Upload folder using huggingface_hub
Browse files- added_tokens.json +24 -0
- chat_template.json +3 -0
- config.json +71 -0
- generation_config.json +12 -0
- merges.txt +0 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +0 -0
- preprocessor_config.json +29 -0
- special_tokens_map.json +31 -0
- tokenizer_config.json +209 -0
- train.log +0 -0
- trainer_state.json +2724 -0
- training_args.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2_5_VLForConditionalGenerationWithVGGT"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"feature_fusion_method": "add",
|
| 9 |
+
"fusion_num_layers": 1,
|
| 10 |
+
"geometry_encoder_type": "vggt",
|
| 11 |
+
"geometry_merger_type": "mlp",
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 3584,
|
| 14 |
+
"image_token_id": 151655,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 18944,
|
| 17 |
+
"max_position_embeddings": 128000,
|
| 18 |
+
"max_window_layers": 28,
|
| 19 |
+
"model_type": "qwen2_5_vl",
|
| 20 |
+
"num_attention_heads": 28,
|
| 21 |
+
"num_hidden_layers": 28,
|
| 22 |
+
"num_key_value_heads": 4,
|
| 23 |
+
"reference_frame": "first",
|
| 24 |
+
"rms_norm_eps": 1e-06,
|
| 25 |
+
"rope_scaling": {
|
| 26 |
+
"mrope_section": [
|
| 27 |
+
16,
|
| 28 |
+
24,
|
| 29 |
+
24
|
| 30 |
+
],
|
| 31 |
+
"rope_type": "default",
|
| 32 |
+
"type": "default"
|
| 33 |
+
},
|
| 34 |
+
"rope_theta": 1000000.0,
|
| 35 |
+
"sliding_window": 32768,
|
| 36 |
+
"tie_word_embeddings": false,
|
| 37 |
+
"torch_dtype": "bfloat16",
|
| 38 |
+
"transformers_version": "4.50.0",
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"use_geometry_encoder": true,
|
| 41 |
+
"use_sliding_window": false,
|
| 42 |
+
"video_token_id": 151656,
|
| 43 |
+
"vision_config": {
|
| 44 |
+
"depth": 32,
|
| 45 |
+
"fullatt_block_indexes": [
|
| 46 |
+
7,
|
| 47 |
+
15,
|
| 48 |
+
23,
|
| 49 |
+
31
|
| 50 |
+
],
|
| 51 |
+
"hidden_act": "silu",
|
| 52 |
+
"hidden_size": 1280,
|
| 53 |
+
"in_channels": 3,
|
| 54 |
+
"in_chans": 3,
|
| 55 |
+
"intermediate_size": 3420,
|
| 56 |
+
"model_type": "qwen2_5_vl",
|
| 57 |
+
"num_heads": 16,
|
| 58 |
+
"out_hidden_size": 3584,
|
| 59 |
+
"patch_size": 14,
|
| 60 |
+
"spatial_merge_size": 2,
|
| 61 |
+
"spatial_patch_size": 14,
|
| 62 |
+
"temporal_patch_size": 2,
|
| 63 |
+
"tokens_per_second": 2,
|
| 64 |
+
"torch_dtype": "bfloat16",
|
| 65 |
+
"window_size": 112
|
| 66 |
+
},
|
| 67 |
+
"vision_end_token_id": 151653,
|
| 68 |
+
"vision_start_token_id": 151652,
|
| 69 |
+
"vision_token_id": 151654,
|
| 70 |
+
"vocab_size": 152064
|
| 71 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.05,
|
| 10 |
+
"temperature": 1e-06,
|
| 11 |
+
"transformers_version": "4.50.0"
|
| 12 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3051699453bba1f8d0bf14e701c3116ba6eea0e63b4dfbdd446567f30c7e87bd
|
| 3 |
+
size 4882864360
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1bef3f3639cad782d1dd6d5c9613bcae2ea14635eaed385ab84320a4f5e0b8a
|
| 3 |
+
size 4932750944
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dbcb2407128bf7e584d3b7ea4cf183d34401f4abc50137447fcb0a4026ef48f9
|
| 3 |
+
size 4991495888
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0269f3250d64013b3cf07838b85d645115c59f368a9a766329091f18609044f2
|
| 3 |
+
size 3692182944
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": true,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.48145466,
|
| 8 |
+
0.4578275,
|
| 9 |
+
0.40821073
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.26862954,
|
| 14 |
+
0.26130258,
|
| 15 |
+
0.27577711
|
| 16 |
+
],
|
| 17 |
+
"max_pixels": 451584,
|
| 18 |
+
"merge_size": 2,
|
| 19 |
+
"min_pixels": 12544,
|
| 20 |
+
"patch_size": 14,
|
| 21 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 22 |
+
"resample": 3,
|
| 23 |
+
"rescale_factor": 0.00392156862745098,
|
| 24 |
+
"size": {
|
| 25 |
+
"longest_edge": 451584,
|
| 26 |
+
"shortest_edge": 12544
|
| 27 |
+
},
|
| 28 |
+
"temporal_patch_size": 2
|
| 29 |
+
}
|
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": "<|im_end|>",
|
| 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_config.json
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
| 199 |
+
"clean_up_tokenization_spaces": false,
|
| 200 |
+
"eos_token": "<|im_end|>",
|
| 201 |
+
"errors": "replace",
|
| 202 |
+
"extra_special_tokens": {},
|
| 203 |
+
"model_max_length": 12800,
|
| 204 |
+
"pad_token": "<|endoftext|>",
|
| 205 |
+
"padding_side": "right",
|
| 206 |
+
"split_special_tokens": false,
|
| 207 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 208 |
+
"unk_token": null
|
| 209 |
+
}
|
train.log
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2724 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.9998371388554119,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 3837,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0026057783134099868,
|
| 14 |
+
"grad_norm": 110.86865234375,
|
| 15 |
+
"learning_rate": 8.620689655172415e-07,
|
| 16 |
+
"loss": 11.4087,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0052115566268199735,
|
| 21 |
+
"grad_norm": 67.33353424072266,
|
| 22 |
+
"learning_rate": 1.724137931034483e-06,
|
| 23 |
+
"loss": 9.1907,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.00781733494022996,
|
| 28 |
+
"grad_norm": 30.089614868164062,
|
| 29 |
+
"learning_rate": 2.5862068965517246e-06,
|
| 30 |
+
"loss": 7.6051,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.010423113253639947,
|
| 35 |
+
"grad_norm": 46.92324447631836,
|
| 36 |
+
"learning_rate": 3.448275862068966e-06,
|
| 37 |
+
"loss": 6.7381,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.013028891567049934,
|
| 42 |
+
"grad_norm": 23.63817596435547,
|
| 43 |
+
"learning_rate": 4.310344827586207e-06,
|
| 44 |
+
"loss": 6.1279,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.01563466988045992,
|
| 49 |
+
"grad_norm": 24.60967445373535,
|
| 50 |
+
"learning_rate": 5.172413793103449e-06,
|
| 51 |
+
"loss": 5.9629,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.018240448193869906,
|
| 56 |
+
"grad_norm": 28.19795036315918,
|
| 57 |
+
"learning_rate": 6.03448275862069e-06,
|
| 58 |
+
"loss": 6.3056,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.020846226507279894,
|
| 63 |
+
"grad_norm": 27.955842971801758,
|
| 64 |
+
"learning_rate": 6.896551724137932e-06,
|
| 65 |
+
"loss": 6.1308,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.02345200482068988,
|
| 70 |
+
"grad_norm": 25.01333236694336,
|
| 71 |
+
"learning_rate": 7.758620689655173e-06,
|
| 72 |
+
"loss": 5.9488,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.026057783134099868,
|
| 77 |
+
"grad_norm": 23.80113983154297,
|
| 78 |
+
"learning_rate": 8.620689655172414e-06,
|
| 79 |
+
"loss": 6.0146,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.028663561447509853,
|
| 84 |
+
"grad_norm": 26.689817428588867,
|
| 85 |
+
"learning_rate": 9.482758620689655e-06,
|
| 86 |
+
"loss": 5.7203,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.03126933976091984,
|
| 91 |
+
"grad_norm": 22.709882736206055,
|
| 92 |
+
"learning_rate": 9.999971487192377e-06,
|
| 93 |
+
"loss": 5.7365,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.03387511807432983,
|
| 98 |
+
"grad_norm": 36.200618743896484,
|
| 99 |
+
"learning_rate": 9.999650721841219e-06,
|
| 100 |
+
"loss": 5.6874,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.03648089638773981,
|
| 105 |
+
"grad_norm": 29.23406410217285,
|
| 106 |
+
"learning_rate": 9.99897357307028e-06,
|
| 107 |
+
"loss": 5.9509,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.0390866747011498,
|
| 112 |
+
"grad_norm": 24.628616333007812,
|
| 113 |
+
"learning_rate": 9.997940089147847e-06,
|
| 114 |
+
"loss": 5.79,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.04169245301455979,
|
| 119 |
+
"grad_norm": 28.551050186157227,
|
| 120 |
+
"learning_rate": 9.996550343742372e-06,
|
| 121 |
+
"loss": 5.5759,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.04429823132796977,
|
| 126 |
+
"grad_norm": 33.07863998413086,
|
| 127 |
+
"learning_rate": 9.994804435917226e-06,
|
| 128 |
+
"loss": 5.6453,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.04690400964137976,
|
| 133 |
+
"grad_norm": 22.246503829956055,
|
| 134 |
+
"learning_rate": 9.992702490123616e-06,
|
| 135 |
+
"loss": 5.2791,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.04950978795478975,
|
| 140 |
+
"grad_norm": 20.640499114990234,
|
| 141 |
+
"learning_rate": 9.99024465619174e-06,
|
| 142 |
+
"loss": 5.4255,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.052115566268199735,
|
| 147 |
+
"grad_norm": 23.933834075927734,
|
| 148 |
+
"learning_rate": 9.987431109320085e-06,
|
| 149 |
+
"loss": 5.6609,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.05472134458160972,
|
| 154 |
+
"grad_norm": 15.145009994506836,
|
| 155 |
+
"learning_rate": 9.984262050062952e-06,
|
| 156 |
+
"loss": 5.2873,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.057327122895019705,
|
| 161 |
+
"grad_norm": 29.326797485351562,
|
| 162 |
+
"learning_rate": 9.98073770431616e-06,
|
| 163 |
+
"loss": 5.4614,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.059932901208429694,
|
| 168 |
+
"grad_norm": 25.808948516845703,
|
| 169 |
+
"learning_rate": 9.97685832330093e-06,
|
| 170 |
+
"loss": 5.573,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.06253867952183968,
|
| 175 |
+
"grad_norm": 28.513263702392578,
|
| 176 |
+
"learning_rate": 9.972624183546001e-06,
|
| 177 |
+
"loss": 5.4075,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.06514445783524966,
|
| 182 |
+
"grad_norm": 22.59028434753418,
|
| 183 |
+
"learning_rate": 9.968035586867893e-06,
|
| 184 |
+
"loss": 5.3587,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.06775023614865966,
|
| 189 |
+
"grad_norm": 21.76101303100586,
|
| 190 |
+
"learning_rate": 9.96309286034941e-06,
|
| 191 |
+
"loss": 5.1256,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.07035601446206964,
|
| 196 |
+
"grad_norm": 24.01523780822754,
|
| 197 |
+
"learning_rate": 9.95779635631632e-06,
|
| 198 |
+
"loss": 5.3442,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.07296179277547962,
|
| 203 |
+
"grad_norm": 26.637128829956055,
|
| 204 |
+
"learning_rate": 9.952146452312243e-06,
|
| 205 |
+
"loss": 5.2615,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.07556757108888962,
|
| 210 |
+
"grad_norm": 30.170167922973633,
|
| 211 |
+
"learning_rate": 9.946143551071731e-06,
|
| 212 |
+
"loss": 5.1369,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.0781733494022996,
|
| 217 |
+
"grad_norm": 19.498395919799805,
|
| 218 |
+
"learning_rate": 9.939788080491572e-06,
|
| 219 |
+
"loss": 5.3608,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.08077912771570958,
|
| 224 |
+
"grad_norm": 23.854351043701172,
|
| 225 |
+
"learning_rate": 9.933080493600281e-06,
|
| 226 |
+
"loss": 5.3208,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.08338490602911958,
|
| 231 |
+
"grad_norm": 18.571094512939453,
|
| 232 |
+
"learning_rate": 9.926021268525808e-06,
|
| 233 |
+
"loss": 5.3767,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.08599068434252956,
|
| 238 |
+
"grad_norm": 21.687772750854492,
|
| 239 |
+
"learning_rate": 9.918610908461455e-06,
|
