 13.75,
|
| 1111 |
+
"learning_rate": 4.266122624302714e-05,
|
| 1112 |
+
"loss": 0.5335,
|
| 1113 |
+
"step": 645
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 0.3837072018890201,
|
| 1117 |
+
"grad_norm": 13.5,
|
| 1118 |
+
"learning_rate": 4.2400789577731485e-05,
|
| 1119 |
+
"loss": 0.3741,
|
| 1120 |
+
"step": 650
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 0.3837072018890201,
|
| 1124 |
+
"eval_loss": 0.4519728720188141,
|
| 1125 |
+
"eval_runtime": 22.0605,
|
| 1126 |
+
"eval_samples_per_second": 90.66,
|
| 1127 |
+
"eval_steps_per_second": 90.66,
|
| 1128 |
+
"step": 650
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 0.38665879574970485,
|
| 1132 |
+
"grad_norm": 19.5,
|
| 1133 |
+
"learning_rate": 4.213922081928763e-05,
|
| 1134 |
+
"loss": 0.5017,
|
| 1135 |
+
"step": 655
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 0.38961038961038963,
|
| 1139 |
+
"grad_norm": 13.4375,
|
| 1140 |
+
"learning_rate": 4.187654384683628e-05,
|
| 1141 |
+
"loss": 0.359,
|
| 1142 |
+
"step": 660
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 0.3925619834710744,
|
| 1146 |
+
"grad_norm": 11.1875,
|
| 1147 |
+
"learning_rate": 4.161278264068925e-05,
|
| 1148 |
+
"loss": 0.2609,
|
| 1149 |
+
"step": 665
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 0.3955135773317591,
|
| 1153 |
+
"grad_norm": 13.0625,
|
| 1154 |
+
"learning_rate": 4.134796128014022e-05,
|
| 1155 |
+
"loss": 0.4038,
|
| 1156 |
+
"step": 670
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 0.3984651711924439,
|
| 1160 |
+
"grad_norm": 17.625,
|
| 1161 |
+
"learning_rate": 4.108210394126652e-05,
|
| 1162 |
+
"loss": 0.3166,
|
| 1163 |
+
"step": 675
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 0.3984651711924439,
|
| 1167 |
+
"eval_loss": 0.44906917214393616,
|
| 1168 |
+
"eval_runtime": 22.0309,
|
| 1169 |
+
"eval_samples_per_second": 90.782,
|
| 1170 |
+
"eval_steps_per_second": 90.782,
|
| 1171 |
+
"step": 675
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.4014167650531287,
|
| 1175 |
+
"grad_norm": 32.25,
|
| 1176 |
+
"learning_rate": 4.0815234894722035e-05,
|
| 1177 |
+
"loss": 0.3372,
|
| 1178 |
+
"step": 680
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.40436835891381345,
|
| 1182 |
+
"grad_norm": 27.25,
|
| 1183 |
+
"learning_rate": 4.05473785035215e-05,
|
| 1184 |
+
"loss": 0.3346,
|
| 1185 |
+
"step": 685
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.40731995277449823,
|
| 1189 |
+
"grad_norm": 24.75,
|
| 1190 |
+
"learning_rate": 4.0278559220816304e-05,
|
| 1191 |
+
"loss": 0.3993,
|
| 1192 |
+
"step": 690
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.410271546635183,
|
| 1196 |
+
"grad_norm": 20.0,
|
| 1197 |
+
"learning_rate": 4.0008801587662194e-05,
|
| 1198 |
+
"loss": 0.34,
|
| 1199 |
+
"step": 695
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.4132231404958678,
|
| 1203 |
+
"grad_norm": 27.25,
|
| 1204 |
+
"learning_rate": 3.9738130230778796e-05,
|
| 1205 |
+
"loss": 0.4442,
|
| 1206 |
+
"step": 700
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.4132231404958678,
|
| 1210 |
+
"eval_loss": 0.4622591435909271,
|
| 1211 |
+
"eval_runtime": 22.0728,
|
| 1212 |
+
"eval_samples_per_second": 90.609,
|
| 1213 |
+
"eval_steps_per_second": 90.609,
