Training in progress, step 2753, checkpoint
Browse files- checkpoint-2753/chat_template.jinja +11 -0
- checkpoint-2753/config.json +108 -0
- checkpoint-2753/generation_config.json +10 -0
- checkpoint-2753/model.safetensors +3 -0
- checkpoint-2753/optimizer.pt +3 -0
- checkpoint-2753/rng_state_0.pth +3 -0
- checkpoint-2753/rng_state_1.pth +3 -0
- checkpoint-2753/scheduler.pt +3 -0
- checkpoint-2753/tokenizer.json +3 -0
- checkpoint-2753/tokenizer_config.json +307 -0
- checkpoint-2753/trainer_state.json +1959 -0
- checkpoint-2753/training_args.bin +3 -0
checkpoint-2753/chat_template.jinja
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% for message in messages %}
|
| 2 |
+
{{ '<|im_start|>' + message['role'] + '
|
| 3 |
+
'
|
| 4 |
+
+ message['content'].strip()
|
| 5 |
+
+ '<|im_end|>
|
| 6 |
+
' }}
|
| 7 |
+
{% endfor %}
|
| 8 |
+
{% if add_generation_prompt %}
|
| 9 |
+
{{ '<|im_start|>assistant
|
| 10 |
+
' }}
|
| 11 |
+
{% endif %}
|
checkpoint-2753/config.json
ADDED
|
@@ -0,0 +1,108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"bos_token_id": 248044,
|
| 6 |
+
"dtype": "bfloat16",
|
| 7 |
+
"eos_token_id": 248044,
|
| 8 |
+
"image_token_id": 248056,
|
| 9 |
+
"model_name": "qwen36-dpo",
|
| 10 |
+
"model_type": "qwen3_5",
|
| 11 |
+
"pad_token_id": 248077,
|
| 12 |
+
"text_config": {
|
| 13 |
+
"attention_bias": false,
|
| 14 |
+
"attention_dropout": 0.0,
|
| 15 |
+
"attn_output_gate": true,
|
| 16 |
+
"bos_token_id": null,
|
| 17 |
+
"dtype": "bfloat16",
|
| 18 |
+
"eos_token_id": 248044,
|
| 19 |
+
"full_attention_interval": 4,
|
| 20 |
+
"head_dim": 256,
|
| 21 |
+
"hidden_act": "silu",
|
| 22 |
+
"hidden_size": 2048,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 6144,
|
| 25 |
+
"layer_types": [
|
| 26 |
+
"linear_attention",
|
| 27 |
+
"linear_attention",
|
| 28 |
+
"linear_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"linear_attention",
|
| 31 |
+
"linear_attention",
|
| 32 |
+
"linear_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"linear_attention",
|
| 35 |
+
"linear_attention",
|
| 36 |
+
"linear_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"linear_attention",
|
| 39 |
+
"linear_attention",
|
| 40 |
+
"linear_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"linear_attention",
|
| 43 |
+
"linear_attention",
|
| 44 |
+
"linear_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"linear_attention",
|
| 47 |
+
"linear_attention",
|
| 48 |
+
"linear_attention",
|
| 49 |
+
"full_attention"
|
| 50 |
+
],
|
| 51 |
+
"linear_conv_kernel_dim": 4,
|
| 52 |
+
"linear_key_head_dim": 128,
|
| 53 |
+
"linear_num_key_heads": 16,
|
| 54 |
+
"linear_num_value_heads": 16,
|
| 55 |
+
"linear_value_head_dim": 128,
|
| 56 |
+
"mamba_ssm_dtype": "float32",
|
| 57 |
+
"max_position_embeddings": 262144,
|
| 58 |
+
"mlp_only_layers": [],
|
| 59 |
+
"model_type": "qwen3_5_text",
|
| 60 |
+
"mtp_num_hidden_layers": 1,
|
| 61 |
+
"mtp_use_dedicated_embeddings": false,
|
| 62 |
+
"num_attention_heads": 8,
|
| 63 |
+
"num_hidden_layers": 24,
|
| 64 |
+
"num_key_value_heads": 2,
|
| 65 |
+
"pad_token_id": null,
|
| 66 |
+
"partial_rotary_factor": 0.25,
|
| 67 |
+
"rms_norm_eps": 1e-06,
|
| 68 |
+
"rope_parameters": {
|
| 69 |
+
"mrope_interleaved": true,
|
| 70 |
+
"mrope_section": [
|
| 71 |
+
11,
|
| 72 |
+
11,
|
| 73 |
+
10
|
| 74 |
+
],
|
| 75 |
+
"partial_rotary_factor": 0.25,
|
| 76 |
+
"rope_theta": 10000000,
|
| 77 |
+
"rope_type": "default"
|
| 78 |
+
},
|
| 79 |
+
"tie_word_embeddings": true,
|
| 80 |
+
"use_cache": true,
|
| 81 |
+
"vocab_size": 248320
|
| 82 |
+
},
|
| 83 |
+
"tie_word_embeddings": true,
|
| 84 |
+
"transformers_version": "5.5.0",
|
| 85 |
+
"unsloth_fixed": true,
|
| 86 |
+
"unsloth_version": "2026.6.1",
|
| 87 |
+
"use_cache": false,
|
| 88 |
+
"video_token_id": 248057,
|
| 89 |
+
"vision_config": {
|
| 90 |
+
"deepstack_visual_indexes": [],
|
| 91 |
+
"depth": 24,
|
| 92 |
+
"dtype": "bfloat16",
|
| 93 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 94 |
+
"hidden_size": 1024,
|
| 95 |
+
"in_channels": 3,
|
| 96 |
+
"initializer_range": 0.02,
|
| 97 |
+
"intermediate_size": 4096,
|
| 98 |
+
"model_type": "qwen3_5",
|
| 99 |
+
"num_heads": 16,
|
| 100 |
+
"num_position_embeddings": 2304,
|
| 101 |
+
"out_hidden_size": 2048,
|
| 102 |
+
"patch_size": 16,
|
| 103 |
+
"spatial_merge_size": 2,
|
| 104 |
+
"temporal_patch_size": 2
|
| 105 |
+
},
|
| 106 |
+
"vision_end_token_id": 248054,
|
| 107 |
+
"vision_start_token_id": 248053
|
| 108 |
+
}
|
checkpoint-2753/generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 248044,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
248044
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 248077,
|
| 8 |
+
"transformers_version": "5.5.0",
|
| 9 |
+
"use_cache": true
|
| 10 |
+
}
|
checkpoint-2753/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e6e8dc2e16ac4e8291fca369d074a6805a5ee6939af0bcdcdc192dbe2a0bd47
|
| 3 |
+
size 4426572920
|
checkpoint-2753/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1dd6796bba1d03bd0910182a393d0eb3c7cb42244a5fefb51eb77a2acc9f4d71
|
| 3 |
+
size 6858880301
|
checkpoint-2753/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4dd7671ce88d469c49c0530724ac76b2306574002d1ecd1ca9294e41621fd96a
|
| 3 |
+
size 14917
|
checkpoint-2753/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3246ef1170ccca541a03b89ad6f20e01c51eb6834a2c2211c78c71c70f896879
|
| 3 |
+
size 14917
|
checkpoint-2753/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20b8a802845fbe6f542c0712299240a7a8f0533284f491526e4ae12d239c10f6
|
| 3 |
+
size 1465
|
checkpoint-2753/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e4440d1bffd87b24e72c2a71573d683b92155d0880898dee70812112387931d
|
| 3 |
+
size 19990631
|
checkpoint-2753/tokenizer_config.json
ADDED
|
@@ -0,0 +1,307 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": "<|endoftext|>",
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|endoftext|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"is_local": true,
|
| 13 |
+
"model_max_length": 262144,
|
| 14 |
+
"model_specific_special_tokens": {
|
| 15 |
+
"audio_bos_token": "<|audio_start|>",
|
| 16 |
+
"audio_eos_token": "<|audio_end|>",
|
| 17 |
+
"audio_token": "<|audio_pad|>",
|
| 18 |
+
"image_token": "<|image_pad|>",
|
| 19 |
+
"video_token": "<|video_pad|>",
|
| 20 |
+
"vision_bos_token": "<|vision_start|>",
|
| 21 |
+
"vision_eos_token": "<|vision_end|>"
|
| 22 |
+
},
|
| 23 |
+
"pad_token": "<|PAD_TOKEN|>",
|
| 24 |
+
"padding_side": "left",
|
| 25 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 26 |
+
"processor_class": "Qwen3VLProcessor",
|
| 27 |
+
"split_special_tokens": false,
|
| 28 |
+
"tokenizer_class": "TokenizersBackend",
|
| 29 |
+
"unk_token": null,
|
| 30 |
+
"video_token": "<|video_pad|>",
|
| 31 |
+
"vision_bos_token": "<|vision_start|>",
|
| 32 |
+
"vision_eos_token": "<|vision_end|>",
|
| 33 |
+
"added_tokens_decoder": {
|
| 34 |
+
"248044": {
|
| 35 |
+
"content": "<|endoftext|>",
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"special": true
|
| 41 |
+
},
|
| 42 |