| 240 |
+
"loss": 5.4237,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.08859646265593954,
|
| 245 |
+
"grad_norm": 25.41843605041504,
|
| 246 |
+
"learning_rate": 9.910849941630018e-06,
|
| 247 |
+
"loss": 5.2219,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.09120224096934954,
|
| 252 |
+
"grad_norm": 25.540990829467773,
|
| 253 |
+
"learning_rate": 9.902738921246122e-06,
|
| 254 |
+
"loss": 5.2091,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.09380801928275952,
|
| 259 |
+
"grad_norm": 31.44894027709961,
|
| 260 |
+
"learning_rate": 9.89427842547679e-06,
|
| 261 |
+
"loss": 5.1991,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.09641379759616951,
|
| 266 |
+
"grad_norm": 22.592653274536133,
|
| 267 |
+
"learning_rate": 9.885469057400234e-06,
|
| 268 |
+
"loss": 5.1389,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.0990195759095795,
|
| 273 |
+
"grad_norm": 22.170074462890625,
|
| 274 |
+
"learning_rate": 9.876311444962866e-06,
|
| 275 |
+
"loss": 5.0448,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.10162535422298948,
|
| 280 |
+
"grad_norm": 13.822409629821777,
|
| 281 |
+
"learning_rate": 9.866806240934527e-06,
|
| 282 |
+
"loss": 5.0568,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.10423113253639947,
|
| 287 |
+
"grad_norm": 19.269241333007812,
|
| 288 |
+
"learning_rate": 9.856954122861978e-06,
|
| 289 |
+
"loss": 4.9459,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.10683691084980945,
|
| 294 |
+
"grad_norm": 17.852279663085938,
|
| 295 |
+
"learning_rate": 9.846755793020579e-06,
|
| 296 |
+
"loss": 5.0611,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.10944268916321943,
|
| 301 |
+
"grad_norm": 21.483306884765625,
|
| 302 |
+
"learning_rate": 9.836211978364248e-06,
|
| 303 |
+
"loss": 5.3688,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.11204846747662943,
|
| 308 |
+
"grad_norm": 17.595417022705078,
|
| 309 |
+
"learning_rate": 9.825323430473626e-06,
|
| 310 |
+
"loss": 5.1688,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.11465424579003941,
|
| 315 |
+
"grad_norm": 18.144386291503906,
|
| 316 |
+
"learning_rate": 9.814090925502526e-06,
|
| 317 |
+
"loss": 5.1724,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.11726002410344939,
|
| 322 |
+
"grad_norm": 22.921968460083008,
|
| 323 |
+
"learning_rate": 9.80251526412258e-06,
|
| 324 |
+
"loss": 5.3381,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.11986580241685939,
|
| 329 |
+
"grad_norm": 17.377622604370117,
|
| 330 |
+
"learning_rate": 9.790597271466192e-06,
|
| 331 |
+
"loss": 5.2437,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.12247158073026937,
|
| 336 |
+
"grad_norm": 19.573436737060547,
|
| 337 |
+
"learning_rate": 9.778337797067697e-06,
|
| 338 |
+
"loss": 5.0667,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.12507735904367936,
|
| 343 |
+
"grad_norm": 17.62881851196289,
|
| 344 |
+
"learning_rate": 9.765737714802825e-06,
|
| 345 |
+
"loss": 5.1604,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.12768313735708933,
|
| 350 |
+
"grad_norm": 21.49463653564453,
|
| 351 |
+
"learning_rate": 9.7527979228264e-06,
|
| 352 |
+
"loss": 5.0928,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.13028891567049933,
|
| 357 |
+
"grad_norm": 18.050058364868164,
|
| 358 |
+
"learning_rate": 9.739519343508314e-06,
|
| 359 |
+
"loss": 5.075,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.13289469398390932,
|
| 364 |
+
"grad_norm": 19.688812255859375,
|
| 365 |
+
"learning_rate": 9.725902923367792e-06,
|
| 366 |
+
"loss": 5.0903,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.13550047229731932,
|
| 371 |
+
"grad_norm": 19.041973114013672,
|
| 372 |
+
"learning_rate": 9.711949633005909e-06,
|
| 373 |
+
"loss": 4.9269,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.1381062506107293,
|
| 378 |
+
"grad_norm": 18.476308822631836,
|
| 379 |
+
"learning_rate": 9.69766046703641e-06,
|
| 380 |
+
"loss": 4.8544,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.14071202892413928,
|
| 385 |
+
"grad_norm": 15.722190856933594,
|
| 386 |
+
"learning_rate": 9.683036444014817e-06,
|
| 387 |
+
"loss": 4.9984,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.14331780723754928,
|
| 392 |
+
"grad_norm": 21.487024307250977,
|
| 393 |
+
"learning_rate": 9.668078606365816e-06,
|
| 394 |
+
"loss": 4.8977,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.14592358555095924,
|
| 399 |
+
"grad_norm": 18.666223526000977,
|
| 400 |
+
"learning_rate": 9.652788020308952e-06,
|
| 401 |
+
"loss": 4.901,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.14852936386436924,
|
| 406 |
+
"grad_norm": 20.14147186279297,
|
| 407 |
+
"learning_rate": 9.637165775782637e-06,
|
| 408 |
+
"loss": 4.9971,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.15113514217777924,
|
| 413 |
+
"grad_norm": 23.309844970703125,
|
| 414 |
+
"learning_rate": 9.621212986366443e-06,
|
| 415 |
+
"loss": 5.0534,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.1537409204911892,
|
| 420 |
+
"grad_norm": 13.043556213378906,
|
| 421 |
+
"learning_rate": 9.60493078920174e-06,
|
| 422 |
+
"loss": 5.0522,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.1563466988045992,
|
| 427 |
+
"grad_norm": 20.287921905517578,
|
| 428 |
+
"learning_rate": 9.588320344910619e-06,
|
| 429 |
+
"loss": 5.0414,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.1589524771180092,
|
| 434 |
+
"grad_norm": 14.688277244567871,
|
| 435 |
+
"learning_rate": 9.571382837513185e-06,
|
| 436 |
+
"loss": 4.6986,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.16155825543141916,
|
| 441 |
+
"grad_norm": 18.477903366088867,
|
| 442 |
+
"learning_rate": 9.554119474343135e-06,
|
| 443 |
+
"loss": 4.9974,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.16416403374482916,
|
| 448 |
+
"grad_norm": 16.775569915771484,
|
| 449 |
+
"learning_rate": 9.536531485961713e-06,
|
| 450 |
+
"loss": 4.7439,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.16676981205823915,
|
| 455 |
+
"grad_norm": 18.829345703125,
|
| 456 |
+
"learning_rate": 9.518620126069985e-06,
|
| 457 |
+
"loss": 4.6874,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.16937559037164912,
|
| 462 |
+
"grad_norm": 17.522567749023438,
|
| 463 |
+
"learning_rate": 9.50038667141948e-06,
|
| 464 |
+
"loss": 4.8453,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.17198136868505912,
|
| 469 |
+
"grad_norm": 18.713659286499023,
|
| 470 |
+
"learning_rate": 9.481832421721169e-06,
|
| 471 |
+
"loss": 4.7213,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.1745871469984691,
|
| 476 |
+
"grad_norm": 20.204282760620117,
|
| 477 |
+
"learning_rate": 9.46295869955284e-06,
|
| 478 |
+
"loss": 4.8567,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.17719292531187908,
|
| 483 |
+
"grad_norm": 16.129371643066406,
|
| 484 |
+
"learning_rate": 9.443766850264801e-06,
|
| 485 |
+
"loss": 4.9081,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.17979870362528907,
|
| 490 |
+
"grad_norm": 25.332008361816406,
|
| 491 |
+
"learning_rate": 9.424258241883991e-06,
|
| 492 |
+
"loss": 4.9269,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.18240448193869907,
|
| 497 |
+
"grad_norm": 15.747159957885742,
|
| 498 |
+
"learning_rate": 9.404434265016467e-06,
|
| 499 |
+
"loss": 4.7581,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.18501026025210907,
|
| 504 |
+
"grad_norm": 20.14042854309082,
|
| 505 |
+
"learning_rate": 9.384296332748276e-06,
|
| 506 |
+
"loss": 4.9649,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.18761603856551903,
|
| 511 |
+
"grad_norm": 14.901525497436523,
|
| 512 |
+
"learning_rate": 9.363845880544723e-06,
|
| 513 |
+
"loss": 4.7825,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.19022181687892903,
|
| 518 |
+
"grad_norm": 19.030302047729492,
|
| 519 |
+
"learning_rate": 9.343084366148064e-06,
|
| 520 |
+
"loss": 4.9372,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.19282759519233902,
|
| 525 |
+
"grad_norm": 17.860355377197266,
|
| 526 |
+
"learning_rate": 9.322013269473575e-06,
|
| 527 |
+
"loss": 4.7285,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.195433373505749,
|
| 532 |
+
"grad_norm": 12.881828308105469,
|
| 533 |
+
"learning_rate": 9.300634092504077e-06,
|
| 534 |
+
"loss": 4.8045,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.198039151819159,
|
| 539 |
+
"grad_norm": 18.505136489868164,
|
| 540 |
+
"learning_rate": 9.27894835918287e-06,
|
| 541 |
+
"loss": 4.9374,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.20064493013256898,
|
| 546 |
+
"grad_norm": 18.28144645690918,
|
| 547 |
+
"learning_rate": 9.25695761530509e-06,
|
| 548 |
+
"loss": 5.0411,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.20325070844597895,
|
| 553 |
+
"grad_norm": 17.294910430908203,
|
| 554 |
+
"learning_rate": 9.234663428407544e-06,
|
| 555 |
+
"loss": 4.769,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.20585648675938895,
|
| 560 |
+
"grad_norm": 14.820845603942871,
|
| 561 |
+
"learning_rate": 9.212067387656959e-06,
|
| 562 |
+
"loss": 4.8812,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.20846226507279894,
|
| 567 |
+
"grad_norm": 20.82420539855957,
|
| 568 |
+
"learning_rate": 9.189171103736703e-06,
|
| 569 |
+
"loss": 4.6257,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.2110680433862089,
|
| 574 |
+
"grad_norm": 17.070852279663086,
|
| 575 |
+
"learning_rate": 9.165976208731979e-06,
|
| 576 |
+
"loss": 4.9519,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.2136738216996189,
|
| 581 |
+
"grad_norm": 22.17974281311035,
|
| 582 |
+
"learning_rate": 9.142484356013486e-06,
|
| 583 |
+
"loss": 4.9592,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.2162796000130289,
|
| 588 |
+
"grad_norm": 18.09177017211914,
|
| 589 |
+
"learning_rate": 9.118697220119563e-06,
|
| 590 |
+
"loss": 4.4487,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.21888537832643887,
|
| 595 |
+
"grad_norm": 15.924223899841309,
|
| 596 |
+
"learning_rate": 9.09461649663682e-06,
|
| 597 |
+
"loss": 4.8125,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.22149115663984886,
|
| 602 |
+
"grad_norm": 16.78546905517578,
|
| 603 |
+
"learning_rate": 9.070243902079285e-06,
|
| 604 |
+
"loss": 4.7626,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.22409693495325886,
|
| 609 |
+
"grad_norm": 15.40041732788086,
|
| 610 |
+
"learning_rate": 9.045581173766038e-06,
|
| 611 |
+
"loss": 4.7893,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.22670271326666883,
|
| 616 |
+
"grad_norm": 19.0047664642334,
|
| 617 |
+
"learning_rate": 9.020630069697378e-06,
|
| 618 |
+
"loss": 4.9998,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.22930849158007882,
|
| 623 |
+
"grad_norm": 17.001070022583008,
|
| 624 |
+
"learning_rate": 8.995392368429503e-06,
|
| 625 |
+
"loss": 4.5877,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.23191426989348882,
|
| 630 |
+
"grad_norm": 12.525654792785645,
|
| 631 |
+
"learning_rate": 8.969869868947743e-06,
|
| 632 |
+
"loss": 4.5884,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.23452004820689878,
|
| 637 |
+
"grad_norm": 11.931947708129883,
|
| 638 |
+
"learning_rate": 8.944064390538314e-06,
|
| 639 |
+