|
| 1214 |
+
"step": 700
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.41617473435655256,
|
| 1218 |
+
"grad_norm": 22.625,
|
| 1219 |
+
"learning_rate": 3.946656986030142e-05,
|
| 1220 |
+
"loss": 0.3391,
|
| 1221 |
+
"step": 705
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.41912632821723733,
|
| 1225 |
+
"grad_norm": 26.125,
|
| 1226 |
+
"learning_rate": 3.919414526752524e-05,
|
| 1227 |
+
"loss": 0.333,
|
| 1228 |
+
"step": 710
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.42207792207792205,
|
| 1232 |
+
"grad_norm": 7.5,
|
| 1233 |
+
"learning_rate": 3.8920881322642036e-05,
|
| 1234 |
+
"loss": 0.3791,
|
| 1235 |
+
"step": 715
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.42502951593860683,
|
| 1239 |
+
"grad_norm": 32.0,
|
| 1240 |
+
"learning_rate": 3.864680297246972e-05,
|
| 1241 |
+
"loss": 0.5102,
|
| 1242 |
+
"step": 720
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.4279811097992916,
|
| 1246 |
+
"grad_norm": 15.5,
|
| 1247 |
+
"learning_rate": 3.8371935238174924e-05,
|
| 1248 |
+
"loss": 0.4723,
|
| 1249 |
+
"step": 725
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.4279811097992916,
|
| 1253 |
+
"eval_loss": 0.44943633675575256,
|
| 1254 |
+
"eval_runtime": 22.0672,
|
| 1255 |
+
"eval_samples_per_second": 90.632,
|
| 1256 |
+
"eval_steps_per_second": 90.632,
|
| 1257 |
+
"step": 725
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 0.4309327036599764,
|
| 1261 |
+
"grad_norm": 26.875,
|
| 1262 |
+
"learning_rate": 3.809630321298872e-05,
|
| 1263 |
+
"loss": 0.4499,
|
| 1264 |
+
"step": 730
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 0.43388429752066116,
|
| 1268 |
+
"grad_norm": 14.3125,
|
| 1269 |
+
"learning_rate": 3.78199320599159e-05,
|
| 1270 |
+
"loss": 0.2574,
|
| 1271 |
+
"step": 735
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 0.43683589138134593,
|
| 1275 |
+
"grad_norm": 10.0625,
|
| 1276 |
+
"learning_rate": 3.754284700943767e-05,
|
| 1277 |
+
"loss": 0.3981,
|
| 1278 |
+
"step": 740
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 0.4397874852420307,
|
| 1282 |
+
"grad_norm": 20.5,
|
| 1283 |
+
"learning_rate": 3.726507335720842e-05,
|
| 1284 |
+
"loss": 0.3897,
|
| 1285 |
+
"step": 745
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 0.4427390791027155,
|
| 1289 |
+
"grad_norm": 12.4375,
|
| 1290 |
+
"learning_rate": 3.6986636461746365e-05,
|
| 1291 |
+
"loss": 0.3282,
|
| 1292 |
+
"step": 750
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 0.4427390791027155,
|
| 1296 |
+
"eval_loss": 0.46209147572517395,
|
| 1297 |
+
"eval_runtime": 22.0979,
|
| 1298 |
+
"eval_samples_per_second": 90.506,
|
| 1299 |
+
"eval_steps_per_second": 90.506,
|
| 1300 |
+
"step": 750
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 0.44569067296340026,
|
| 1304 |
+
"grad_norm": 17.0,
|
| 1305 |
+
"learning_rate": 3.6707561742118546e-05,
|
| 1306 |
+
"loss": 0.3905,
|
| 1307 |
+
"step": 755
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 0.448642266824085,
|
| 1311 |
+
"grad_norm": 16.875,
|
| 1312 |
+
"learning_rate": 3.642787467562024e-05,
|
| 1313 |
+
"loss": 0.2688,
|
| 1314 |
+
"step": 760
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 0.45159386068476975,
|
| 1318 |
+
"grad_norm": 17.625,
|
| 1319 |
+