+
"248045": {
|
| 43 |
+
"content": "<|im_start|>",
|
| 44 |
+
"single_word": false,
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"rstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"special": true
|
| 49 |
+
},
|
| 50 |
+
"248046": {
|
| 51 |
+
"content": "<|im_end|>",
|
| 52 |
+
"single_word": false,
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"rstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"special": true
|
| 57 |
+
},
|
| 58 |
+
"248047": {
|
| 59 |
+
"content": "<|object_ref_start|>",
|
| 60 |
+
"single_word": false,
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"rstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"special": true
|
| 65 |
+
},
|
| 66 |
+
"248048": {
|
| 67 |
+
"content": "<|object_ref_end|>",
|
| 68 |
+
"single_word": false,
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"rstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"special": true
|
| 73 |
+
},
|
| 74 |
+
"248049": {
|
| 75 |
+
"content": "<|box_start|>",
|
| 76 |
+
"single_word": false,
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"rstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"special": true
|
| 81 |
+
},
|
| 82 |
+
"248050": {
|
| 83 |
+
"content": "<|box_end|>",
|
| 84 |
+
"single_word": false,
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"rstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"special": true
|
| 89 |
+
},
|
| 90 |
+
"248051": {
|
| 91 |
+
"content": "<|quad_start|>",
|
| 92 |
+
"single_word": false,
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"rstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"special": true
|
| 97 |
+
},
|
| 98 |
+
"248052": {
|
| 99 |
+
"content": "<|quad_end|>",
|
| 100 |
+
"single_word": false,
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"rstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"special": true
|
| 105 |
+
},
|
| 106 |
+
"248053": {
|
| 107 |
+
"content": "<|vision_start|>",
|
| 108 |
+
"single_word": false,
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"rstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"special": true
|
| 113 |
+
},
|
| 114 |
+
"248054": {
|
| 115 |
+
"content": "<|vision_end|>",
|
| 116 |
+
"single_word": false,
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"rstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"special": true
|
| 121 |
+
},
|
| 122 |
+
"248055": {
|
| 123 |
+
"content": "<|vision_pad|>",
|
| 124 |
+
"single_word": false,
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"rstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"special": true
|
| 129 |
+
},
|
| 130 |
+
"248056": {
|
| 131 |
+
"content": "<|image_pad|>",
|
| 132 |
+
"single_word": false,
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"rstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"special": true
|
| 137 |
+
},
|
| 138 |
+
"248057": {
|
| 139 |
+
"content": "<|video_pad|>",
|
| 140 |
+
"single_word": false,
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"rstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"special": true
|
| 145 |
+
},
|
| 146 |
+
"248058": {
|
| 147 |
+
"content": "<tool_call>",
|
| 148 |
+
"single_word": false,
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"rstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"special": false
|
| 153 |
+
},
|
| 154 |
+
"248059": {
|
| 155 |
+
"content": "</tool_call>",
|
| 156 |
+
"single_word": false,
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"rstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"special": false
|
| 161 |
+
},
|
| 162 |
+
"248060": {
|
| 163 |
+
"content": "<|fim_prefix|>",
|
| 164 |
+
"single_word": false,
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"rstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"special": false
|
| 169 |
+
},
|
| 170 |
+
"248061": {
|
| 171 |
+
"content": "<|fim_middle|>",
|
| 172 |
+
"single_word": false,
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"rstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"special": false
|
| 177 |
+
},
|
| 178 |
+
"248062": {
|
| 179 |
+
"content": "<|fim_suffix|>",
|
| 180 |
+
"single_word": false,
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"rstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"special": false
|
| 185 |
+
},
|
| 186 |
+
"248063": {
|
| 187 |
+
"content": "<|fim_pad|>",
|
| 188 |
+
"single_word": false,
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"rstrip": false,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"special": false
|
| 193 |
+
},
|
| 194 |
+
"248064": {
|
| 195 |
+
"content": "<|repo_name|>",
|
| 196 |
+
"single_word": false,
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"rstrip": false,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"special": false
|
| 201 |
+
},
|
| 202 |
+
"248065": {
|
| 203 |
+
"content": "<|file_sep|>",
|
| 204 |
+
"single_word": false,
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"rstrip": false,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"special": false
|
| 209 |
+
},
|
| 210 |
+
"248066": {
|
| 211 |
+
"content": "<tool_response>",
|
| 212 |
+
"single_word": false,
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"rstrip": false,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"special": false
|
| 217 |
+
},
|
| 218 |
+
"248067": {
|
| 219 |
+
"content": "</tool_response>",
|
| 220 |
+
"single_word": false,
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"rstrip": false,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"special": false
|
| 225 |
+
},
|
| 226 |
+
"248068": {
|
| 227 |
+
"content": "<think>",
|
| 228 |
+
"single_word": false,
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"rstrip": false,
|
| 231 |
+
"normalized": false,
|
| 232 |
+
"special": false
|
| 233 |
+
},
|
| 234 |
+
"248069": {
|
| 235 |
+
"content": "</think>",
|
| 236 |
+
"single_word": false,
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"rstrip": false,
|
| 239 |
+
"normalized": false,
|
| 240 |
+
"special": false
|
| 241 |
+
},
|
| 242 |
+
"248070": {
|
| 243 |
+
"content": "<|audio_start|>",
|
| 244 |
+
"single_word": false,
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"rstrip": false,
|
| 247 |
+
"normalized": false,
|
| 248 |
+
"special": true
|
| 249 |
+
},
|
| 250 |
+
"248071": {
|
| 251 |
+
"content": "<|audio_end|>",
|
| 252 |
+
"single_word": false,
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"rstrip": false,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"special": true
|
| 257 |
+
},
|
| 258 |
+
"248072": {
|
| 259 |
+
"content": "<tts_pad>",
|
| 260 |
+
"single_word": false,
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"rstrip": false,
|
| 263 |
+
"normalized": false,
|
| 264 |
+
"special": true
|
| 265 |
+
},
|
| 266 |
+
"248073": {
|
| 267 |
+
"content": "<tts_text_bos>",
|
| 268 |
+
"single_word": false,
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"rstrip": false,
|
| 271 |
+
"normalized": false,
|
| 272 |
+
"special": true
|
| 273 |
+
},
|
| 274 |
+
"248074": {
|
| 275 |
+
"content": "<tts_text_eod>",