"loss": 4.74,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.23712582652030878,
|
| 644 |
+
"grad_norm": 13.704660415649414,
|
| 645 |
+
"learning_rate": 8.917977772658639e-06,
|
| 646 |
+
"loss": 4.6114,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.23973160483371878,
|
| 651 |
+
"grad_norm": 14.836153030395508,
|
| 652 |
+
"learning_rate": 8.891611874806236e-06,
|
| 653 |
+
"loss": 4.5371,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.24233738314712877,
|
| 658 |
+
"grad_norm": 17.466421127319336,
|
| 659 |
+
"learning_rate": 8.864968576386157e-06,
|
| 660 |
+
"loss": 4.7917,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.24494316146053874,
|
| 665 |
+
"grad_norm": 15.29416561126709,
|
| 666 |
+
"learning_rate": 8.838049776577036e-06,
|
| 667 |
+
"loss": 4.5563,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.24754893977394873,
|
| 672 |
+
"grad_norm": 14.739514350891113,
|
| 673 |
+
"learning_rate": 8.810857394195693e-06,
|
| 674 |
+
"loss": 4.6889,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.25015471808735873,
|
| 679 |
+
"grad_norm": 19.16230010986328,
|
| 680 |
+
"learning_rate": 8.783393367560382e-06,
|
| 681 |
+
"loss": 4.7563,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.2527604964007687,
|
| 686 |
+
"grad_norm": 15.767837524414062,
|
| 687 |
+
"learning_rate": 8.755659654352599e-06,
|
| 688 |
+
"loss": 4.6225,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.25536627471417866,
|
| 693 |
+
"grad_norm": 18.233675003051758,
|
| 694 |
+
"learning_rate": 8.72765823147756e-06,
|
| 695 |
+
"loss": 4.9221,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.2579720530275887,
|
| 700 |
+
"grad_norm": 17.42734146118164,
|
| 701 |
+
"learning_rate": 8.699391094923258e-06,
|
| 702 |
+
"loss": 4.6117,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.26057783134099866,
|
| 707 |
+
"grad_norm": 16.672109603881836,
|
| 708 |
+
"learning_rate": 8.670860259618208e-06,
|
| 709 |
+
"loss": 4.605,
|
| 710 |
+
"step": 1000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.2631836096544087,
|
| 714 |
+
"grad_norm": 11.820645332336426,
|
| 715 |
+
"learning_rate": 8.642067759287811e-06,
|
| 716 |
+
"loss": 4.6395,
|
| 717 |
+
"step": 1010
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.26578938796781865,
|
| 721 |
+
"grad_norm": 21.83611297607422,
|
| 722 |
+
"learning_rate": 8.61301564630938e-06,
|
| 723 |
+
"loss": 4.613,
|
| 724 |
+
"step": 1020
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.2683951662812286,
|
| 728 |
+
"grad_norm": 17.045490264892578,
|
| 729 |
+
"learning_rate": 8.583705991565853e-06,
|
| 730 |
+
"loss": 4.5266,
|
| 731 |
+
"step": 1030
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.27100094459463864,
|
| 735 |
+
"grad_norm": 11.697915077209473,
|
| 736 |
+
"learning_rate": 8.554140884298175e-06,
|
| 737 |
+
"loss": 4.6898,
|
| 738 |
+
"step": 1040
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.2736067229080486,
|
| 742 |
+
"grad_norm": 15.796126365661621,
|
| 743 |
+
"learning_rate": 8.524322431956368e-06,
|
| 744 |
+
"loss": 4.5086,
|
| 745 |
+
"step": 1050
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.2762125012214586,
|
| 749 |
+
"grad_norm": 13.956991195678711,
|
| 750 |
+
"learning_rate": 8.494252760049318e-06,
|
| 751 |
+
"loss": 4.6036,
|
| 752 |
+
"step": 1060
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.2788182795348686,
|
| 756 |
+
"grad_norm": 16.567855834960938,
|
| 757 |
+
"learning_rate": 8.463934011993253e-06,
|
| 758 |
+
"loss": 4.5016,
|
| 759 |
+
"step": 1070
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.28142405784827856,
|
| 763 |
+
"grad_norm": 16.10079574584961,
|
| 764 |
+
"learning_rate": 8.433368348958965e-06,
|
| 765 |
+
"loss": 4.4031,
|
| 766 |
+
"step": 1080
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.28402983616168853,
|
| 770 |
+
"grad_norm": 16.99315071105957,
|
| 771 |
+
"learning_rate": 8.402557949717761e-06,
|
| 772 |
+
"loss": 4.3646,
|
| 773 |
+
"step": 1090
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.28663561447509855,
|
| 777 |
+
"grad_norm": 15.070565223693848,
|
| 778 |
+
"learning_rate": 8.371505010486147e-06,
|
| 779 |
+
"loss": 4.6657,
|
| 780 |
+
"step": 1100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.2892413927885085,
|
| 784 |
+
"grad_norm": 19.31537437438965,
|
| 785 |
+
"learning_rate": 8.340211744769283e-06,
|
| 786 |
+
"loss": 4.4376,
|
| 787 |
+
"step": 1110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.2918471711019185,
|
| 791 |
+
"grad_norm": 12.955595970153809,
|
| 792 |
+
"learning_rate": 8.308680383203202e-06,
|
| 793 |
+
"loss": 4.4304,
|
| 794 |
+
"step": 1120
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.2944529494153285,
|
| 798 |
+
"grad_norm": 13.809191703796387,
|
| 799 |
+
"learning_rate": 8.276913173395809e-06,
|
| 800 |
+
"loss": 4.4724,
|
| 801 |
+
"step": 1130
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.2970587277287385,
|
| 805 |
+
"grad_norm": 18.226318359375,
|
| 806 |
+
"learning_rate": 8.244912379766653e-06,
|
| 807 |
+
"loss": 4.3936,
|
| 808 |
+
"step": 1140
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.29966450604214845,
|
| 812 |
+
"grad_norm": 17.735475540161133,
|
| 813 |
+
"learning_rate": 8.21268028338554e-06,
|
| 814 |
+
"loss": 4.3535,
|
| 815 |
+
"step": 1150
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.30227028435555847,
|
| 819 |
+
"grad_norm": 13.831572532653809,
|
| 820 |
+
"learning_rate": 8.180219181809912e-06,
|
| 821 |
+
"loss": 4.5458,
|
| 822 |
+
"step": 1160
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.30487606266896844,
|
| 826 |
+
"grad_norm": 16.973173141479492,
|
| 827 |
+
"learning_rate": 8.147531388921084e-06,
|
| 828 |
+
"loss": 4.4995,
|
| 829 |
+
"step": 1170
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.3074818409823784,
|
| 833 |
+
"grad_norm": 18.7071475982666,
|
| 834 |
+
"learning_rate": 8.114619234759307e-06,
|
| 835 |
+
"loss": 4.5931,
|
| 836 |
+
"step": 1180
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.31008761929578843,
|
| 840 |
+
"grad_norm": 19.668136596679688,
|
| 841 |
+
"learning_rate": 8.081485065357673e-06,
|
| 842 |
+
"loss": 4.3721,
|
| 843 |
+
"step": 1190
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.3126933976091984,
|
| 847 |
+
"grad_norm": 15.036663055419922,
|
| 848 |
+
"learning_rate": 8.048131242574891e-06,
|
| 849 |
+
"loss": 4.5976,
|
| 850 |
+
"step": 1200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.31529917592260837,
|
| 854 |
+
"grad_norm": 17.58373260498047,
|
| 855 |
+
"learning_rate": 8.014560143926932e-06,
|
| 856 |
+
"loss": 4.3176,
|
| 857 |
+
"step": 1210
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.3179049542360184,
|
| 861 |
+
"grad_norm": 18.513734817504883,
|
| 862 |
+
"learning_rate": 7.98077416241755e-06,
|
| 863 |
+
"loss": 4.4521,
|
| 864 |
+
"step": 1220
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.32051073254942836,
|
| 868 |
+
"grad_norm": 16.059385299682617,
|
| 869 |
+
"learning_rate": 7.946775706367702e-06,
|
| 870 |
+
"loss": 4.3128,
|
| 871 |
+
"step": 1230
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.3231165108628383,
|
| 875 |
+
"grad_norm": 16.732637405395508,
|
| 876 |
+
"learning_rate": 7.91256719924389e-06,
|
| 877 |
+
"loss": 4.5139,
|
| 878 |
+
"step": 1240
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.32572228917624835,
|
| 882 |
+
"grad_norm": 14.471945762634277,
|
| 883 |
+
"learning_rate": 7.878151079485404e-06,
|
| 884 |
+
"loss": 4.3712,
|
| 885 |
+
"step": 1250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.3283280674896583,
|
| 889 |
+
"grad_norm": 12.185126304626465,
|
| 890 |
+
"learning_rate": 7.843529800330506e-06,
|
| 891 |
+
"loss": 4.3276,
|
| 892 |
+
"step": 1260
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.3309338458030683,
|
| 896 |
+
"grad_norm": 14.59766674041748,
|
| 897 |
+
"learning_rate": 7.808705829641566e-06,
|
| 898 |
+
"loss": 4.2467,
|
| 899 |
+
"step": 1270
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.3335396241164783,
|
| 903 |
+
"grad_norm": 15.650346755981445,
|
| 904 |
+
"learning_rate": 7.773681649729134e-06,
|
| 905 |
+
"loss": 4.3089,
|
| 906 |
+
"step": 1280
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.3361454024298883,
|
| 910 |
+
"grad_norm": 14.673676490783691,
|
| 911 |
+
"learning_rate": 7.738459757175018e-06,
|
| 912 |
+
"loss": 4.4802,
|
| 913 |
+
"step": 1290
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.33875118074329824,
|
| 917 |
+
"grad_norm": 14.831808090209961,
|
| 918 |
+
"learning_rate": 7.703042662654306e-06,
|
| 919 |
+
"loss": 4.3544,
|
| 920 |
+
"step": 1300
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.34135695905670826,
|
| 924 |
+
"grad_norm": 17.22333526611328,
|
| 925 |
+
"learning_rate": 7.667432890756405e-06,
|
| 926 |
+
"loss": 4.5225,
|
| 927 |
+
"step": 1310
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.34396273737011823,
|
| 931 |
+
"grad_norm": 16.81097984313965,
|
| 932 |
+
"learning_rate": 7.631632979805091e-06,
|
| 933 |
+
"loss": 4.5263,
|
| 934 |
+
"step": 1320
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.3465685156835282,
|
| 938 |
+
"grad_norm": 15.247102737426758,
|
| 939 |
+
"learning_rate": 7.595645481677566e-06,
|
| 940 |
+
"loss": 4.2129,
|
| 941 |
+
"step": 1330
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.3491742939969382,
|
| 945 |
+
"grad_norm": 18.437294006347656,
|
| 946 |
+
"learning_rate": 7.559472961622556e-06,
|
| 947 |
+
"loss": 4.238,
|
| 948 |
+
"step": 1340
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.3517800723103482,
|
| 952 |
+
"grad_norm": 15.78176212310791,
|
| 953 |
+
"learning_rate": 7.523117998077458e-06,
|
| 954 |
+
"loss": 4.4029,
|
| 955 |
+
"step": 1350
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.35438585062375816,
|
| 959 |
+
"grad_norm": 15.515727996826172,
|
| 960 |
+
"learning_rate": 7.486583182484549e-06,
|
| 961 |
+
"loss": 4.2979,
|
| 962 |
+
"step": 1360
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.3569916289371682,
|
| 966 |
+
"grad_norm": 13.51162338256836,
|
| 967 |
+
"learning_rate": 7.449871119106255e-06,
|
| 968 |
+
"loss": 4.2729,
|
| 969 |
+
"step": 1370
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.35959740725057815,
|
| 973 |
+
"grad_norm": 21.5229434967041,
|
| 974 |
+
"learning_rate": 7.412984424839517e-06,
|
| 975 |
+
"loss": 4.6604,
|
| 976 |
+
"step": 1380
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.3622031855639881,
|
| 980 |
+
"grad_norm": 11.996355056762695,
|
| 981 |
+
"learning_rate": 7.375925729029262e-06,
|
| 982 |
+
"loss": 4.2956,
|
| 983 |
+
"step": 1390
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.36480896387739814,
|
| 987 |
+
"grad_norm": 13.862077713012695,
|
| 988 |
+
"learning_rate": 7.33869767328097e-06,
|
| 989 |
+
"loss": 4.1634,
|
| 990 |
+
"step": 1400
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.3674147421908081,
|
| 994 |
+
"grad_norm": 14.155905723571777,
|
| 995 |
+
"learning_rate": 7.301302911272377e-06,
|
| 996 |
+
"loss": 4.3229,
|
| 997 |
+
"step": 1410
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.37002052050421813,
|
| 1001 |
+
"grad_norm": 14.502531051635742,
|
| 1002 |