"learning_rate": 3.614760079544913e-05,
|
| 1320 |
+
"loss": 0.369,
|
| 1321 |
+
"step": 765
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 0.45454545454545453,
|
| 1325 |
+
"grad_norm": 24.0,
|
| 1326 |
+
"learning_rate": 3.5866765688374296e-05,
|
| 1327 |
+
"loss": 0.4732,
|
| 1328 |
+
"step": 770
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 0.4574970484061393,
|
| 1332 |
+
"grad_norm": 16.375,
|
| 1333 |
+
"learning_rate": 3.558539499240037e-05,
|
| 1334 |
+
"loss": 0.3928,
|
| 1335 |
+
"step": 775
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 0.4574970484061393,
|
| 1339 |
+
"eval_loss": 0.4500948488712311,
|
| 1340 |
+
"eval_runtime": 22.071,
|
| 1341 |
+
"eval_samples_per_second": 90.617,
|
| 1342 |
+
"eval_steps_per_second": 90.617,
|
| 1343 |
+
"step": 775
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.4604486422668241,
|
| 1347 |
+
"grad_norm": 11.375,
|
| 1348 |
+
"learning_rate": 3.530351439442696e-05,
|
| 1349 |
+
"loss": 0.498,
|
| 1350 |
+
"step": 780
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.46340023612750886,
|
| 1354 |
+
"grad_norm": 9.125,
|
| 1355 |
+
"learning_rate": 3.502114962790366e-05,
|
| 1356 |
+
"loss": 0.3545,
|
| 1357 |
+
"step": 785
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.46635182998819363,
|
| 1361 |
+
"grad_norm": 12.375,
|
| 1362 |
+
"learning_rate": 3.473832647048079e-05,
|
| 1363 |
+
"loss": 0.5654,
|
| 1364 |
+
"step": 790
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.4693034238488784,
|
| 1368 |
+
"grad_norm": 10.9375,
|
| 1369 |
+
"learning_rate": 3.445507074165612e-05,
|
| 1370 |
+
"loss": 0.3995,
|
| 1371 |
+
"step": 795
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.4722550177095632,
|
| 1375 |
+
"grad_norm": 8.375,
|
| 1376 |
+
"learning_rate": 3.41714083004177e-05,
|
| 1377 |
+
"loss": 0.4174,
|
| 1378 |
+
"step": 800
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.4722550177095632,
|
| 1382 |
+
"eval_loss": 0.4428013265132904,
|
| 1383 |
+
"eval_runtime": 22.0412,
|
| 1384 |
+
"eval_samples_per_second": 90.739,
|
| 1385 |
+
"eval_steps_per_second": 90.739,
|
| 1386 |
+
"step": 800
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 0.47520661157024796,
|
| 1390 |
+
"grad_norm": 14.3125,
|
| 1391 |
+
"learning_rate": 3.3887365042883226e-05,
|
| 1392 |
+
"loss": 0.487,
|
| 1393 |
+
"step": 805
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"epoch": 0.4781582054309327,
|
| 1397 |
+
"grad_norm": 12.4375,
|
| 1398 |
+
"learning_rate": 3.360296689993586e-05,
|
| 1399 |
+
"loss": 0.367,
|
| 1400 |
+
"step": 810
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 0.48110979929161746,
|
| 1404 |
+
"grad_norm": 10.375,
|
| 1405 |
+
"learning_rate": 3.331823983485695e-05,
|
| 1406 |
+
"loss": 0.2972,
|
| 1407 |
+
"step": 815
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 0.48406139315230223,
|
| 1411 |
+
"grad_norm": 14.0,
|
| 1412 |
+
"learning_rate": 3.303320984095584e-05,
|
| 1413 |
+
"loss": 0.417,
|
| 1414 |
+
"step": 820
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"epoch": 0.487012987012987,
|
| 1418 |
+
"grad_norm": 25.0,
|
| 1419 |
+
"learning_rate": 3.274790293919685e-05,
|
| 1420 |
+
"loss": 0.3814,
|
| 1421 |
+
"step": 825
|
| 1422 |
+
},
|
| 1423 |
+
{
|
| 1424 |
+