|
| 276 |
+
"single_word": false,
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"rstrip": false,
|
| 279 |
+
"normalized": false,
|
| 280 |
+
"special": true
|
| 281 |
+
},
|
| 282 |
+
"248075": {
|
| 283 |
+
"content": "<tts_text_bos_single>",
|
| 284 |
+
"single_word": false,
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"rstrip": false,
|
| 287 |
+
"normalized": false,
|
| 288 |
+
"special": true
|
| 289 |
+
},
|
| 290 |
+
"248076": {
|
| 291 |
+
"content": "<|audio_pad|>",
|
| 292 |
+
"single_word": false,
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"rstrip": false,
|
| 295 |
+
"normalized": false,
|
| 296 |
+
"special": true
|
| 297 |
+
},
|
| 298 |
+
"248077": {
|
| 299 |
+
"content": "<|PAD_TOKEN|>",
|
| 300 |
+
"single_word": false,
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"rstrip": false,
|
| 303 |
+
"normalized": false,
|
| 304 |
+
"special": true
|
| 305 |
+
}
|
| 306 |
+
}
|
| 307 |
+
}
|
checkpoint-2753/trainer_state.json
ADDED
|
@@ -0,0 +1,1959 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.9502660721990508,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2753,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.003451747447145117,
|
| 14 |
+
"grad_norm": 1.515625,
|
| 15 |
+
"learning_rate": 8.275862068965518e-06,
|
| 16 |
+
"loss": 1.4933374404907227,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.006903494894290234,
|
| 21 |
+
"grad_norm": 1.140625,
|
| 22 |
+
"learning_rate": 1.7471264367816093e-05,
|
| 23 |
+
"loss": 1.4012754440307618,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.010355242341435351,
|
| 28 |
+
"grad_norm": 1.046875,
|
| 29 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 30 |
+
"loss": 1.3529090881347656,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.013806989788580469,
|
| 35 |
+
"grad_norm": 1.0078125,
|
| 36 |
+
"learning_rate": 3.586206896551725e-05,
|
| 37 |
+
"loss": 1.3065607070922851,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.017258737235725585,
|
| 42 |
+
"grad_norm": 0.97265625,
|
| 43 |
+
"learning_rate": 4.505747126436782e-05,
|
| 44 |
+
"loss": 1.2669370651245118,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.020710484682870702,
|
| 49 |
+
"grad_norm": 1.03125,
|
| 50 |
+
"learning_rate": 5.425287356321839e-05,
|
| 51 |
+
"loss": 1.2412751197814942,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.02416223213001582,
|
| 56 |
+
"grad_norm": 1.0546875,
|
| 57 |
+
"learning_rate": 6.344827586206897e-05,
|
| 58 |
+
"loss": 1.234446144104004,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.027613979577160937,
|
| 63 |
+
"grad_norm": 1.15625,
|
| 64 |
+
"learning_rate": 7.264367816091954e-05,
|
| 65 |
+
"loss": 1.2307755470275878,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.031065727024306055,
|
| 70 |
+
"grad_norm": 1.1484375,
|
| 71 |
+
"learning_rate": 7.999990007644875e-05,
|
| 72 |
+
"loss": 1.212033462524414,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.03451747447145117,
|
| 77 |
+
"grad_norm": 1.296875,
|
| 78 |
+
"learning_rate": 7.999640280457428e-05,
|
| 79 |
+
"loss": 1.213148307800293,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.03796922191859629,
|
| 84 |
+
"grad_norm": 1.0234375,
|
| 85 |
+
"learning_rate": 7.998790985436162e-05,
|
| 86 |
+
"loss": 1.223739242553711,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.041420969365741404,
|
| 91 |
+
"grad_norm": 1.03125,
|
| 92 |
+
"learning_rate": 7.997442228660735e-05,
|
| 93 |
+
"loss": 1.2254825592041017,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.04487271681288652,
|
| 98 |
+
"grad_norm": 1.0546875,
|
| 99 |
+
"learning_rate": 7.995594178595172e-05,
|
| 100 |
+
"loss": 1.2246017456054688,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.04832446426003164,
|
| 105 |
+
"grad_norm": 1.0,
|
| 106 |
+
"learning_rate": 7.993247066066824e-05,
|
| 107 |
+
"loss": 1.1996318817138671,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.05177621170717676,
|
| 112 |
+
"grad_norm": 1.03125,
|
| 113 |
+
"learning_rate": 7.990401184237533e-05,
|
| 114 |
+
"loss": 1.198674201965332,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.055227959154321875,
|
| 119 |
+
"grad_norm": 1.015625,
|
| 120 |
+
"learning_rate": 7.987056888567024e-05,
|
| 121 |
+
"loss": 1.199861717224121,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.05867970660146699,
|
| 126 |
+
"grad_norm": 1.015625,
|
| 127 |
+
"learning_rate": 7.983214596768496e-05,
|
| 128 |
+
"loss": 1.2021236419677734,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.06213145404861211,
|
| 133 |
+
"grad_norm": 1.03125,
|
| 134 |
+
"learning_rate": 7.978874788756457e-05,
|
| 135 |
+
"loss": 1.1930582046508789,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.06558320149575722,
|
| 140 |
+
"grad_norm": 0.93359375,
|
| 141 |
+
"learning_rate": 7.974038006586773e-05,
|
| 142 |
+
"loss": 1.1789539337158204,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.06903494894290234,
|
| 147 |
+
"grad_norm": 1.21875,
|
| 148 |
+
"learning_rate": 7.968704854388973e-05,
|
| 149 |
+
"loss": 1.1880826950073242,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.07248669639004746,
|
| 154 |
+
"grad_norm": 0.984375,
|
| 155 |
+
"learning_rate": 7.962875998290784e-05,
|
| 156 |
+
"loss": 1.189031982421875,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.07593844383719257,
|
| 161 |
+
"grad_norm": 1.2421875,
|
| 162 |
+
"learning_rate": 7.956552166334933e-05,
|
| 163 |
+
"loss": 1.1735943794250487,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.07939019128433769,
|
| 168 |
+
"grad_norm": 0.99609375,
|
| 169 |
+
"learning_rate": 7.949734148388211e-05,
|
| 170 |
+
"loss": 1.1657325744628906,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.08284193873148281,
|
| 175 |
+
"grad_norm": 0.90625,
|
| 176 |
+
"learning_rate": 7.942422796042814e-05,
|
| 177 |
+
"loss": 1.158841323852539,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.08629368617862793,
|
| 182 |
+
"grad_norm": 0.953125,
|
| 183 |
+
"learning_rate": 7.934619022509981e-05,
|
| 184 |
+
"loss": 1.1521339416503906,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.08974543362577304,
|
| 189 |
+
"grad_norm": 1.0859375,
|
| 190 |
+
"learning_rate": 7.926323802505929e-05,
|
| 191 |
+
"loss": 1.1672565460205078,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.09319718107291816,
|
| 196 |
+
"grad_norm": 0.89453125,
|
| 197 |
+
"learning_rate": 7.917538172130105e-05,
|
| 198 |
+
"loss": 1.1572137832641602,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.09664892852006328,
|
| 203 |
+
"grad_norm": 1.2734375,
|
| 204 |
+
"learning_rate": 7.908263228735779e-05,
|
| 205 |
+
"loss": 1.1525598526000977,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.1001006759672084,
|
| 210 |
+
"grad_norm": 0.99609375,
|
| 211 |
+
"learning_rate": 7.898500130792977e-05,
|
| 212 |
+
"loss": 1.1617563247680665,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.10355242341435351,
|
| 217 |
+
"grad_norm": 0.9453125,
|
| 218 |
+
"learning_rate": 7.888250097743785e-05,
|
| 219 |