+
"learning_rate": 7.263744108564322e-06,
|
| 1003 |
+
"loss": 4.1903,
|
| 1004 |
+
"step": 1420
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.3726262988176281,
|
| 1008 |
+
"grad_norm": 13.393369674682617,
|
| 1009 |
+
"learning_rate": 7.226023942410737e-06,
|
| 1010 |
+
"loss": 4.4647,
|
| 1011 |
+
"step": 1430
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.37523207713103807,
|
| 1015 |
+
"grad_norm": 15.637059211730957,
|
| 1016 |
+
"learning_rate": 7.188145101567808e-06,
|
| 1017 |
+
"loss": 4.2615,
|
| 1018 |
+
"step": 1440
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.3778378554444481,
|
| 1022 |
+
"grad_norm": 14.05248737335205,
|
| 1023 |
+
"learning_rate": 7.150110286102317e-06,
|
| 1024 |
+
"loss": 4.2637,
|
| 1025 |
+
"step": 1450
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.38044363375785806,
|
| 1029 |
+
"grad_norm": 13.274151802062988,
|
| 1030 |
+
"learning_rate": 7.111922207199179e-06,
|
| 1031 |
+
"loss": 4.4334,
|
| 1032 |
+
"step": 1460
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.383049412071268,
|
| 1036 |
+
"grad_norm": 11.994894027709961,
|
| 1037 |
+
"learning_rate": 7.073583586968177e-06,
|
| 1038 |
+
"loss": 4.2808,
|
| 1039 |
+
"step": 1470
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.38565519038467805,
|
| 1043 |
+
"grad_norm": 14.430219650268555,
|
| 1044 |
+
"learning_rate": 7.035097158249933e-06,
|
| 1045 |
+
"loss": 4.3506,
|
| 1046 |
+
"step": 1480
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.388260968698088,
|
| 1050 |
+
"grad_norm": 17.56449317932129,
|
| 1051 |
+
"learning_rate": 6.996465664421105e-06,
|
| 1052 |
+
"loss": 4.1288,
|
| 1053 |
+
"step": 1490
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.390866747011498,
|
| 1057 |
+
"grad_norm": 19.60065269470215,
|
| 1058 |
+
"learning_rate": 6.957691859198832e-06,
|
| 1059 |
+
"loss": 4.3444,
|
| 1060 |
+
"step": 1500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.393472525324908,
|
| 1064 |
+
"grad_norm": 18.07255744934082,
|
| 1065 |
+
"learning_rate": 6.9187785064444444e-06,
|
| 1066 |
+
"loss": 4.4992,
|
| 1067 |
+
"step": 1510
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.396078303638318,
|
| 1071 |
+
"grad_norm": 13.20527172088623,
|
| 1072 |
+
"learning_rate": 6.879728379966456e-06,
|
| 1073 |
+
"loss": 4.3032,
|
| 1074 |
+
"step": 1520
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.39868408195172794,
|
| 1078 |
+
"grad_norm": 14.027434349060059,
|
| 1079 |
+
"learning_rate": 6.840544263322837e-06,
|
| 1080 |
+
"loss": 4.1749,
|
| 1081 |
+
"step": 1530
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.40128986026513797,
|
| 1085 |
+
"grad_norm": 18.15109634399414,
|
| 1086 |
+
"learning_rate": 6.801228949622601e-06,
|
| 1087 |
+
"loss": 4.2167,
|
| 1088 |
+
"step": 1540
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.40389563857854793,
|
| 1092 |
+
"grad_norm": 16.032686233520508,
|
| 1093 |
+
"learning_rate": 6.761785241326702e-06,
|
| 1094 |
+
"loss": 4.3622,
|
| 1095 |
+
"step": 1550
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.4065014168919579,
|
| 1099 |
+
"grad_norm": 14.840039253234863,
|
| 1100 |
+
"learning_rate": 6.722215950048279e-06,
|
| 1101 |
+
"loss": 4.4087,
|
| 1102 |
+
"step": 1560
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.4091071952053679,
|
| 1106 |
+
"grad_norm": 17.22282600402832,
|
| 1107 |
+
"learning_rate": 6.682523896352233e-06,
|
| 1108 |
+
"loss": 4.2356,
|
| 1109 |
+
"step": 1570
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.4117129735187779,
|
| 1113 |
+
"grad_norm": 18.42442512512207,
|
| 1114 |
+
"learning_rate": 6.6427119095541745e-06,
|
| 1115 |
+
"loss": 4.2499,
|
| 1116 |
+
"step": 1580
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.41431875183218786,
|
| 1120 |
+
"grad_norm": 20.72328758239746,
|
| 1121 |
+
"learning_rate": 6.602782827518745e-06,
|
| 1122 |
+
"loss": 4.3409,
|
| 1123 |
+
"step": 1590
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.4169245301455979,
|
| 1127 |
+
"grad_norm": 14.20974063873291,
|
| 1128 |
+
"learning_rate": 6.562739496457331e-06,
|
| 1129 |
+
"loss": 4.2615,
|
| 1130 |
+
"step": 1600
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.41953030845900785,
|
| 1134 |
+
"grad_norm": 15.402676582336426,
|
| 1135 |
+
"learning_rate": 6.522584770725176e-06,
|
| 1136 |
+
"loss": 4.1779,
|
| 1137 |
+
"step": 1610
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.4221360867724178,
|
| 1141 |
+
"grad_norm": 12.078060150146484,
|
| 1142 |
+
"learning_rate": 6.482321512617921e-06,
|
| 1143 |
+
"loss": 4.1917,
|
| 1144 |
+
"step": 1620
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.42474186508582784,
|
| 1148 |
+
"grad_norm": 15.220149993896484,
|
| 1149 |
+
"learning_rate": 6.441952592167581e-06,
|
| 1150 |
+
"loss": 4.1267,
|
| 1151 |
+
"step": 1630
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.4273476433992378,
|
| 1155 |
+
"grad_norm": 17.776363372802734,
|
| 1156 |
+
"learning_rate": 6.401480886937953e-06,
|
| 1157 |
+
"loss": 4.0676,
|
| 1158 |
+
"step": 1640
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.4299534217126478,
|
| 1162 |
+
"grad_norm": 12.913515090942383,
|
| 1163 |
+
"learning_rate": 6.360909281819504e-06,
|
| 1164 |
+
"loss": 4.1282,
|
| 1165 |
+
"step": 1650
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.4325592000260578,
|
| 1169 |
+
"grad_norm": 11.285195350646973,
|
| 1170 |
+
"learning_rate": 6.320240668823736e-06,
|
| 1171 |
+
"loss": 4.0471,
|
| 1172 |
+
"step": 1660
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.43516497833946777,
|
| 1176 |
+
"grad_norm": 10.345324516296387,
|
| 1177 |
+
"learning_rate": 6.279477946877028e-06,
|
| 1178 |
+
"loss": 3.8555,
|
| 1179 |
+
"step": 1670
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.43777075665287773,
|
| 1183 |
+
"grad_norm": 13.721894264221191,
|
| 1184 |
+
"learning_rate": 6.23862402161401e-06,
|
| 1185 |
+
"loss": 3.9643,
|
| 1186 |
+
"step": 1680
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.44037653496628776,
|
| 1190 |
+
"grad_norm": 15.820916175842285,
|
| 1191 |
+
"learning_rate": 6.197681805170422e-06,
|
| 1192 |
+
"loss": 4.0938,
|
| 1193 |
+
"step": 1690
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.4429823132796977,
|
| 1197 |
+
"grad_norm": 17.715919494628906,
|
| 1198 |
+
"learning_rate": 6.1566542159755595e-06,
|
| 1199 |
+
"loss": 3.9832,
|
| 1200 |
+
"step": 1700
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.4455880915931077,
|
| 1204 |
+
"grad_norm": 8.974435806274414,
|
| 1205 |
+
"learning_rate": 6.115544178544225e-06,
|
| 1206 |
+
"loss": 3.9275,
|
| 1207 |
+
"step": 1710
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.4481938699065177,
|
| 1211 |
+
"grad_norm": 17.12237548828125,
|
| 1212 |
+
"learning_rate": 6.074354623268267e-06,
|
| 1213 |
+
"loss": 4.3123,
|
| 1214 |
+
"step": 1720
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.4507996482199277,
|
| 1218 |
+
"grad_norm": 16.286693572998047,
|
| 1219 |
+
"learning_rate": 6.0330884862077e-06,
|
| 1220 |
+
"loss": 3.9415,
|
| 1221 |
+
"step": 1730
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.45340542653333765,
|
| 1225 |
+
"grad_norm": 15.777528762817383,
|
| 1226 |
+
"learning_rate": 5.9917487088814155e-06,
|
| 1227 |
+
"loss": 3.7763,
|
| 1228 |
+
"step": 1740
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.4560112048467477,
|
| 1232 |
+
"grad_norm": 13.690078735351562,
|
| 1233 |
+
"learning_rate": 5.950338238057504e-06,
|
| 1234 |
+
"loss": 3.9306,
|
| 1235 |
+
"step": 1750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.45861698316015764,
|
| 1239 |
+
"grad_norm": 15.70811939239502,
|
| 1240 |
+
"learning_rate": 5.908860025543209e-06,
|
| 1241 |
+
"loss": 4.0651,
|
| 1242 |
+
"step": 1760
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.4612227614735676,
|
| 1246 |
+
"grad_norm": 17.726015090942383,
|
| 1247 |
+
"learning_rate": 5.8673170279745095e-06,
|
| 1248 |
+
"loss": 4.1444,
|
| 1249 |
+
"step": 1770
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.46382853978697763,
|
| 1253 |
+
"grad_norm": 14.940733909606934,
|
| 1254 |
+
"learning_rate": 5.825712206605378e-06,
|
| 1255 |
+
"loss": 4.0553,
|
| 1256 |
+
"step": 1780
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.4664343181003876,
|
| 1260 |
+
"grad_norm": 14.057848930358887,
|
| 1261 |
+
"learning_rate": 5.784048527096684e-06,
|
| 1262 |
+
"loss": 4.0629,
|
| 1263 |
+
"step": 1790
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.46904009641379757,
|
| 1267 |
+
"grad_norm": 16.68400764465332,
|
| 1268 |
+
"learning_rate": 5.742328959304807e-06,
|
| 1269 |
+
"loss": 4.0647,
|
| 1270 |
+
"step": 1800
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.4716458747272076,
|
| 1274 |
+
"grad_norm": 13.257894515991211,
|
| 1275 |
+
"learning_rate": 5.700556477069933e-06,
|
| 1276 |
+
"loss": 3.9701,
|
| 1277 |
+
"step": 1810
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.47425165304061756,
|
| 1281 |
+
"grad_norm": 14.973817825317383,
|
| 1282 |
+
"learning_rate": 5.65873405800408e-06,
|
| 1283 |
+
"loss": 4.1676,
|
| 1284 |
+
"step": 1820
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.4768574313540276,
|
| 1288 |
+
"grad_norm": 16.108644485473633,
|
| 1289 |
+
"learning_rate": 5.616864683278848e-06,
|
| 1290 |
+
"loss": 3.9516,
|
| 1291 |
+
"step": 1830
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.47946320966743755,
|
| 1295 |
+
"grad_norm": 15.061484336853027,
|
| 1296 |
+
"learning_rate": 5.574951337412908e-06,
|
| 1297 |
+
"loss": 4.1029,
|
| 1298 |
+
"step": 1840
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.4820689879808475,
|
| 1302 |
+
"grad_norm": 14.548176765441895,
|
| 1303 |
+
"learning_rate": 5.532997008059274e-06,
|
| 1304 |
+
"loss": 3.8363,
|
| 1305 |
+
"step": 1850
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.48467476629425754,
|
| 1309 |
+
"grad_norm": 14.403671264648438,
|
| 1310 |
+
"learning_rate": 5.4910046857923286e-06,
|
| 1311 |
+
"loss": 3.952,
|
| 1312 |
+
"step": 1860
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.4872805446076675,
|
| 1316 |
+
"grad_norm": 13.332658767700195,
|
| 1317 |
+
"learning_rate": 5.44897736389465e-06,
|
| 1318 |
+
"loss": 3.9628,
|
| 1319 |
+
"step": 1870
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.4898863229210775,
|
| 1323 |
+
"grad_norm": 12.246014595031738,
|
| 1324 |
+
"learning_rate": 5.406918038143653e-06,
|
| 1325 |
+
"loss": 3.9829,
|
| 1326 |
+
"step": 1880
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.4924921012344875,
|
| 1330 |
+
"grad_norm": 14.760672569274902,
|
| 1331 |
+
"learning_rate": 5.364829706598036e-06,
|
| 1332 |
+
"loss": 3.9532,
|
| 1333 |
+
"step": 1890
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.49509787954789747,
|
| 1337 |
+
"grad_norm": 14.489956855773926,
|
| 1338 |
+
"learning_rate": 5.322715369384081e-06,
|
| 1339 |
+
"loss": 3.98,
|
| 1340 |
+
"step": 1900
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.49770365786130744,
|
| 1344 |
+
"grad_norm": 16.848976135253906,
|
| 1345 |
+
"learning_rate": 5.2805780284817985e-06,
|
| 1346 |
+
"loss": 3.8639,
|
| 1347 |
+
"step": 1910
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.5003094361747175,