"epoch": 0.487012987012987,
|
| 1425 |
+
"eval_loss": 0.45124053955078125,
|
| 1426 |
+
"eval_runtime": 22.0625,
|
| 1427 |
+
"eval_samples_per_second": 90.652,
|
| 1428 |
+
"eval_steps_per_second": 90.652,
|
| 1429 |
+
"step": 825
|
| 1430 |
+
},
|
| 1431 |
+
{
|
| 1432 |
+
"epoch": 0.4899645808736718,
|
| 1433 |
+
"grad_norm": 19.125,
|
| 1434 |
+
"learning_rate": 3.246234517582378e-05,
|
| 1435 |
+
"loss": 0.4698,
|
| 1436 |
+
"step": 830
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 0.49291617473435656,
|
| 1440 |
+
"grad_norm": 19.625,
|
| 1441 |
+
"learning_rate": 3.217656261998208e-05,
|
| 1442 |
+
"loss": 0.4826,
|
| 1443 |
+
"step": 835
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 0.49586776859504134,
|
| 1447 |
+
"grad_norm": 9.25,
|
| 1448 |
+
"learning_rate": 3.189058136133898e-05,
|
| 1449 |
+
"loss": 0.4592,
|
| 1450 |
+
"step": 840
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 0.4988193624557261,
|
| 1454 |
+
"grad_norm": 7.40625,
|
| 1455 |
+
"learning_rate": 3.1604427507701675e-05,
|
| 1456 |
+
"loss": 0.551,
|
| 1457 |
+
"step": 845
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 0.5017709563164109,
|
| 1461 |
+
"grad_norm": 22.25,
|
| 1462 |
+
"learning_rate": 3.131812718263392e-05,
|
| 1463 |
+
"loss": 0.3845,
|
| 1464 |
+
"step": 850
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 0.5017709563164109,
|
| 1468 |
+
"eval_loss": 0.42552411556243896,
|
| 1469 |
+
"eval_runtime": 22.0632,
|
| 1470 |
+
"eval_samples_per_second": 90.649,
|
| 1471 |
+
"eval_steps_per_second": 90.649,
|
| 1472 |
+
"step": 850
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.5047225501770957,
|
| 1476 |
+
"grad_norm": 11.875,
|
| 1477 |
+
"learning_rate": 3.1031706523071115e-05,
|
| 1478 |
+
"loss": 0.5727,
|
| 1479 |
+
"step": 855
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.5076741440377804,
|
| 1483 |
+
"grad_norm": 5.21875,
|
| 1484 |
+
"learning_rate": 3.0745191676934285e-05,
|
| 1485 |
+
"loss": 0.4759,
|
| 1486 |
+
"step": 860
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.5106257378984652,
|
| 1490 |
+
"grad_norm": 20.75,
|
| 1491 |
+
"learning_rate": 3.0458608800742883e-05,
|
| 1492 |
+
"loss": 0.4727,
|
| 1493 |
+
"step": 865
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.51357733175915,
|
| 1497 |
+
"grad_norm": 19.125,
|
| 1498 |
+
"learning_rate": 3.0171984057227008e-05,
|
| 1499 |
+
"loss": 0.4733,
|
| 1500 |
+
"step": 870
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.5165289256198347,
|
| 1504 |
+
"grad_norm": 21.125,
|
| 1505 |
+
"learning_rate": 2.988534361293888e-05,
|
| 1506 |
+
"loss": 0.3789,
|
| 1507 |
+
"step": 875
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.5165289256198347,
|
| 1511 |
+
"eval_loss": 0.41610679030418396,
|
| 1512 |
+
"eval_runtime": 22.0756,
|
| 1513 |
+
"eval_samples_per_second": 90.598,
|
| 1514 |
+
"eval_steps_per_second": 90.598,
|
| 1515 |
+
"step": 875
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.5194805194805194,
|
| 1519 |
+
"grad_norm": 10.8125,
|
| 1520 |
+
"learning_rate": 2.959871363586411e-05,
|
| 1521 |
+
"loss": 0.4258,
|
| 1522 |
+
"step": 880
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.5224321133412042,
|
| 1526 |
+
"grad_norm": 9.0625,
|
| 1527 |
+