+
"loss": 1.1401342391967773,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.10700417086149863,
|
| 224 |
+
"grad_norm": 0.91015625,
|
| 225 |
+
"learning_rate": 7.877514409850039e-05,
|
| 226 |
+
"loss": 1.154245948791504,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.11045591830864375,
|
| 231 |
+
"grad_norm": 0.91796875,
|
| 232 |
+
"learning_rate": 7.866294408033413e-05,
|
| 233 |
+
"loss": 1.1580471038818358,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.11390766575578887,
|
| 238 |
+
"grad_norm": 0.92578125,
|
| 239 |
+
"learning_rate": 7.854591493707942e-05,
|
| 240 |
+
"loss": 1.146213912963867,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.11735941320293398,
|
| 245 |
+
"grad_norm": 0.9140625,
|
| 246 |
+
"learning_rate": 7.842407128604962e-05,
|
| 247 |
+
"loss": 1.1395330429077148,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.1208111606500791,
|
| 252 |
+
"grad_norm": 0.94140625,
|
| 253 |
+
"learning_rate": 7.829742834590559e-05,
|
| 254 |
+
"loss": 1.1332656860351562,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.12426290809722422,
|
| 259 |
+
"grad_norm": 0.9296875,
|
| 260 |
+
"learning_rate": 7.816600193475465e-05,
|
| 261 |
+
"loss": 1.1313667297363281,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.12771465554436934,
|
| 266 |
+
"grad_norm": 0.90625,
|
| 267 |
+
"learning_rate": 7.802980846817494e-05,
|
| 268 |
+
"loss": 1.1501797676086425,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.13116640299151444,
|
| 273 |
+
"grad_norm": 1.0078125,
|
| 274 |
+
"learning_rate": 7.788886495716503e-05,
|
| 275 |
+
"loss": 1.1436135292053222,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.13461815043865957,
|
| 280 |
+
"grad_norm": 1.03125,
|
| 281 |
+
"learning_rate": 7.774318900601919e-05,
|
| 282 |
+
"loss": 1.1435402870178222,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.13806989788580468,
|
| 287 |
+
"grad_norm": 0.90625,
|
| 288 |
+
"learning_rate": 7.759279881012857e-05,
|
| 289 |
+
"loss": 1.1246019363403321,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.1415216453329498,
|
| 294 |
+
"grad_norm": 1.015625,
|
| 295 |
+
"learning_rate": 7.743771315370852e-05,
|
| 296 |
+
"loss": 1.1361026763916016,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.1449733927800949,
|
| 301 |
+
"grad_norm": 0.91015625,
|
| 302 |
+
"learning_rate": 7.727795140745241e-05,
|
| 303 |
+
"loss": 1.1319564819335937,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.14842514022724004,
|
| 308 |
+
"grad_norm": 0.89453125,
|
| 309 |
+
"learning_rate": 7.711353352611214e-05,
|
| 310 |
+
"loss": 1.127757453918457,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.15187688767438515,
|
| 315 |
+
"grad_norm": 0.86328125,
|
| 316 |
+
"learning_rate": 7.694448004600577e-05,
|
| 317 |
+
"loss": 1.1355487823486328,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.15532863512153028,
|
| 322 |
+
"grad_norm": 0.91796875,
|
| 323 |
+
"learning_rate": 7.677081208245238e-05,
|
| 324 |
+
"loss": 1.115908718109131,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.15878038256867538,
|
| 329 |
+
"grad_norm": 0.87890625,
|
| 330 |
+
"learning_rate": 7.65925513271348e-05,
|
| 331 |
+
"loss": 1.119523811340332,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.1622321300158205,
|
| 336 |
+
"grad_norm": 0.87109375,
|
| 337 |
+
"learning_rate": 7.64097200453902e-05,
|
| 338 |
+
"loss": 1.11494140625,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.16568387746296562,
|
| 343 |
+
"grad_norm": 0.8984375,
|
| 344 |
+
"learning_rate": 7.622234107342908e-05,
|
| 345 |
+
"loss": 1.1108716011047364,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.16913562491011075,
|
| 350 |
+
"grad_norm": 0.9375,
|
| 351 |
+
"learning_rate": 7.603043781548295e-05,
|
| 352 |
+
"loss": 1.115338134765625,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.17258737235725585,
|
| 357 |
+
"grad_norm": 0.9296875,
|
| 358 |
+
"learning_rate": 7.58340342408811e-05,
|
| 359 |
+
"loss": 1.1127838134765624,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.17603911980440098,
|
| 364 |
+
"grad_norm": 1.0078125,
|
| 365 |
+
"learning_rate": 7.563315488105674e-05,
|
| 366 |
+
"loss": 1.1144102096557618,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.1794908672515461,
|
| 371 |
+
"grad_norm": 0.8671875,
|
| 372 |
+
"learning_rate": 7.542782482648287e-05,
|
| 373 |
+
"loss": 1.1094780921936036,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.18294261469869122,
|
| 378 |
+
"grad_norm": 0.89453125,
|
| 379 |
+
"learning_rate": 7.521806972353853e-05,
|
| 380 |
+
"loss": 1.1146849632263183,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.18639436214583632,
|
| 385 |
+
"grad_norm": 0.84375,
|
| 386 |
+
"learning_rate": 7.500391577130541e-05,
|
| 387 |
+
"loss": 1.1111886978149415,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.18984610959298145,
|
| 392 |
+
"grad_norm": 1.046875,
|
| 393 |
+
"learning_rate": 7.478538971829551e-05,
|
| 394 |
+
"loss": 1.1091678619384766,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.19329785704012656,
|
| 399 |
+
"grad_norm": 0.92578125,
|
| 400 |
+
"learning_rate": 7.456251885911015e-05,
|
| 401 |
+
"loss": 1.1091707229614258,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.1967496044872717,
|
| 406 |
+
"grad_norm": 0.8671875,
|
| 407 |
+
"learning_rate": 7.433533103103083e-05,
|
| 408 |
+
"loss": 1.0971466064453126,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.2002013519344168,
|
| 413 |
+
"grad_norm": 0.828125,
|
| 414 |
+
"learning_rate": 7.410385461054222e-05,
|
| 415 |
+
"loss": 1.0914318084716796,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.20365309938156193,
|
| 420 |
+
"grad_norm": 0.875,
|
| 421 |
+
"learning_rate": 7.386811850978788e-05,
|
| 422 |
+
"loss": 1.0979490280151367,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.20710484682870703,
|
| 427 |
+
"grad_norm": 0.99609375,
|
| 428 |
+
"learning_rate": 7.362815217295904e-05,
|
| 429 |
+
"loss": 1.0880674362182616,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.21055659427585216,
|
| 434 |
+
"grad_norm": 0.9375,
|
| 435 |
+
"learning_rate": 7.338398557261688e-05,
|
| 436 |
+
"loss": 1.1013910293579101,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.21400834172299726,
|
| 441 |
+
"grad_norm": 0.83203125,
|
| 442 |
+
"learning_rate": 7.313564920594891e-05,
|
| 443 |
+
"loss": 1.0965831756591797,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.2174600891701424,
|
| 448 |
+
"grad_norm": 0.85546875,
|
| 449 |
+
"learning_rate": 7.288317409095979e-05,
|
| 450 |
+
"loss": 1.0987209320068358,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.2209118366172875,
|
| 455 |
+
"grad_norm": 0.859375,
|
| 456 |
+
"learning_rate": 7.2626591762597e-05,
|
| 457 |
+
"loss": 1.0892770767211915,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.22436358406443263,
|
| 462 |
+
"grad_norm": 0.859375,
|
| 463 |
+
"learning_rate": 7.236593426881212e-05,
|
| 464 |
+
"loss": 1.0795110702514648,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.22781533151157773,