|
| 1351 |
+
"grad_norm": 15.439696311950684,
|
| 1352 |
+
"learning_rate": 5.238420687510938e-06,
|
| 1353 |
+
"loss": 4.0984,
|
| 1354 |
+
"step": 1920
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.5029152144881274,
|
| 1358 |
+
"grad_norm": 15.015402793884277,
|
| 1359 |
+
"learning_rate": 5.196246351516886e-06,
|
| 1360 |
+
"loss": 3.8387,
|
| 1361 |
+
"step": 1930
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.5055209928015374,
|
| 1365 |
+
"grad_norm": 15.858648300170898,
|
| 1366 |
+
"learning_rate": 5.154058026756464e-06,
|
| 1367 |
+
"loss": 3.9072,
|
| 1368 |
+
"step": 1940
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.5081267711149474,
|
| 1372 |
+
"grad_norm": 13.647195816040039,
|
| 1373 |
+
"learning_rate": 5.111858720483639e-06,
|
| 1374 |
+
"loss": 3.6977,
|
| 1375 |
+
"step": 1950
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.5107325494283573,
|
| 1379 |
+
"grad_norm": 14.408649444580078,
|
| 1380 |
+
"learning_rate": 5.069651440735153e-06,
|
| 1381 |
+
"loss": 3.9188,
|
| 1382 |
+
"step": 1960
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.5133383277417674,
|
| 1386 |
+
"grad_norm": 17.214282989501953,
|
| 1387 |
+
"learning_rate": 5.027439196116116e-06,
|
| 1388 |
+
"loss": 3.9998,
|
| 1389 |
+
"step": 1970
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.5159441060551774,
|
| 1393 |
+
"grad_norm": 14.95472240447998,
|
| 1394 |
+
"learning_rate": 4.985224995585539e-06,
|
| 1395 |
+
"loss": 4.102,
|
| 1396 |
+
"step": 1980
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.5185498843685873,
|
| 1400 |
+
"grad_norm": 13.100905418395996,
|
| 1401 |
+
"learning_rate": 4.94301184824185e-06,
|
| 1402 |
+
"loss": 3.8382,
|
| 1403 |
+
"step": 1990
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.5211556626819973,
|
| 1407 |
+
"grad_norm": 16.31537437438965,
|
| 1408 |
+
"learning_rate": 4.900802763108413e-06,
|
| 1409 |
+
"loss": 3.9042,
|
| 1410 |
+
"step": 2000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.5237614409954073,
|
| 1414 |
+
"grad_norm": 16.4555721282959,
|
| 1415 |
+
"learning_rate": 4.858600748919023e-06,
|
| 1416 |
+
"loss": 3.7303,
|
| 1417 |
+
"step": 2010
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.5263672193088174,
|
| 1421 |
+
"grad_norm": 17.20844078063965,
|
| 1422 |
+
"learning_rate": 4.816408813903454e-06,
|
| 1423 |
+
"loss": 3.9703,
|
| 1424 |
+
"step": 2020
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.5289729976222273,
|
| 1428 |
+
"grad_norm": 13.8233642578125,
|
| 1429 |
+
"learning_rate": 4.7742299655730095e-06,
|
| 1430 |
+
"loss": 3.8214,
|
| 1431 |
+
"step": 2030
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.5315787759356373,
|
| 1435 |
+
"grad_norm": 15.877490997314453,
|
| 1436 |
+
"learning_rate": 4.7320672105061626e-06,
|
| 1437 |
+
"loss": 4.1141,
|
| 1438 |
+
"step": 2040
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.5341845542490473,
|
| 1442 |
+
"grad_norm": 14.362630844116211,
|
| 1443 |
+
"learning_rate": 4.689923554134224e-06,
|
| 1444 |
+
"loss": 3.9246,
|
| 1445 |
+
"step": 2050
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.5367903325624572,
|
| 1449 |
+
"grad_norm": 12.109440803527832,
|
| 1450 |
+
"learning_rate": 4.6478020005271216e-06,
|
| 1451 |
+
"loss": 3.867,
|
| 1452 |
+
"step": 2060
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.5393961108758673,
|
| 1456 |
+
"grad_norm": 12.930885314941406,
|
| 1457 |
+
"learning_rate": 4.605705552179264e-06,
|
| 1458 |
+
"loss": 3.8407,
|
| 1459 |
+
"step": 2070
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.5420018891892773,
|
| 1463 |
+
"grad_norm": 16.971628189086914,
|
| 1464 |
+
"learning_rate": 4.563637209795509e-06,
|
| 1465 |
+
"loss": 3.7308,
|
| 1466 |
+
"step": 2080
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.5446076675026872,
|
| 1470 |
+
"grad_norm": 14.160455703735352,
|
| 1471 |
+
"learning_rate": 4.521599972077278e-06,
|
| 1472 |
+
"loss": 3.8111,
|
| 1473 |
+
"step": 2090
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.5472134458160972,
|
| 1477 |
+
"grad_norm": 12.518649101257324,
|
| 1478 |
+
"learning_rate": 4.479596835508798e-06,
|
| 1479 |
+
"loss": 3.6568,
|
| 1480 |
+
"step": 2100
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.5498192241295072,
|
| 1484 |
+
"grad_norm": 13.215614318847656,
|
| 1485 |
+
"learning_rate": 4.437630794143513e-06,
|
| 1486 |
+
"loss": 3.8166,
|
| 1487 |
+
"step": 2110
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.5524250024429171,
|
| 1491 |
+
"grad_norm": 14.059877395629883,
|
| 1492 |
+
"learning_rate": 4.395704839390657e-06,
|
| 1493 |
+
"loss": 3.8354,
|
| 1494 |
+
"step": 2120
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.5550307807563272,
|
| 1498 |
+
"grad_norm": 15.828983306884766,
|
| 1499 |
+
"learning_rate": 4.353821959802024e-06,
|
| 1500 |
+
"loss": 3.7703,
|
| 1501 |
+
"step": 2130
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.5576365590697372,
|
| 1505 |
+
"grad_norm": 17.402969360351562,
|
| 1506 |
+
"learning_rate": 4.311985140858935e-06,
|
| 1507 |
+
"loss": 3.7362,
|
| 1508 |
+
"step": 2140
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.5602423373831471,
|
| 1512 |
+
"grad_norm": 17.005844116210938,
|
| 1513 |
+
"learning_rate": 4.270197364759439e-06,
|
| 1514 |
+
"loss": 3.9624,
|
| 1515 |
+
"step": 2150
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.5628481156965571,
|
| 1519 |
+
"grad_norm": 14.91238784790039,
|
| 1520 |
+
"learning_rate": 4.228461610205722e-06,
|
| 1521 |
+
"loss": 4.049,
|
| 1522 |
+
"step": 2160
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.5654538940099672,
|
| 1526 |
+
"grad_norm": 14.350924491882324,
|
| 1527 |
+
"learning_rate": 4.186780852191795e-06,
|
| 1528 |
+
"loss": 3.7585,
|
| 1529 |
+
"step": 2170
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.5680596723233771,
|
| 1533 |
+
"grad_norm": 11.497078895568848,
|
| 1534 |
+
"learning_rate": 4.145158061791416e-06,
|
| 1535 |
+
"loss": 3.7662,
|
| 1536 |
+
"step": 2180
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.5706654506367871,
|
| 1540 |
+
"grad_norm": 15.729626655578613,
|
| 1541 |
+
"learning_rate": 4.103596205946323e-06,
|
| 1542 |
+
"loss": 3.7275,
|
| 1543 |
+
"step": 2190
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.5732712289501971,
|
| 1547 |
+
"grad_norm": 11.974518775939941,
|
| 1548 |
+
"learning_rate": 4.062098247254731e-06,
|
| 1549 |
+
"loss": 3.7067,
|
| 1550 |
+
"step": 2200
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.575877007263607,
|
| 1554 |
+
"grad_norm": 14.49791431427002,
|
| 1555 |
+
"learning_rate": 4.020667143760165e-06,
|
| 1556 |
+
"loss": 3.7751,
|
| 1557 |
+
"step": 2210
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.578482785577017,
|
| 1561 |
+
"grad_norm": 15.29405689239502,
|
| 1562 |
+
"learning_rate": 3.979305848740596e-06,
|
| 1563 |
+
"loss": 3.9426,
|
| 1564 |
+
"step": 2220
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.5810885638904271,
|
| 1568 |
+
"grad_norm": 12.552131652832031,
|
| 1569 |
+
"learning_rate": 3.938017310497932e-06,
|
| 1570 |
+
"loss": 3.6313,
|
| 1571 |
+
"step": 2230
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.583694342203837,
|
| 1575 |
+
"grad_norm": 17.384660720825195,
|
| 1576 |
+
"learning_rate": 3.896804472147861e-06,
|
| 1577 |
+
"loss": 3.8203,
|
| 1578 |
+
"step": 2240
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.586300120517247,
|
| 1582 |
+
"grad_norm": 14.073604583740234,
|
| 1583 |
+
"learning_rate": 3.85567027141005e-06,
|
| 1584 |
+
"loss": 3.6645,
|
| 1585 |
+
"step": 2250
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.588905898830657,
|
| 1589 |
+
"grad_norm": 13.519288063049316,
|
| 1590 |
+
"learning_rate": 3.814617640398753e-06,
|
| 1591 |
+
"loss": 3.8115,
|
| 1592 |
+
"step": 2260
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.5915116771440669,
|
| 1596 |
+
"grad_norm": 12.820542335510254,
|
| 1597 |
+
"learning_rate": 3.773649505413789e-06,
|
| 1598 |
+
"loss": 3.6747,
|
| 1599 |
+
"step": 2270
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.594117455457477,
|
| 1603 |
+
"grad_norm": 17.818037033081055,
|
| 1604 |
+
"learning_rate": 3.7327687867319717e-06,
|
| 1605 |
+
"loss": 3.5499,
|
| 1606 |
+
"step": 2280
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.596723233770887,
|
| 1610 |
+
"grad_norm": 16.579925537109375,
|
| 1611 |
+
"learning_rate": 3.691978398398923e-06,
|
| 1612 |
+
"loss": 3.7834,
|
| 1613 |
+
"step": 2290
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.5993290120842969,
|
| 1617 |
+
"grad_norm": 16.559738159179688,
|
| 1618 |
+
"learning_rate": 3.651281248021379e-06,
|
| 1619 |
+
"loss": 3.9243,
|
| 1620 |
+
"step": 2300
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.6019347903977069,
|
| 1624 |
+
"grad_norm": 12.809834480285645,
|
| 1625 |
+
"learning_rate": 3.610680236559909e-06,
|
| 1626 |
+
"loss": 3.7475,
|
| 1627 |
+
"step": 2310
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.6045405687111169,
|
| 1631 |
+
"grad_norm": 13.733206748962402,
|
| 1632 |
+
"learning_rate": 3.5701782581221488e-06,
|
| 1633 |
+
"loss": 3.6457,
|
| 1634 |
+
"step": 2320
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.6071463470245269,
|
| 1638 |
+
"grad_norm": 13.553963661193848,
|
| 1639 |
+
"learning_rate": 3.529778199756487e-06,
|
| 1640 |
+
"loss": 3.7017,
|
| 1641 |
+
"step": 2330
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.6097521253379369,
|
| 1645 |
+
"grad_norm": 16.884859085083008,
|
| 1646 |
+
"learning_rate": 3.4894829412462906e-06,
|
| 1647 |
+
"loss": 3.8158,
|
| 1648 |
+
"step": 2340
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.6123579036513469,
|
| 1652 |
+
"grad_norm": 13.558512687683105,
|
| 1653 |
+
"learning_rate": 3.4492953549046067e-06,
|
| 1654 |
+
"loss": 3.5459,
|
| 1655 |
+
"step": 2350
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.6149636819647568,
|
| 1659 |
+
"grad_norm": 15.28806209564209,
|
| 1660 |
+
"learning_rate": 3.4092183053694416e-06,
|
| 1661 |
+
"loss": 3.7603,
|
| 1662 |
+
"step": 2360
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.6175694602781668,
|
| 1666 |
+
"grad_norm": 19.83453941345215,
|
| 1667 |
+
"learning_rate": 3.3692546493995465e-06,
|
| 1668 |
+
"loss": 3.8987,
|
| 1669 |
+
"step": 2370
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.6201752385915769,
|
| 1673 |
+
"grad_norm": 15.962160110473633,
|
| 1674 |
+
"learning_rate": 3.329407235670796e-06,
|
| 1675 |
+
"loss": 3.8286,
|
| 1676 |
+
"step": 2380
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.6227810169049868,
|
| 1680 |
+
"grad_norm": 11.203872680664062,
|
| 1681 |
+
"learning_rate": 3.2896789045731213e-06,
|
| 1682 |
+
"loss": 3.7235,
|
| 1683 |
+
"step": 2390
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.6253867952183968,
|
| 1687 |
+
"grad_norm": 12.741243362426758,
|
| 1688 |
+
"learning_rate": 3.2500724880080457e-06,
|
| 1689 |
+
"loss": 3.5928,
|
| 1690 |
+
"step": 2400
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.6279925735318068,
|
| 1694 |
+
"grad_norm": 15.227933883666992,
|
| 1695 |
+
"learning_rate": 3.2105908091868244e-06,
|
| 1696 |
+