"learning_rate": 2.9312120293032703e-05,
|
| 1528 |
+
"loss": 0.408,
|
| 1529 |
+
"step": 885
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.525383707201889,
|
| 1533 |
+
"grad_norm": 29.375,
|
| 1534 |
+
"learning_rate": 2.902558974813026e-05,
|
| 1535 |
+
"loss": 0.5145,
|
| 1536 |
+
"step": 890
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.5283353010625738,
|
| 1540 |
+
"grad_norm": 14.9375,
|
| 1541 |
+
"learning_rate": 2.873914815910944e-05,
|
| 1542 |
+
"loss": 0.4281,
|
| 1543 |
+
"step": 895
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.5312868949232585,
|
| 1547 |
+
"grad_norm": 19.125,
|
| 1548 |
+
"learning_rate": 2.8452821675801944e-05,
|
| 1549 |
+
"loss": 0.3189,
|
| 1550 |
+
"step": 900
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.5312868949232585,
|
| 1554 |
+
"eval_loss": 0.41652774810791016,
|
| 1555 |
+
"eval_runtime": 22.0235,
|
| 1556 |
+
"eval_samples_per_second": 90.812,
|
| 1557 |
+
"eval_steps_per_second": 90.812,
|
| 1558 |
+
"step": 900
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 0.5342384887839433,
|
| 1562 |
+
"grad_norm": 19.375,
|
| 1563 |
+
"learning_rate": 2.81666364375312e-05,
|
| 1564 |
+
"loss": 0.4598,
|
| 1565 |
+
"step": 905
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 0.5371900826446281,
|
| 1569 |
+
"grad_norm": 13.4375,
|
| 1570 |
+
"learning_rate": 2.7880618570726142e-05,
|
| 1571 |
+
"loss": 0.4811,
|
| 1572 |
+
"step": 910
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 0.5401416765053129,
|
| 1576 |
+
"grad_norm": 23.0,
|
| 1577 |
+
"learning_rate": 2.7594794186535993e-05,
|
| 1578 |
+
"loss": 0.4931,
|
| 1579 |
+
"step": 915
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 0.5430932703659976,
|
| 1583 |
+
"grad_norm": 24.125,
|
| 1584 |
+
"learning_rate": 2.7309189378446578e-05,
|
| 1585 |
+
"loss": 0.5955,
|
| 1586 |
+
"step": 920
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 0.5460448642266824,
|
| 1590 |
+
"grad_norm": 19.875,
|
| 1591 |
+
"learning_rate": 2.702383021989817e-05,
|
| 1592 |
+
"loss": 0.3743,
|
| 1593 |
+
"step": 925
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 0.5460448642266824,
|
| 1597 |
+
"eval_loss": 0.41767558455467224,
|
| 1598 |
+
"eval_runtime": 22.0719,
|
| 1599 |
+
"eval_samples_per_second": 90.613,
|
| 1600 |
+
"eval_steps_per_second": 90.613,
|
| 1601 |
+
"step": 925
|
| 1602 |
+
}
|
| 1603 |
+
],
|
| 1604 |
+
"logging_steps": 5,
|
| 1605 |
+
"max_steps": 1694,
|
| 1606 |
+
"num_input_tokens_seen": 0,
|
| 1607 |
+
"num_train_epochs": 1,
|
| 1608 |
+
"save_steps": 25,
|
| 1609 |
+
"stateful_callbacks": {
|
| 1610 |
+
"TrainerControl": {
|
| 1611 |
+
"args": {
|
| 1612 |
+
"should_epoch_stop": false,
|
| 1613 |
+
"should_evaluate": false,
|
| 1614 |
+
"should_log": false,
|
| 1615 |
+
"should_save": true,
|
| 1616 |
+
"should_training_stop": false
|
| 1617 |
+
},
|
| 1618 |
+
"attributes": {}
|
| 1619 |
+
}
|
| 1620 |
+
},
|
| 1621 |
+
"total_flos": 1.3649613399392256e+16,
|
| 1622 |
+
"train_batch_size": 1,
|
| 1623 |
+
"trial_name": null,
|
| 1624 |
+
"trial_params": null
|
| 1625 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b9d3fb6a396b6f7fbd066e1f1e57ac46cbb2892debf89344c191c26dfa7a815
|
| 3 |
+
size 5777
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|