|
| 469 |
+
"grad_norm": 0.89453125,
|
| 470 |
+
"learning_rate": 7.210123416655787e-05,
|
| 471 |
+
"loss": 1.0909635543823242,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.23126707895872287,
|
| 476 |
+
"grad_norm": 0.828125,
|
| 477 |
+
"learning_rate": 7.183252451772167e-05,
|
| 478 |
+
"loss": 1.0831426620483398,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.23471882640586797,
|
| 483 |
+
"grad_norm": 0.859375,
|
| 484 |
+
"learning_rate": 7.155983888499612e-05,
|
| 485 |
+
"loss": 1.0963306427001953,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.2381705738530131,
|
| 490 |
+
"grad_norm": 0.84375,
|
| 491 |
+
"learning_rate": 7.128321132768689e-05,
|
| 492 |
+
"loss": 1.0896781921386718,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.2416223213001582,
|
| 497 |
+
"grad_norm": 1.3203125,
|
| 498 |
+
"learning_rate": 7.100267639745857e-05,
|
| 499 |
+
"loss": 1.086720085144043,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.2450740687473033,
|
| 504 |
+
"grad_norm": 0.83203125,
|
| 505 |
+
"learning_rate": 7.071826913401916e-05,
|
| 506 |
+
"loss": 1.0758808135986329,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.24852581619444844,
|
| 511 |
+
"grad_norm": 0.91015625,
|
| 512 |
+
"learning_rate": 7.043002506074339e-05,
|
| 513 |
+
"loss": 1.069956398010254,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.25197756364159357,
|
| 518 |
+
"grad_norm": 0.8984375,
|
| 519 |
+
"learning_rate": 7.013798018023579e-05,
|
| 520 |
+
"loss": 1.0716007232666016,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.2554293110887387,
|
| 525 |
+
"grad_norm": 0.87890625,
|
| 526 |
+
"learning_rate": 6.984217096983386e-05,
|
| 527 |
+
"loss": 1.0779573440551757,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.2588810585358838,
|
| 532 |
+
"grad_norm": 0.84765625,
|
| 533 |
+
"learning_rate": 6.954263437705189e-05,
|
| 534 |
+
"loss": 1.0841156005859376,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.2623328059830289,
|
| 539 |
+
"grad_norm": 0.85546875,
|
| 540 |
+
"learning_rate": 6.923940781496613e-05,
|
| 541 |
+
"loss": 1.0857189178466797,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.26578455343017404,
|
| 546 |
+
"grad_norm": 0.85546875,
|
| 547 |
+
"learning_rate": 6.89325291575418e-05,
|
| 548 |
+
"loss": 1.0597757339477538,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.26923630087731915,
|
| 553 |
+
"grad_norm": 0.85546875,
|
| 554 |
+
"learning_rate": 6.862203673490243e-05,
|
| 555 |
+
"loss": 1.0634410858154297,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.27268804832446425,
|
| 560 |
+
"grad_norm": 1.0078125,
|
| 561 |
+
"learning_rate": 6.830796932854238e-05,
|
| 562 |
+
"loss": 1.0832180023193358,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.27613979577160935,
|
| 567 |
+
"grad_norm": 0.8671875,
|
| 568 |
+
"learning_rate": 6.799036616648294e-05,
|
| 569 |
+
"loss": 1.0712278366088868,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.2795915432187545,
|
| 574 |
+
"grad_norm": 0.875,
|
| 575 |
+
"learning_rate": 6.766926691837246e-05,
|
| 576 |
+
"loss": 1.0655813217163086,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.2830432906658996,
|
| 581 |
+
"grad_norm": 0.83984375,
|
| 582 |
+
"learning_rate": 6.734471169053167e-05,
|
| 583 |
+
"loss": 1.0602886199951171,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.2864950381130447,
|
| 588 |
+
"grad_norm": 0.84375,
|
| 589 |
+
"learning_rate": 6.701674102094419e-05,
|
| 590 |
+
"loss": 1.050639533996582,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.2899467855601898,
|
| 595 |
+
"grad_norm": 0.87109375,
|
| 596 |
+
"learning_rate": 6.66853958741932e-05,
|
| 597 |
+
"loss": 1.0695268630981445,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.293398533007335,
|
| 602 |
+
"grad_norm": 0.84375,
|
| 603 |
+
"learning_rate": 6.635071763634483e-05,
|
| 604 |
+
"loss": 1.056867504119873,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.2968502804544801,
|
| 609 |
+
"grad_norm": 0.8671875,
|
| 610 |
+
"learning_rate": 6.601274810977895e-05,
|
| 611 |
+
"loss": 1.0739686965942383,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.3003020279016252,
|
| 616 |
+
"grad_norm": 0.83984375,
|
| 617 |
+
"learning_rate": 6.567152950796788e-05,
|
| 618 |
+
"loss": 1.073014736175537,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.3037537753487703,
|
| 623 |
+
"grad_norm": 0.83984375,
|
| 624 |
+
"learning_rate": 6.532710445020382e-05,
|
| 625 |
+
"loss": 1.0589933395385742,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.30720552279591545,
|
| 630 |
+
"grad_norm": 0.81640625,
|
| 631 |
+
"learning_rate": 6.497951595627554e-05,
|
| 632 |
+
"loss": 1.0577510833740233,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.31065727024306056,
|
| 637 |
+
"grad_norm": 0.82421875,
|
| 638 |
+
"learning_rate": 6.462880744109506e-05,
|
| 639 |
+
"loss": 1.0552112579345703,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.31410901769020566,
|
| 644 |
+
"grad_norm": 0.8046875,
|
| 645 |
+
"learning_rate": 6.427502270927504e-05,
|
| 646 |
+
"loss": 1.0574883460998534,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.31756076513735076,
|
| 651 |
+
"grad_norm": 0.84375,
|
| 652 |
+
"learning_rate": 6.391820594965743e-05,
|
| 653 |
+
"loss": 1.0548366546630858,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.3210125125844959,
|
| 658 |
+
"grad_norm": 0.80078125,
|
| 659 |
+
"learning_rate": 6.355840172979406e-05,
|
| 660 |
+
"loss": 1.0538974761962892,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.324464260031641,
|
| 665 |
+
"grad_norm": 0.84375,
|
| 666 |
+
"learning_rate": 6.319565499038015e-05,
|
| 667 |
+
"loss": 1.036550521850586,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.32791600747878613,
|
| 672 |
+
"grad_norm": 0.84375,
|
| 673 |
+
"learning_rate": 6.283001103964098e-05,
|
| 674 |
+
"loss": 1.0195422172546387,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.33136775492593123,
|
| 679 |
+
"grad_norm": 0.87109375,
|
| 680 |
+
"learning_rate": 6.246151554767273e-05,
|
| 681 |
+
"loss": 1.0480091094970703,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.3348195023730764,
|
| 686 |
+
"grad_norm": 0.83203125,
|
| 687 |
+
"learning_rate": 6.209021454073827e-05,
|
| 688 |
+
"loss": 1.0464174270629882,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.3382712498202215,
|
| 693 |
+
"grad_norm": 0.84375,
|
| 694 |
+
"learning_rate": 6.17161543955181e-05,
|
| 695 |
+
"loss": 1.0504976272583009,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.3417229972673666,
|
| 700 |
+
"grad_norm": 0.8359375,
|
| 701 |
+
"learning_rate": 6.133938183331802e-05,
|
| 702 |
+
"loss": 1.0350493431091308,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.3451747447145117,
|
| 707 |
+
"grad_norm": 0.83984375,
|
| 708 |
+
"learning_rate": 6.095994391423333e-05,
|
| 709 |
+
"loss": 1.031199073791504,
|
| 710 |
+
"step": 1000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.34862649216165686,
|
| 714 |
+
"grad_norm": 0.796875,
|
| 715 |
+