"loss": 3.7883,
|
| 1697 |
+
"step": 2410
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.6305983518452167,
|
| 1701 |
+
"grad_norm": 20.24930763244629,
|
| 1702 |
+
"learning_rate": 3.1712366824291942e-06,
|
| 1703 |
+
"loss": 3.8285,
|
| 1704 |
+
"step": 2420
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.6332041301586268,
|
| 1708 |
+
"grad_norm": 16.056732177734375,
|
| 1709 |
+
"learning_rate": 3.1320129129627746e-06,
|
| 1710 |
+
"loss": 3.9102,
|
| 1711 |
+
"step": 2430
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.6358099084720368,
|
| 1715 |
+
"grad_norm": 15.546942710876465,
|
| 1716 |
+
"learning_rate": 3.092922296723093e-06,
|
| 1717 |
+
"loss": 3.6855,
|
| 1718 |
+
"step": 2440
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.6384156867854467,
|
| 1722 |
+
"grad_norm": 11.7498197555542,
|
| 1723 |
+
"learning_rate": 3.0539676201543033e-06,
|
| 1724 |
+
"loss": 3.3764,
|
| 1725 |
+
"step": 2450
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.6410214650988567,
|
| 1729 |
+
"grad_norm": 12.475979804992676,
|
| 1730 |
+
"learning_rate": 3.0151516600105425e-06,
|
| 1731 |
+
"loss": 3.6341,
|
| 1732 |
+
"step": 2460
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 0.6436272434122667,
|
| 1736 |
+
"grad_norm": 13.076690673828125,
|
| 1737 |
+
"learning_rate": 2.9764771831580196e-06,
|
| 1738 |
+
"loss": 3.5907,
|
| 1739 |
+
"step": 2470
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 0.6462330217256766,
|
| 1743 |
+
"grad_norm": 16.922422409057617,
|
| 1744 |
+
"learning_rate": 2.937946946377771e-06,
|
| 1745 |
+
"loss": 3.7659,
|
| 1746 |
+
"step": 2480
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.6488388000390867,
|
| 1750 |
+
"grad_norm": 14.761316299438477,
|
| 1751 |
+
"learning_rate": 2.8995636961691696e-06,
|
| 1752 |
+
"loss": 3.6365,
|
| 1753 |
+
"step": 2490
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.6514445783524967,
|
| 1757 |
+
"grad_norm": 14.662260055541992,
|
| 1758 |
+
"learning_rate": 2.8613301685541317e-06,
|
| 1759 |
+
"loss": 3.609,
|
| 1760 |
+
"step": 2500
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 0.6540503566659066,
|
| 1764 |
+
"grad_norm": 15.36502456665039,
|
| 1765 |
+
"learning_rate": 2.823249088882106e-06,
|
| 1766 |
+
"loss": 3.3966,
|
| 1767 |
+
"step": 2510
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.6566561349793166,
|
| 1771 |
+
"grad_norm": 13.890869140625,
|
| 1772 |
+
"learning_rate": 2.785323171635792e-06,
|
| 1773 |
+
"loss": 3.7109,
|
| 1774 |
+
"step": 2520
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 0.6592619132927267,
|
| 1778 |
+
"grad_norm": 12.394003868103027,
|
| 1779 |
+
"learning_rate": 2.7475551202376592e-06,
|
| 1780 |
+
"loss": 3.5207,
|
| 1781 |
+
"step": 2530
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 0.6618676916061366,
|
| 1785 |
+
"grad_norm": 15.049907684326172,
|
| 1786 |
+
"learning_rate": 2.709947626857231e-06,
|
| 1787 |
+
"loss": 3.7788,
|
| 1788 |
+
"step": 2540
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 0.6644734699195466,
|
| 1792 |
+
"grad_norm": 12.339613914489746,
|
| 1793 |
+
"learning_rate": 2.6725033722191933e-06,
|
| 1794 |
+
"loss": 3.5978,
|
| 1795 |
+
"step": 2550
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.6670792482329566,
|
| 1799 |
+
"grad_norm": 14.613420486450195,
|
| 1800 |
+
"learning_rate": 2.6352250254123024e-06,
|
| 1801 |
+
"loss": 3.5278,
|
| 1802 |
+
"step": 2560
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.6696850265463665,
|
| 1806 |
+
"grad_norm": 16.619083404541016,
|
| 1807 |
+
"learning_rate": 2.598115243699123e-06,
|
| 1808 |
+
"loss": 3.5254,
|
| 1809 |
+
"step": 2570
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.6722908048597765,
|
| 1813 |
+
"grad_norm": 15.4705810546875,
|
| 1814 |
+
"learning_rate": 2.5611766723266263e-06,
|
| 1815 |
+
"loss": 3.6409,
|
| 1816 |
+
"step": 2580
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.6748965831731866,
|
| 1820 |
+
"grad_norm": 16.65482521057129,
|
| 1821 |
+
"learning_rate": 2.52441194433762e-06,
|
| 1822 |
+
"loss": 3.5709,
|
| 1823 |
+
"step": 2590
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 0.6775023614865965,
|
| 1827 |
+
"grad_norm": 17.72576904296875,
|
| 1828 |
+
"learning_rate": 2.4878236803830737e-06,
|
| 1829 |
+
"loss": 3.7983,
|
| 1830 |
+
"step": 2600
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 0.6801081398000065,
|
| 1834 |
+
"grad_norm": 10.647336959838867,
|
| 1835 |
+
"learning_rate": 2.451414488535296e-06,
|
| 1836 |
+
"loss": 3.4455,
|
| 1837 |
+
"step": 2610
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 0.6827139181134165,
|
| 1841 |
+
"grad_norm": 12.20052719116211,
|
| 1842 |
+
"learning_rate": 2.415186964102049e-06,
|
| 1843 |
+
"loss": 3.271,
|
| 1844 |
+
"step": 2620
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 0.6853196964268264,
|
| 1848 |
+
"grad_norm": 11.24185848236084,
|
| 1849 |
+
"learning_rate": 2.3791436894415322e-06,
|
| 1850 |
+
"loss": 3.4162,
|
| 1851 |
+
"step": 2630
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 0.6879254747402365,
|
| 1855 |
+
"grad_norm": 13.407733917236328,
|
| 1856 |
+
"learning_rate": 2.343287233778319e-06,
|
| 1857 |
+
"loss": 3.4585,
|
| 1858 |
+
"step": 2640
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 0.6905312530536465,
|
| 1862 |
+
"grad_norm": 17.364498138427734,
|
| 1863 |
+
"learning_rate": 2.3076201530202097e-06,
|
| 1864 |
+
"loss": 3.5986,
|
| 1865 |
+
"step": 2650
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 0.6931370313670564,
|
| 1869 |
+
"grad_norm": 16.45816993713379,
|
| 1870 |
+
"learning_rate": 2.2721449895760513e-06,
|
| 1871 |
+
"loss": 3.414,
|
| 1872 |
+
"step": 2660
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 0.6957428096804664,
|
| 1876 |
+
"grad_norm": 15.844749450683594,
|
| 1877 |
+
"learning_rate": 2.2368642721745e-06,
|
| 1878 |
+
"loss": 3.5246,
|
| 1879 |
+
"step": 2670
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 0.6983485879938764,
|
| 1883 |
+
"grad_norm": 16.561187744140625,
|
| 1884 |
+
"learning_rate": 2.201780515683781e-06,
|
| 1885 |
+
"loss": 3.4861,
|
| 1886 |
+
"step": 2680
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 0.7009543663072864,
|
| 1890 |
+
"grad_norm": 10.903932571411133,
|
| 1891 |
+
"learning_rate": 2.1668962209324103e-06,
|
| 1892 |
+
"loss": 3.4997,
|
| 1893 |
+
"step": 2690
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 0.7035601446206964,
|
| 1897 |
+
"grad_norm": 14.6264066696167,
|
| 1898 |
+
"learning_rate": 2.132213874530948e-06,
|
| 1899 |
+
"loss": 3.4731,
|
| 1900 |
+
"step": 2700
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 0.7061659229341064,
|
| 1904 |
+
"grad_norm": 14.201605796813965,
|
| 1905 |
+
"learning_rate": 2.097735948694732e-06,
|
| 1906 |
+
"loss": 3.2508,
|
| 1907 |
+
"step": 2710
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 0.7087717012475163,
|
| 1911 |
+
"grad_norm": 18.47288703918457,
|
| 1912 |
+
"learning_rate": 2.0634649010676693e-06,
|
| 1913 |
+
"loss": 3.3319,
|
| 1914 |
+
"step": 2720
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 0.7113774795609263,
|
| 1918 |
+
"grad_norm": 12.578482627868652,
|
| 1919 |
+
"learning_rate": 2.029403174547037e-06,
|
| 1920 |
+
"loss": 3.3993,
|
| 1921 |
+
"step": 2730
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 0.7139832578743364,
|
| 1925 |
+
"grad_norm": 15.884589195251465,
|
| 1926 |
+
"learning_rate": 1.9955531971093633e-06,
|
| 1927 |
+
"loss": 3.7486,
|
| 1928 |
+
"step": 2740
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 0.7165890361877463,
|
| 1932 |
+
"grad_norm": 15.347840309143066,
|
| 1933 |
+
"learning_rate": 1.9619173816373432e-06,
|
| 1934 |
+
"loss": 3.5858,
|
| 1935 |
+
"step": 2750
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 0.7191948145011563,
|
| 1939 |
+
"grad_norm": 10.553122520446777,
|
| 1940 |
+
"learning_rate": 1.92849812574785e-06,
|
| 1941 |
+
"loss": 3.3866,
|
| 1942 |
+
"step": 2760
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 0.7218005928145663,
|
| 1946 |
+
"grad_norm": 14.734107971191406,
|
| 1947 |
+
"learning_rate": 1.895297811621038e-06,
|
| 1948 |
+
"loss": 3.436,
|
| 1949 |
+
"step": 2770
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 0.7244063711279762,
|
| 1953 |
+
"grad_norm": 11.851035118103027,
|
| 1954 |
+
"learning_rate": 1.862318805830518e-06,
|
| 1955 |
+
"loss": 3.4734,
|
| 1956 |
+
"step": 2780
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 0.7270121494413863,
|
| 1960 |
+
"grad_norm": 10.015957832336426,
|
| 1961 |
+
"learning_rate": 1.8295634591746831e-06,
|
| 1962 |
+
"loss": 3.6312,
|
| 1963 |
+
"step": 2790
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 0.7296179277547963,
|
| 1967 |
+
"grad_norm": 16.27783203125,
|
| 1968 |
+
"learning_rate": 1.7970341065091246e-06,
|
| 1969 |
+
"loss": 3.4476,
|
| 1970 |
+
"step": 2800
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 0.7322237060682062,
|
| 1974 |
+
"grad_norm": 15.0385160446167,
|
| 1975 |
+
"learning_rate": 1.7647330665802126e-06,
|
| 1976 |
+
"loss": 3.3677,
|
| 1977 |
+
"step": 2810
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 0.7348294843816162,
|
| 1981 |
+
"grad_norm": 14.585554122924805,
|
| 1982 |
+
"learning_rate": 1.7326626418597986e-06,
|
| 1983 |
+
"loss": 3.5593,
|
| 1984 |
+
"step": 2820
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 0.7374352626950262,
|
| 1988 |
+
"grad_norm": 17.731149673461914,
|
| 1989 |
+
"learning_rate": 1.7008251183811053e-06,
|
| 1990 |
+
"loss": 3.4138,
|
| 1991 |
+
"step": 2830
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 0.7400410410084363,
|
| 1995 |
+
"grad_norm": 13.647686004638672,
|
| 1996 |
+
"learning_rate": 1.6692227655757615e-06,
|
| 1997 |
+
"loss": 3.4228,
|
| 1998 |
+
"step": 2840
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 0.7426468193218462,
|
| 2002 |
+
"grad_norm": 15.621156692504883,
|
| 2003 |
+
"learning_rate": 1.6378578361120444e-06,
|
| 2004 |
+
"loss": 3.4514,
|
| 2005 |
+
"step": 2850
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 0.7452525976352562,
|
| 2009 |
+
"grad_norm": 15.368025779724121,
|
| 2010 |
+
"learning_rate": 1.606732565734296e-06,
|
| 2011 |
+
"loss": 3.6202,
|
| 2012 |
+
"step": 2860
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 0.7478583759486662,
|
| 2016 |
+
"grad_norm": 11.095398902893066,
|
| 2017 |
+
"learning_rate": 1.5758491731035618e-06,
|
| 2018 |
+
"loss": 3.4014,
|
| 2019 |
+
"step": 2870
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 0.7504641542620761,
|
| 2023 |
+
"grad_norm": 14.120464324951172,
|
| 2024 |
+
"learning_rate": 1.5452098596394427e-06,
|
| 2025 |
+
"loss": 3.5584,
|
| 2026 |
+
"step": 2880
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 0.7530699325754862,
|
| 2030 |
+
"grad_norm": 15.765480041503906,
|
| 2031 |
+
"learning_rate": 1.5148168093631639e-06,
|
| 2032 |
+
"loss": 3.5786,
|
| 2033 |
+
"step": 2890
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 0.7556757108888962,
|
| 2037 |
+
"grad_norm": 13.703192710876465,
|
| 2038 |
+
"learning_rate": 1.4846721887419063e-06,
|
| 2039 |
+
"loss": 3.333,
|
| 2040 |
+
"step": 2900