"learning_rate": 6.057788803127089e-05,
|
| 716 |
+
"loss": 1.0315200805664062,
|
| 717 |
+
"step": 1010
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.35207823960880197,
|
| 721 |
+
"grad_norm": 0.81640625,
|
| 722 |
+
"learning_rate": 6.0193261904429646e-05,
|
| 723 |
+
"loss": 1.0326057434082032,
|
| 724 |
+
"step": 1020
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.35552998705594707,
|
| 728 |
+
"grad_norm": 0.8671875,
|
| 729 |
+
"learning_rate": 5.980611357474013e-05,
|
| 730 |
+
"loss": 1.030609130859375,
|
| 731 |
+
"step": 1030
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.3589817345030922,
|
| 735 |
+
"grad_norm": 0.87890625,
|
| 736 |
+
"learning_rate": 5.941649139826413e-05,
|
| 737 |
+
"loss": 1.033174705505371,
|
| 738 |
+
"step": 1040
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.36243348195023734,
|
| 742 |
+
"grad_norm": 0.8046875,
|
| 743 |
+
"learning_rate": 5.9024444040054776e-05,
|
| 744 |
+
"loss": 1.0314329147338868,
|
| 745 |
+
"step": 1050
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.36588522939738244,
|
| 749 |
+
"grad_norm": 0.84765625,
|
| 750 |
+
"learning_rate": 5.863002046807809e-05,
|
| 751 |
+
"loss": 1.0311765670776367,
|
| 752 |
+
"step": 1060
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.36933697684452754,
|
| 756 |
+
"grad_norm": 0.79296875,
|
| 757 |
+
"learning_rate": 5.8233269947096865e-05,
|
| 758 |
+
"loss": 1.027195930480957,
|
| 759 |
+
"step": 1070
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.37278872429167265,
|
| 763 |
+
"grad_norm": 0.8125,
|
| 764 |
+
"learning_rate": 5.7834242032517145e-05,
|
| 765 |
+
"loss": 1.0420419692993164,
|
| 766 |
+
"step": 1080
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.37624047173881775,
|
| 770 |
+
"grad_norm": 0.85546875,
|
| 771 |
+
"learning_rate": 5.7432986564198786e-05,
|
| 772 |
+
"loss": 1.0313511848449708,
|
| 773 |
+
"step": 1090
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.3796922191859629,
|
| 777 |
+
"grad_norm": 0.83203125,
|
| 778 |
+
"learning_rate": 5.702955366023016e-05,
|
| 779 |
+
"loss": 1.0336549758911133,
|
| 780 |
+
"step": 1100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.383143966633108,
|
| 784 |
+
"grad_norm": 0.83203125,
|
| 785 |
+
"learning_rate": 5.662399371066833e-05,
|
| 786 |
+
"loss": 1.0237671852111816,
|
| 787 |
+
"step": 1110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.3865957140802531,
|
| 791 |
+
"grad_norm": 0.81640625,
|
| 792 |
+
"learning_rate": 5.6216357371245144e-05,
|
| 793 |
+
"loss": 1.0216711044311524,
|
| 794 |
+
"step": 1120
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.3900474615273982,
|
| 798 |
+
"grad_norm": 0.8359375,
|
| 799 |
+
"learning_rate": 5.5806695557040134e-05,
|
| 800 |
+
"loss": 1.023019790649414,
|
| 801 |
+
"step": 1130
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.3934992089745434,
|
| 805 |
+
"grad_norm": 0.82421875,
|
| 806 |
+
"learning_rate": 5.5395059436121126e-05,
|
| 807 |
+
"loss": 1.02832088470459,
|
| 808 |
+
"step": 1140
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.3969509564216885,
|
| 812 |
+
"grad_norm": 0.8203125,
|
| 813 |
+
"learning_rate": 5.498150042315316e-05,
|
| 814 |
+
"loss": 1.0066239356994628,
|
| 815 |
+
"step": 1150
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.4004027038688336,
|
| 819 |
+
"grad_norm": 0.859375,
|
| 820 |
+
"learning_rate": 5.456607017297661e-05,
|
| 821 |
+
"loss": 1.0093968391418457,
|
| 822 |
+
"step": 1160
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.4038544513159787,
|
| 826 |
+
"grad_norm": 0.83203125,
|
| 827 |
+
"learning_rate": 5.414882057415535e-05,
|
| 828 |
+
"loss": 1.0341301918029786,
|
| 829 |
+
"step": 1170
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.40730619876312385,
|
| 833 |
+
"grad_norm": 0.80078125,
|
| 834 |
+
"learning_rate": 5.372980374249569e-05,
|
| 835 |
+
"loss": 1.026323127746582,
|
| 836 |
+
"step": 1180
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.41075794621026895,
|
| 840 |
+
"grad_norm": 0.80078125,
|
| 841 |
+
"learning_rate": 5.330907201453702e-05,
|
| 842 |
+
"loss": 1.0211387634277345,
|
| 843 |
+
"step": 1190
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.41420969365741406,
|
| 847 |
+
"grad_norm": 0.8359375,
|
| 848 |
+
"learning_rate": 5.288667794101469e-05,
|
| 849 |
+
"loss": 1.0229217529296875,
|
| 850 |
+
"step": 1200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.41766144110455916,
|
| 854 |
+
"grad_norm": 0.859375,
|
| 855 |
+
"learning_rate": 5.246267428029633e-05,
|
| 856 |
+
"loss": 1.016196060180664,
|
| 857 |
+
"step": 1210
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.4211131885517043,
|
| 861 |
+
"grad_norm": 0.87109375,
|
| 862 |
+
"learning_rate": 5.2037113991792185e-05,
|
| 863 |
+
"loss": 1.0084825515747071,
|
| 864 |
+
"step": 1220
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.4245649359988494,
|
| 868 |
+
"grad_norm": 0.83203125,
|
| 869 |
+
"learning_rate": 5.161005022934019e-05,
|
| 870 |
+
"loss": 1.0148038864135742,
|
| 871 |
+
"step": 1230
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.42801668344599453,
|
| 875 |
+
"grad_norm": 0.82421875,
|
| 876 |
+
"learning_rate": 5.118153633456708e-05,
|
| 877 |
+
"loss": 1.0144267082214355,
|
| 878 |
+
"step": 1240
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.43146843089313963,
|
| 882 |
+
"grad_norm": 0.80859375,
|
| 883 |
+
"learning_rate": 5.0751625830225664e-05,
|
| 884 |
+
"loss": 1.0142309188842773,
|
| 885 |
+
"step": 1250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.4349201783402848,
|
| 889 |
+
"grad_norm": 0.84765625,
|
| 890 |
+
"learning_rate": 5.0320372413509786e-05,
|
| 891 |
+
"loss": 1.0305488586425782,
|
| 892 |
+
"step": 1260
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.4383719257874299,
|
| 896 |
+
"grad_norm": 0.8046875,
|
| 897 |
+
"learning_rate": 4.988782994934732e-05,
|
| 898 |
+
"loss": 1.0084169387817383,
|
| 899 |
+
"step": 1270
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.441823673234575,
|
| 903 |
+
"grad_norm": 0.80078125,
|
| 904 |
+
"learning_rate": 4.945405246367226e-05,
|
| 905 |
+
"loss": 1.00357666015625,
|
| 906 |
+
"step": 1280
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.4452754206817201,
|
| 910 |
+
"grad_norm": 0.8359375,
|
| 911 |
+
"learning_rate": 4.901909413667675e-05,
|
| 912 |
+
"loss": 1.0097660064697265,
|
| 913 |
+
"step": 1290
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.44872716812886526,
|
| 917 |
+
"grad_norm": 0.78515625,
|
| 918 |
+
"learning_rate": 4.858300929604379e-05,
|
| 919 |
+
"loss": 1.0070899963378905,
|
| 920 |
+
"step": 1300
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.45217891557601037,
|
| 924 |
+
"grad_norm": 0.82421875,
|
| 925 |
+
"learning_rate": 4.81458524101615e-05,
|
| 926 |
+
"loss": 1.0107892036437989,
|
| 927 |
+
"step": 1310
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.45563066302315547,
|
| 931 |
+
"grad_norm": 0.80078125,
|
| 932 |
+
"learning_rate": 4.770767808131988e-05,
|
| 933 |
+
"loss": 1.0003870010375977,
|
| 934 |
+
"step": 1320
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.4590824104703006,
|
| 938 |
+
"grad_norm": 0.81640625,
|
| 939 |
+
"learning_rate": 4.726854103889083e-05,
|
| 940 |
+
"loss": 0.9783724784851074,
|
| 941 |
+
"step": 1330
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.46253415791744573,
|
| 945 |
+
"grad_norm": 0.84375,
|
| 946 |
+
"learning_rate": 4.682849613249223e-05,
|
| 947 |
+
"loss": 0.9953472137451171,
|
| 948 |
+
"step": 1340
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.46598590536459084,
|
| 952 |
+
"grad_norm": 0.81640625,
|
| 953 |
+
"learning_rate": 4.638759832513705e-05,
|
| 954 |
+
"loss": 1.003485107421875,
|
| 955 |
+
"step": 1350
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.46943765281173594,
|
| 959 |
+
"grad_norm": 0.7890625,
|
| 960 |
+
"learning_rate": 4.5945902686368336e-05,
|
| 961 |
+
"loss": 0.9853975296020507,
|
| 962 |
+
"step": 1360
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.47288940025888104,
|
| 966 |
+
"grad_norm": 0.8125,
|
| 967 |
+
"learning_rate": 4.5503464385380805e-05,
|
| 968 |
+
"loss": 0.9910802841186523,
|
| 969 |
+
"step": 1370
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.4763411477060262,
|
| 973 |
+
"grad_norm": 0.81640625,
|
| 974 |
+
"learning_rate": 4.506033868413006e-05,
|
| 975 |
+
"loss": 0.986263656616211,
|
| 976 |
+
"step": 1380
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.4797928951531713,
|
| 980 |
+
"grad_norm": 0.8046875,
|
| 981 |
+
"learning_rate": 4.461658093043023e-05,
|
| 982 |
+
"loss": 0.9845444679260253,
|
| 983 |
+
"step": 1390
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.4832446426003164,
|
| 987 |
+
"grad_norm": 0.8203125,
|
| 988 |
+
"learning_rate": 4.4172246551040736e-05,
|
| 989 |
+
"loss": 1.017231559753418,
|
| 990 |
+
"step": 1400
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.4866963900474615,
|
| 994 |
+
"grad_norm": 0.82421875,
|
| 995 |
+
"learning_rate": 4.372739104474345e-05,
|
| 996 |
+
"loss": 0.9790552139282227,
|
| 997 |
+
"step": 1410
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.4901481374946066,
|
| 1001 |
+
"grad_norm": 0.8046875,
|
| 1002 |
+
"learning_rate": 4.328206997541062e-05,
|
| 1003 |
+
"loss": 0.9778913497924805,
|
| 1004 |
+
"step": 1420
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.4935998849417518,
|
| 1008 |
+
"grad_norm": 0.81640625,
|
| 1009 |
+
"learning_rate": 4.283633896506484e-05,
|
| 1010 |
+
"loss": 0.999072265625,
|
| 1011 |
+
"step": 1430
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.4970516323888969,
|
| 1015 |
+
"grad_norm": 0.796875,
|
| 1016 |
+
"learning_rate": 4.2390253686931595e-05,
|
| 1017 |
+
"loss": 0.9829935073852539,
|
| 1018 |
+
"step": 1440
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.500503379836042,
|
| 1022 |
+
"grad_norm": 0.78515625,
|
| 1023 |
+
"learning_rate": 4.1943869858485604e-05,
|
| 1024 |
+
"loss": 0.9685152053833008,
|
| 1025 |
+
"step": 1450
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.5039551272831871,
|
| 1029 |
+
"grad_norm": 0.8125,
|
| 1030 |
+
"learning_rate": 4.1497243234491426e-05,
|
| 1031 |
+
"loss": 0.9828019142150879,
|
| 1032 |
+
"step": 1460
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.5074068747303322,
|
| 1036 |
+
"grad_norm": 0.79296875,
|
| 1037 |
+
"learning_rate": 4.105042960003958e-05,
|
| 1038 |
+
"loss": 0.9914402008056641,
|
| 1039 |
+
"step": 1470
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.5108586221774774,
|
| 1043 |
+
"grad_norm": 0.8125,
|
| 1044 |
+
"learning_rate": 4.060348476357877e-05,
|
| 1045 |
+
"loss": 0.982816219329834,
|
| 1046 |
+
"step": 1480
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.5143103696246225,
|
| 1050 |
+
"grad_norm": 1.484375,
|
| 1051 |
+
"learning_rate": 4.015646454994529e-05,
|
| 1052 |
+
"loss": 0.9954681396484375,
|
| 1053 |
+
"step": 1490
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.5177621170717676,
|
| 1057 |
+
"grad_norm": 0.84765625,
|
| 1058 |
+
"learning_rate": 3.9709424793390244e-05,
|
| 1059 |
+
"loss": 1.0002605438232421,
|
| 1060 |
+
"step": 1500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.5212138645189127,
|
| 1064 |
+
"grad_norm": 0.80078125,
|
| 1065 |
+
"learning_rate": 3.926242133060573e-05,
|
| 1066 |
+
"loss": 0.9856294631958008,
|
| 1067 |
+
"step": 1510
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.5246656119660578,
|
| 1071 |
+
"grad_norm": 0.8046875,
|
| 1072 |
+
"learning_rate": 3.881550999375063e-05,
|
| 1073 |
+
"loss": 0.9805760383605957,
|
| 1074 |
+
"step": 1520
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.5281173594132029,
|
| 1078 |
+
"grad_norm": 0.77734375,
|
| 1079 |
+
"learning_rate": 3.836874660347698e-05,
|
| 1080 |
+
"loss": 0.9846339225769043,
|
| 1081 |
+
"step": 1530
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.5315691068603481,
|
| 1085 |
+
"grad_norm": 0.77734375,
|
| 1086 |
+
"learning_rate": 3.792218696195787e-05,
|
| 1087 |
+
"loss": 0.967560863494873,
|
| 1088 |
+
"step": 1540
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.5350208543074931,
|
| 1092 |
+
"grad_norm": 0.79296875,
|
| 1093 |
+
"learning_rate": 3.747588684591748e-05,
|
| 1094 |
+
"loss": 0.9505450248718261,
|
| 1095 |
+
"step": 1550
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.5384726017546383,
|
| 1099 |
+
"grad_norm": 0.8671875,
|
| 1100 |
+
"learning_rate": 3.702990199966444e-05,
|
| 1101 |
+
"loss": 0.9622068405151367,
|
| 1102 |
+
"step": 1560
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.5419243492017835,
|
| 1106 |
+
"grad_norm": 0.8203125,
|
| 1107 |
+
"learning_rate": 3.658428812812919e-05,
|
| 1108 |
+
"loss": 0.9831565856933594,
|
| 1109 |
+
"step": 1570
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.5453760966489285,
|
| 1113 |
+
"grad_norm": 0.77734375,
|
| 1114 |
+
"learning_rate": 3.613910088990622e-05,
|
| 1115 |
+
"loss": 0.9684982299804688,
|
| 1116 |
+
"step": 1580
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.5488278440960737,
|
| 1120 |
+
"grad_norm": 0.8046875,
|
| 1121 |
+
"learning_rate": 3.569439589030215e-05,
|
| 1122 |
+
"loss": 0.96829252243042,
|
| 1123 |
+
"step": 1590
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.5522795915432187,
|
| 1127 |
+
"grad_norm": 0.80859375,
|
| 1128 |
+
"learning_rate": 3.52502286743905e-05,
|
| 1129 |
+
"loss": 0.9854541778564453,
|
| 1130 |
+
"step": 1600
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.5557313389903639,
|
| 1134 |
+
"grad_norm": 0.80078125,
|
| 1135 |
+
"learning_rate": 3.480665472007388e-05,
|
| 1136 |
+
"loss": 0.964383888244629,
|
| 1137 |
+
"step": 1610
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.559183086437509,
|
| 1141 |
+
"grad_norm": 0.765625,
|
| 1142 |
+
"learning_rate": 3.436372943115461e-05,
|
| 1143 |
+
"loss": 0.965116310119629,
|
| 1144 |
+
"step": 1620
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.5626348338846541,
|
| 1148 |
+
"grad_norm": 0.796875,
|
| 1149 |
+
"learning_rate": 3.392150813041463e-05,
|
| 1150 |
+
"loss": 0.9741801261901856,
|