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 0.7582814892023061,
|
| 2044 |
+
"grad_norm": 14.422611236572266,
|
| 2045 |
+
"learning_rate": 1.454778146534368e-06,
|
| 2046 |
+
"loss": 3.4666,
|
| 2047 |
+
"step": 2910
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 0.7608872675157161,
|
| 2051 |
+
"grad_norm": 11.853596687316895,
|
| 2052 |
+
"learning_rate": 1.4251368136376053e-06,
|
| 2053 |
+
"loss": 3.4863,
|
| 2054 |
+
"step": 2920
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 0.7634930458291261,
|
| 2058 |
+
"grad_norm": 15.993678092956543,
|
| 2059 |
+
"learning_rate": 1.3957503029351288e-06,
|
| 2060 |
+
"loss": 3.6314,
|
| 2061 |
+
"step": 2930
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 0.766098824142536,
|
| 2065 |
+
"grad_norm": 14.112190246582031,
|
| 2066 |
+
"learning_rate": 1.3666207091463057e-06,
|
| 2067 |
+
"loss": 3.543,
|
| 2068 |
+
"step": 2940
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 0.7687046024559461,
|
| 2072 |
+
"grad_norm": 14.038150787353516,
|
| 2073 |
+
"learning_rate": 1.3377501086770322e-06,
|
| 2074 |
+
"loss": 3.3686,
|
| 2075 |
+
"step": 2950
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 0.7713103807693561,
|
| 2079 |
+
"grad_norm": 9.788325309753418,
|
| 2080 |
+
"learning_rate": 1.3091405594717348e-06,
|
| 2081 |
+
"loss": 3.3148,
|
| 2082 |
+
"step": 2960
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 0.773916159082766,
|
| 2086 |
+
"grad_norm": 12.188491821289062,
|
| 2087 |
+
"learning_rate": 1.2807941008666668e-06,
|
| 2088 |
+
"loss": 3.3429,
|
| 2089 |
+
"step": 2970
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 0.776521937396176,
|
| 2093 |
+
"grad_norm": 14.495473861694336,
|
| 2094 |
+
"learning_rate": 1.2527127534445516e-06,
|
| 2095 |
+
"loss": 3.6177,
|
| 2096 |
+
"step": 2980
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 0.779127715709586,
|
| 2100 |
+
"grad_norm": 15.1799898147583,
|
| 2101 |
+
"learning_rate": 1.2248985188905404e-06,
|
| 2102 |
+
"loss": 3.421,
|
| 2103 |
+
"step": 2990
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 0.781733494022996,
|
| 2107 |
+
"grad_norm": 17.934301376342773,
|
| 2108 |
+
"learning_rate": 1.1973533798495412e-06,
|
| 2109 |
+
"loss": 3.6812,
|
| 2110 |
+
"step": 3000
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 0.784339272336406,
|
| 2114 |
+
"grad_norm": 14.297499656677246,
|
| 2115 |
+
"learning_rate": 1.1700792997848798e-06,
|
| 2116 |
+
"loss": 3.5429,
|
| 2117 |
+
"step": 3010
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 0.786945050649816,
|
| 2121 |
+
"grad_norm": 15.446012496948242,
|
| 2122 |
+
"learning_rate": 1.1430782228383535e-06,
|
| 2123 |
+
"loss": 3.6879,
|
| 2124 |
+
"step": 3020
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 0.7895508289632259,
|
| 2128 |
+
"grad_norm": 12.20955753326416,
|
| 2129 |
+
"learning_rate": 1.1163520736916383e-06,
|
| 2130 |
+
"loss": 3.4111,
|
| 2131 |
+
"step": 3030
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 0.792156607276636,
|
| 2135 |
+
"grad_norm": 13.675918579101562,
|
| 2136 |
+
"learning_rate": 1.0899027574291e-06,
|
| 2137 |
+
"loss": 3.4263,
|
| 2138 |
+
"step": 3040
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 0.794762385590046,
|
| 2142 |
+
"grad_norm": 13.190848350524902,
|
| 2143 |
+
"learning_rate": 1.0637321594019995e-06,
|
| 2144 |
+
"loss": 3.5549,
|
| 2145 |
+
"step": 3050
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 0.7973681639034559,
|
| 2149 |
+
"grad_norm": 16.32231330871582,
|
| 2150 |
+
"learning_rate": 1.037842145094094e-06,
|
| 2151 |
+
"loss": 3.5263,
|
| 2152 |
+
"step": 3060
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 0.7999739422168659,
|
| 2156 |
+
"grad_norm": 16.69465446472168,
|
| 2157 |
+
"learning_rate": 1.0122345599886708e-06,
|
| 2158 |
+
"loss": 3.4501,
|
| 2159 |
+
"step": 3070
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 0.8025797205302759,
|
| 2163 |
+
"grad_norm": 18.10247039794922,
|
| 2164 |
+
"learning_rate": 9.869112294369881e-07,
|
| 2165 |
+
"loss": 3.5796,
|
| 2166 |
+
"step": 3080
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 0.8051854988436858,
|
| 2170 |
+
"grad_norm": 14.562990188598633,
|
| 2171 |
+
"learning_rate": 9.618739585281734e-07,
|
| 2172 |
+
"loss": 3.3573,
|
| 2173 |
+
"step": 3090
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 0.8077912771570959,
|
| 2177 |
+
"grad_norm": 14.317696571350098,
|
| 2178 |
+
"learning_rate": 9.371245319605404e-07,
|
| 2179 |
+
"loss": 3.3424,
|
| 2180 |
+
"step": 3100
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 0.8103970554705059,
|
| 2184 |
+
"grad_norm": 12.70585823059082,
|
| 2185 |
+
"learning_rate": 9.126647139143857e-07,
|
| 2186 |
+
"loss": 3.4635,
|
| 2187 |
+
"step": 3110
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 0.8130028337839158,
|
| 2191 |
+
"grad_norm": 15.492018699645996,
|
| 2192 |
+
"learning_rate": 8.884962479262227e-07,
|
| 2193 |
+
"loss": 3.5435,
|
| 2194 |
+
"step": 3120
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 0.8156086120973258,
|
| 2198 |
+
"grad_norm": 14.00477409362793,
|
| 2199 |
+
"learning_rate": 8.646208567645109e-07,
|
| 2200 |
+
"loss": 3.4005,
|
| 2201 |
+
"step": 3130
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 0.8182143904107358,
|
| 2205 |
+
"grad_norm": 16.292644500732422,
|
| 2206 |
+
"learning_rate": 8.410402423068448e-07,
|
| 2207 |
+
"loss": 3.5322,
|
| 2208 |
+
"step": 3140
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 0.8208201687241458,
|
| 2212 |
+
"grad_norm": 15.230997085571289,
|
| 2213 |
+
"learning_rate": 8.177560854186473e-07,
|
| 2214 |
+
"loss": 3.4093,
|
| 2215 |
+
"step": 3150
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 0.8234259470375558,
|
| 2219 |
+
"grad_norm": 14.827224731445312,
|
| 2220 |
+
"learning_rate": 7.947700458333507e-07,
|
| 2221 |
+
"loss": 3.4979,
|
| 2222 |
+
"step": 3160
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 0.8260317253509658,
|
| 2226 |
+
"grad_norm": 12.555737495422363,
|
| 2227 |
+
"learning_rate": 7.720837620340932e-07,
|
| 2228 |
+
"loss": 3.5504,
|
| 2229 |
+
"step": 3170
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 0.8286375036643757,
|
| 2233 |
+
"grad_norm": 15.211166381835938,
|
| 2234 |
+
"learning_rate": 7.496988511369174e-07,
|
| 2235 |
+
"loss": 3.4964,
|
| 2236 |
+
"step": 3180
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 0.8312432819777857,
|
| 2240 |
+
"grad_norm": 15.974442481994629,
|
| 2241 |
+
"learning_rate": 7.276169087755098e-07,
|
| 2242 |
+
"loss": 3.4433,
|
| 2243 |
+
"step": 3190
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 0.8338490602911958,
|
| 2247 |
+
"grad_norm": 19.52552604675293,
|
| 2248 |
+
"learning_rate": 7.058395089874492e-07,
|
| 2249 |
+
"loss": 3.4431,
|
| 2250 |
+
"step": 3200
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 0.8364548386046057,
|
| 2254 |
+
"grad_norm": 13.694509506225586,
|
| 2255 |
+
"learning_rate": 6.843682041020183e-07,
|
| 2256 |
+
"loss": 3.393,
|
| 2257 |
+
"step": 3210
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 0.8390606169180157,
|
| 2261 |
+
"grad_norm": 13.908066749572754,
|
| 2262 |
+
"learning_rate": 6.632045246295454e-07,
|
| 2263 |
+
"loss": 3.3117,
|
| 2264 |
+
"step": 3220
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 0.8416663952314257,
|
| 2268 |
+
"grad_norm": 15.066481590270996,
|
| 2269 |
+
"learning_rate": 6.423499791523047e-07,
|
| 2270 |
+
"loss": 3.4593,
|
| 2271 |
+
"step": 3230
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 0.8442721735448356,
|
| 2275 |
+
"grad_norm": 15.917520523071289,
|
| 2276 |
+
"learning_rate": 6.21806054216989e-07,
|
| 2277 |
+
"loss": 3.6252,
|
| 2278 |
+
"step": 3240
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 0.8468779518582457,
|
| 2282 |
+
"grad_norm": 14.044636726379395,
|
| 2283 |
+
"learning_rate": 6.015742142287378e-07,
|
| 2284 |
+
"loss": 3.4254,
|
| 2285 |
+
"step": 3250
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 0.8494837301716557,
|
| 2289 |
+
"grad_norm": 12.949217796325684,
|
| 2290 |
+
"learning_rate": 5.816559013467605e-07,
|
| 2291 |
+
"loss": 3.3669,
|
| 2292 |
+
"step": 3260
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 0.8520895084850656,
|
| 2296 |
+
"grad_norm": 12.033577919006348,
|
| 2297 |
+
"learning_rate": 5.620525353815292e-07,
|
| 2298 |
+
"loss": 3.4006,
|
| 2299 |
+
"step": 3270
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 0.8546952867984756,
|
| 2303 |
+
"grad_norm": 15.906982421875,
|
| 2304 |
+
"learning_rate": 5.427655136935805e-07,
|
| 2305 |
+
"loss": 3.5475,
|
| 2306 |
+
"step": 3280
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 0.8573010651118856,
|
| 2310 |
+
"grad_norm": 16.381826400756836,
|
| 2311 |
+
"learning_rate": 5.237962110938998e-07,
|
| 2312 |
+
"loss": 3.4749,
|
| 2313 |
+
"step": 3290
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 0.8599068434252956,
|
| 2317 |
+
"grad_norm": 14.224139213562012,
|
| 2318 |
+
"learning_rate": 5.051459797459296e-07,
|
| 2319 |
+
"loss": 3.2448,
|
| 2320 |
+
"step": 3300
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 0.8625126217387056,
|
| 2324 |
+
"grad_norm": 15.212875366210938,
|
| 2325 |
+
"learning_rate": 4.868161490691848e-07,
|
| 2326 |
+
"loss": 3.2814,
|
| 2327 |
+
"step": 3310
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 0.8651184000521156,
|
| 2331 |
+
"grad_norm": 13.000926971435547,
|
| 2332 |
+
"learning_rate": 4.688080256444827e-07,
|
| 2333 |
+
"loss": 3.2083,
|
| 2334 |
+
"step": 3320
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 0.8677241783655255,
|
| 2338 |
+
"grad_norm": 14.853813171386719,
|
| 2339 |
+
"learning_rate": 4.5112289312081834e-07,
|
| 2340 |
+
"loss": 3.2162,
|
| 2341 |
+
"step": 3330
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 0.8703299566789355,
|
| 2345 |
+
"grad_norm": 15.472539901733398,
|
| 2346 |
+
"learning_rate": 4.3376201212385393e-07,
|
| 2347 |
+
"loss": 3.4829,
|
| 2348 |
+
"step": 3340
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 0.8729357349923456,
|
| 2352 |
+
"grad_norm": 21.189714431762695,
|
| 2353 |
+
"learning_rate": 4.167266201660636e-07,
|
| 2354 |
+
"loss": 3.3972,
|
| 2355 |
+
"step": 3350
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 0.8755415133057555,
|
| 2359 |
+
"grad_norm": 13.189949035644531,
|
| 2360 |
+
"learning_rate": 4.0001793155852396e-07,
|
| 2361 |
+
"loss": 3.2157,
|
| 2362 |
+
"step": 3360
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 0.8781472916191655,
|
| 2366 |
+
"grad_norm": 11.203957557678223,
|
| 2367 |
+
"learning_rate": 3.8363713732435084e-07,
|
| 2368 |
+
"loss": 3.4225,
|
| 2369 |
+
"step": 3370
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 0.8807530699325755,
|
| 2373 |
+
"grad_norm": 14.881497383117676,
|
| 2374 |
+
"learning_rate": 3.6758540511380505e-07,
|
| 2375 |
+
"loss": 3.348,
|
| 2376 |
+
"step": 3380
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 0.8833588482459854,
|
| 2380 |
+
"grad_norm": 14.552695274353027,
|
| 2381 |
+
"learning_rate": 3.518638791210599e-07,
|
| 2382 |
+
"loss": 3.4734,
|
| 2383 |
+
"step": 3390
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 0.8859646265593955,
|
| 2387 |
+
"grad_norm": 14.461812973022461,
|
| 2388 |
+
"learning_rate": 3.3647368000263745e-07,
|
| 2389 |
+
"loss": 3.3613,
|
| 2390 |
+
"step": 3400
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 0.8885704048728055,
|
| 2394 |
+
"grad_norm": 13.983736991882324,
|
| 2395 |
+
"learning_rate": 3.214159047975324e-07,
|
| 2396 |
+
"loss": 3.4505,
|
| 2397 |
+
"step": 3410
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 0.8911761831862154,
|
| 2401 |
+
"grad_norm": 14.170096397399902,
|
| 2402 |
+
"learning_rate": 3.0669162684900555e-07,
|
| 2403 |
+
"loss": 3.3938,
|
| 2404 |
+
"step": 3420
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 0.8937819614996254,
|
| 2408 |
+
"grad_norm": 13.338794708251953,
|
| 2409 |
+
"learning_rate": 2.923018957280843e-07,
|
| 2410 |
+
"loss": 3.4493,
|
| 2411 |
+
"step": 3430
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 0.8963877398130354,
|
| 2415 |
+
"grad_norm": 14.849313735961914,
|
| 2416 |
+
"learning_rate": 2.782477371587361e-07,
|
| 2417 |
+
"loss": 3.3652,
|
| 2418 |
+
"step": 3440
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 0.8989935181264453,
|
| 2422 |
+
"grad_norm": 14.38377571105957,
|
| 2423 |
+
"learning_rate": 2.6453015294476247e-07,
|
| 2424 |
+
"loss": 3.4273,
|
| 2425 |
+
"step": 3450
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 0.9015992964398554,
|
| 2429 |
+
"grad_norm": 11.596222877502441,
|
| 2430 |
+
"learning_rate": 2.51150120898383e-07,
|
| 2431 |
+
"loss": 3.4077,
|
| 2432 |
+
"step": 3460
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 0.9042050747532654,
|
| 2436 |
+
"grad_norm": 13.537557601928711,
|
| 2437 |
+
"learning_rate": 2.3810859477053972e-07,
|
| 2438 |
+
"loss": 3.3455,
|
| 2439 |
+
"step": 3470
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 0.9068108530666753,
|
| 2443 |
+
"grad_norm": 14.95813274383545,
|
| 2444 |
+
"learning_rate": 2.2540650418290565e-07,
|
| 2445 |
+
"loss": 3.361,
|
| 2446 |
+
"step": 3480
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 0.9094166313800853,
|
| 2450 |
+
"grad_norm": 15.819819450378418,
|
| 2451 |
+
"learning_rate": 2.130447545616282e-07,
|
| 2452 |
+
"loss": 3.494,
|
| 2453 |
+
"step": 3490
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 0.9120224096934954,
|
| 2457 |
+
"grad_norm": 12.460811614990234,
|
| 2458 |
+
"learning_rate": 2.0102422707278135e-07,
|
| 2459 |
+
"loss": 3.2347,
|
| 2460 |
+
"step": 3500
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 0.9146281880069053,
|
| 2464 |
+
"grad_norm": 13.781402587890625,
|
| 2465 |
+
"learning_rate": 1.893457785595604e-07,
|
| 2466 |
+
"loss": 3.3209,
|
| 2467 |
+
"step": 3510
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 0.9172339663203153,
|
| 2471 |
+
"grad_norm": 13.93978214263916,
|
| 2472 |
+
"learning_rate": 1.7801024148120018e-07,
|
| 2473 |
+
"loss": 3.213,
|
| 2474 |
+
"step": 3520
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 0.9198397446337253,
|
| 2478 |
+
"grad_norm": 16.11202049255371,
|
| 2479 |
+
"learning_rate": 1.6701842385363932e-07,
|
| 2480 |
+
"loss": 3.1792,
|
| 2481 |
+
"step": 3530
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 0.9224455229471352,
|
| 2485 |
+
"grad_norm": 15.065796852111816,
|
| 2486 |
+
"learning_rate": 1.5637110919192289e-07,
|
| 2487 |
+
"loss": 3.2897,
|
| 2488 |
+
"step": 3540
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 0.9250513012605452,
|
| 2492 |
+
"grad_norm": 14.395028114318848,
|
| 2493 |
+
"learning_rate": 1.4606905645434876e-07,
|
| 2494 |
+
"loss": 3.2679,
|
| 2495 |
+
"step": 3550
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 0.9276570795739553,
|
| 2499 |
+
"grad_norm": 15.025830268859863,
|
| 2500 |
+
"learning_rate": 1.3611299998837367e-07,
|
| 2501 |
+
"loss": 3.2002,
|
| 2502 |
+
"step": 3560
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 0.9302628578873652,
|
| 2506 |
+
"grad_norm": 13.283101081848145,
|
| 2507 |
+
"learning_rate": 1.265036494782629e-07,
|
| 2508 |
+
"loss": 3.3427,
|
| 2509 |
+
"step": 3570
|
| 2510 |
+
},
|
| 2511 |
+
{
|
| 2512 |
+
"epoch": 0.9328686362007752,
|
| 2513 |
+
"grad_norm": 12.859179496765137,
|
| 2514 |
+
"learning_rate": 1.1724168989450391e-07,
|
| 2515 |
+
"loss": 3.277,
|
| 2516 |
+
"step": 3580
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 0.9354744145141852,
|
| 2520 |
+
"grad_norm": 13.371453285217285,
|
| 2521 |
+
"learning_rate": 1.0832778144498291e-07,
|
| 2522 |
+
"loss": 3.218,
|
| 2523 |
+
"step": 3590
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 0.9380801928275951,
|
| 2527 |
+
"grad_norm": 13.968640327453613,
|
| 2528 |
+
"learning_rate": 9.976255952792168e-08,
|
| 2529 |
+
"loss": 3.1963,
|
| 2530 |
+
"step": 3600
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 0.9406859711410052,
|
| 2534 |
+
"grad_norm": 12.617493629455566,
|
| 2535 |
+
"learning_rate": 9.15466346865851e-08,
|
| 2536 |
+
"loss": 3.2342,
|
| 2537 |
+
"step": 3610
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 0.9432917494544152,
|
| 2541 |
+
"grad_norm": 13.56783676147461,
|
| 2542 |
+
"learning_rate": 8.368059256576244e-08,
|
| 2543 |
+
"loss": 3.3285,
|
| 2544 |
+
"step": 3620
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 0.9458975277678251,
|
| 2548 |
+
"grad_norm": 14.597091674804688,
|
| 2549 |
+
"learning_rate": 7.616499387001985e-08,
|
| 2550 |
+
"loss": 3.4222,
|
| 2551 |
+
"step": 3630
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 0.9485033060812351,
|
| 2555 |
+
"grad_norm": 12.133713722229004,
|
| 2556 |
+
"learning_rate": 6.900037432373441e-08,
|
| 2557 |
+
"loss": 3.3353,
|
| 2558 |
+
"step": 3640
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 0.9511090843946451,
|
| 2562 |
+
"grad_norm": 16.943021774291992,
|
| 2563 |
+
"learning_rate": 6.21872446329036e-08,
|
| 2564 |
+
"loss": 3.4428,
|
| 2565 |
+
"step": 3650
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 0.9537148627080552,
|
| 2569 |
+
"grad_norm": 16.915424346923828,
|
| 2570 |
+
"learning_rate": 5.572609044874666e-08,
|
| 2571 |
+
"loss": 3.4972,
|
| 2572 |
+
"step": 3660
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 0.9563206410214651,
|
| 2576 |
+
"grad_norm": 15.0619478225708,
|
| 2577 |
+
"learning_rate": 4.961737233307895e-08,
|
| 2578 |
+
"loss": 3.2978,
|
| 2579 |
+
"step": 3670
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 0.9589264193348751,
|
| 2583 |
+
"grad_norm": 12.197420120239258,
|
| 2584 |
+
"learning_rate": 4.3861525725490406e-08,
|
| 2585 |
+
"loss": 3.3231,
|
| 2586 |
+
"step": 3680
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 0.9615321976482851,
|
| 2590 |
+
"grad_norm": 15.157994270324707,
|
| 2591 |
+
"learning_rate": 3.8458960912300946e-08,
|
| 2592 |
+
"loss": 3.5443,
|
| 2593 |
+
"step": 3690
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 0.964137975961695,
|
| 2597 |
+
"grad_norm": 16.018217086791992,
|
| 2598 |
+
"learning_rate": 3.341006299731664e-08,
|
| 2599 |
+
"loss": 3.4109,
|
| 2600 |
+
"step": 3700
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 0.9667437542751051,
|
| 2604 |
+
"grad_norm": 14.247093200683594,
|
| 2605 |
+
"learning_rate": 2.871519187437999e-08,
|
| 2606 |
+
"loss": 3.4134,
|
| 2607 |
+
"step": 3710
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 0.9693495325885151,
|
| 2611 |
+
"grad_norm": 12.761212348937988,
|
| 2612 |
+
"learning_rate": 2.437468220171324e-08,
|
| 2613 |
+
"loss": 3.3059,
|
| 2614 |
+
"step": 3720
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 0.971955310901925,
|
| 2618 |
+
"grad_norm": 13.68462085723877,
|
| 2619 |
+
"learning_rate": 2.0388843378065792e-08,
|
| 2620 |
+
"loss": 3.4214,
|
| 2621 |
+
"step": 3730
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 0.974561089215335,
|
| 2625 |
+
"grad_norm": 12.86118221282959,
|
| 2626 |
+
"learning_rate": 1.6757959520659616e-08,
|
| 2627 |
+
"loss": 3.2223,
|
| 2628 |
+
"step": 3740
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 0.977166867528745,
|
| 2632 |
+
"grad_norm": 14.72098445892334,
|
| 2633 |
+
"learning_rate": 1.3482289444934903e-08,
|
| 2634 |
+
"loss": 3.4439,
|
| 2635 |
+
"step": 3750
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 0.979772645842155,
|
| 2639 |
+
"grad_norm": 16.50194549560547,
|
| 2640 |
+
"learning_rate": 1.0562066646103707e-08,
|
| 2641 |
+
"loss": 3.3943,
|
| 2642 |
+
"step": 3760
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 0.982378424155565,
|
| 2646 |
+
"grad_norm": 11.808096885681152,
|
| 2647 |
+
"learning_rate": 7.997499282504373e-09,
|
| 2648 |
+
"loss": 3.2021,
|
| 2649 |
+
"step": 3770
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 0.984984202468975,
|
| 2653 |
+
"grad_norm": 12.357420921325684,
|
| 2654 |
+
"learning_rate": 5.788770160764512e-09,
|
| 2655 |
+
"loss": 3.3199,
|
| 2656 |
+
"step": 3780
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 0.9875899807823849,
|
| 2660 |
+
"grad_norm": 12.219795227050781,
|
| 2661 |
+
"learning_rate": 3.93603672277032e-09,
|
| 2662 |
+
"loss": 3.2891,
|
| 2663 |
+
"step": 3790
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 0.9901957590957949,
|
| 2667 |
+
"grad_norm": 12.849437713623047,
|
| 2668 |
+
"learning_rate": 2.4394310344422188e-09,
|
| 2669 |
+
"loss": 3.2032,
|
| 2670 |
+
"step": 3800
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 0.992801537409205,
|
| 2674 |
+
"grad_norm": 11.828692436218262,
|
| 2675 |
+
"learning_rate": 1.299059776324052e-09,
|
| 2676 |
+
"loss": 3.5092,
|
| 2677 |
+
"step": 3810
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 0.9954073157226149,
|
| 2681 |
+
"grad_norm": 15.673126220703125,
|
| 2682 |
+
"learning_rate": 5.150042359752805e-10,
|
| 2683 |
+
"loss": 3.2089,
|
| 2684 |
+
"step": 3820
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 0.9980130940360249,
|
| 2688 |
+
"grad_norm": 11.875957489013672,
|
| 2689 |
+
"learning_rate": 8.732030217895037e-11,
|
| 2690 |
+
"loss": 3.2474,
|
| 2691 |
+
"step": 3830
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 0.9998371388554119,
|
| 2695 |
+
"step": 3837,
|
| 2696 |
+
"total_flos": 5.861244180679046e+19,
|
| 2697 |
+
"train_loss": 4.158595516869945,
|
| 2698 |
+
"train_runtime": 42770.6847,
|
| 2699 |
+
"train_samples_per_second": 5.742,
|
| 2700 |
+
"train_steps_per_second": 0.09
|
| 2701 |
+
}
|
| 2702 |
+
],
|
| 2703 |
+
"logging_steps": 10,
|
| 2704 |
+
"max_steps": 3837,
|
| 2705 |
+
"num_input_tokens_seen": 0,
|
| 2706 |
+
"num_train_epochs": 1,
|
| 2707 |
+
"save_steps": 1000,
|
| 2708 |
+
"stateful_callbacks": {
|
| 2709 |
+
"TrainerControl": {
|
| 2710 |
+
"args": {
|
| 2711 |
+
"should_epoch_stop": false,
|
| 2712 |
+
"should_evaluate": false,
|
| 2713 |
+
"should_log": false,
|
| 2714 |
+
"should_save": true,
|
| 2715 |
+
"should_training_stop": true
|
| 2716 |
+
},
|
| 2717 |
+
"attributes": {}
|
| 2718 |
+
}
|
| 2719 |
+
},
|
| 2720 |
+
"total_flos": 5.861244180679046e+19,
|
| 2721 |
+
"train_batch_size": 1,
|
| 2722 |
+
"trial_name": null,
|
| 2723 |
+
"trial_params": null
|
| 2724 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:015c18036cc2f7bcebd89af1f86068518a5c39a13edd019020ff53ff0a120843
|
| 3 |
+
size 7288
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|