| 1151 |
+
"step": 1630
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.5660865813317992,
|
| 1155 |
+
"grad_norm": 0.76953125,
|
| 1156 |
+
"learning_rate": 3.3480046052705524e-05,
|
| 1157 |
+
"loss": 0.9536490440368652,
|
| 1158 |
+
"step": 1640
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.5695383287789444,
|
| 1162 |
+
"grad_norm": 0.76171875,
|
| 1163 |
+
"learning_rate": 3.303939833804952e-05,
|
| 1164 |
+
"loss": 0.9583781242370606,
|
| 1165 |
+
"step": 1650
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.5729900762260894,
|
| 1169 |
+
"grad_norm": 0.77734375,
|
| 1170 |
+
"learning_rate": 3.259962002475227e-05,
|
| 1171 |
+
"loss": 0.9700896263122558,
|
| 1172 |
+
"step": 1660
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.5764418236732346,
|
| 1176 |
+
"grad_norm": 0.765625,
|
| 1177 |
+
"learning_rate": 3.216076604252842e-05,
|
| 1178 |
+
"loss": 0.9651447296142578,
|
| 1179 |
+
"step": 1670
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.5798935711203796,
|
| 1183 |
+
"grad_norm": 0.77734375,
|
| 1184 |
+
"learning_rate": 3.172289120564074e-05,
|
| 1185 |
+
"loss": 0.9791692733764649,
|
| 1186 |
+
"step": 1680
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.5833453185675248,
|
| 1190 |
+
"grad_norm": 0.77734375,
|
| 1191 |
+
"learning_rate": 3.128605020605358e-05,
|
| 1192 |
+
"loss": 0.9495502471923828,
|
| 1193 |
+
"step": 1690
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.58679706601467,
|
| 1197 |
+
"grad_norm": 0.8046875,
|
| 1198 |
+
"learning_rate": 3.085029760660178e-05,
|
| 1199 |
+
"loss": 0.9585142135620117,
|
| 1200 |
+
"step": 1700
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.590248813461815,
|
| 1204 |
+
"grad_norm": 0.796875,
|
| 1205 |
+
"learning_rate": 3.041568783417547e-05,
|
| 1206 |
+
"loss": 0.9721488952636719,
|
| 1207 |
+
"step": 1710
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.5937005609089602,
|
| 1211 |
+
"grad_norm": 0.77734375,
|
| 1212 |
+
"learning_rate": 2.9982275172922065e-05,
|
| 1213 |
+
"loss": 0.9778090476989746,
|
| 1214 |
+
"step": 1720
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.5971523083561053,
|
| 1218 |
+
"grad_norm": 0.78125,
|
| 1219 |
+
"learning_rate": 2.9550113757465965e-05,
|
| 1220 |
+
"loss": 0.9518679618835449,
|
| 1221 |
+
"step": 1730
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.6006040558032504,
|
| 1225 |
+
"grad_norm": 0.7734375,
|
| 1226 |
+
"learning_rate": 2.9119257566146976e-05,
|
| 1227 |
+
"loss": 0.9666889190673829,
|
| 1228 |
+
"step": 1740
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.6040558032503955,
|
| 1232 |
+
"grad_norm": 0.7890625,
|
| 1233 |
+
"learning_rate": 2.8689760414278263e-05,
|
| 1234 |
+
"loss": 0.9599795341491699,
|
| 1235 |
+
"step": 1750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.6075075506975406,
|
| 1239 |
+
"grad_norm": 0.77734375,
|
| 1240 |
+
"learning_rate": 2.8261675947424606e-05,
|
| 1241 |
+
"loss": 0.9571071624755859,
|
| 1242 |
+
"step": 1760
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.6109592981446857,
|
| 1246 |
+
"grad_norm": 0.765625,
|
| 1247 |
+
"learning_rate": 2.783505763470192e-05,
|
| 1248 |
+
"loss": 0.9467939376831055,
|
| 1249 |
+
"step": 1770
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.6144110455918309,
|
| 1253 |
+
"grad_norm": 0.78515625,
|
| 1254 |
+
"learning_rate": 2.740995876209881e-05,
|
| 1255 |
+
"loss": 0.952598762512207,
|
| 1256 |
+
"step": 1780
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.617862793038976,
|
| 1260 |
+
"grad_norm": 0.79296875,
|
| 1261 |
+
"learning_rate": 2.6986432425820926e-05,
|
| 1262 |
+
"loss": 0.965939998626709,
|
| 1263 |
+
"step": 1790
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.6213145404861211,
|
| 1267 |
+
"grad_norm": 0.80078125,
|
| 1268 |
+
"learning_rate": 2.6564531525659165e-05,
|
| 1269 |
+
"loss": 0.9617385864257812,
|
| 1270 |
+
"step": 1800
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.6247662879332662,
|
| 1274 |
+
"grad_norm": 0.78125,
|
| 1275 |
+
"learning_rate": 2.6144308758382216e-05,
|
| 1276 |
+
"loss": 0.9621437072753907,
|
| 1277 |
+
"step": 1810
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.6282180353804113,
|
| 1281 |
+
"grad_norm": 0.796875,
|
| 1282 |
+
"learning_rate": 2.5725816611154635e-05,
|
| 1283 |
+
"loss": 0.9544252395629883,
|
| 1284 |
+
"step": 1820
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.6316697828275565,
|
| 1288 |
+
"grad_norm": 0.796875,
|
| 1289 |
+
"learning_rate": 2.530910735498103e-05,
|
| 1290 |
+
"loss": 0.9507457733154296,
|
| 1291 |
+
"step": 1830
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.6351215302747015,
|
| 1295 |
+
"grad_norm": 0.82421875,
|
| 1296 |
+
"learning_rate": 2.4894233038177174e-05,
|
| 1297 |
+
"loss": 0.9430961608886719,
|
| 1298 |
+
"step": 1840
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.6385732777218467,
|
| 1302 |
+
"grad_norm": 0.76953125,
|
| 1303 |
+
"learning_rate": 2.4481245479869144e-05,
|
| 1304 |
+
"loss": 0.9510479927062988,
|
| 1305 |
+
"step": 1850
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.6420250251689918,
|
| 1309 |
+
"grad_norm": 0.80078125,
|
| 1310 |
+
"learning_rate": 2.4070196263520774e-05,
|
| 1311 |
+
"loss": 0.9614797592163086,
|
| 1312 |
+
"step": 1860
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.6454767726161369,
|
| 1316 |
+
"grad_norm": 0.75,
|
| 1317 |
+
"learning_rate": 2.3661136730490854e-05,
|
| 1318 |
+
"loss": 0.9490167617797851,
|
| 1319 |
+
"step": 1870
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.648928520063282,
|
| 1323 |
+
"grad_norm": 0.7734375,
|
| 1324 |
+
"learning_rate": 2.3254117973620342e-05,
|
| 1325 |
+
"loss": 0.9488746643066406,
|
| 1326 |
+
"step": 1880
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.6523802675104271,
|
| 1330 |
+
"grad_norm": 0.78515625,
|
| 1331 |
+
"learning_rate": 2.2849190830850777e-05,
|
| 1332 |
+
"loss": 0.9446886062622071,
|
| 1333 |
+
"step": 1890
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.6558320149575723,
|
| 1337 |
+
"grad_norm": 0.7890625,
|
| 1338 |
+
"learning_rate": 2.2446405878874403e-05,
|
| 1339 |
+
"loss": 0.9745735168457031,
|
| 1340 |
+
"step": 1900
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.6592837624047174,
|
| 1344 |
+
"grad_norm": 0.78125,
|
| 1345 |
+
"learning_rate": 2.2045813426817002e-05,
|
| 1346 |
+
"loss": 0.9526460647583008,
|
| 1347 |
+
"step": 1910
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.6627355098518625,
|
| 1351 |
+
"grad_norm": 0.7578125,
|
| 1352 |
+
"learning_rate": 2.1647463509954144e-05,
|
| 1353 |
+
"loss": 0.9487321853637696,
|
| 1354 |
+
"step": 1920
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.6661872572990076,
|
| 1358 |
+
"grad_norm": 0.82421875,
|
| 1359 |
+
"learning_rate": 2.1251405883461532e-05,
|
| 1360 |
+
"loss": 0.9646244049072266,
|
| 1361 |
+
"step": 1930
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.6696390047461528,
|
| 1365 |
+
"grad_norm": 0.7734375,
|
| 1366 |
+
"learning_rate": 2.085769001620055e-05,
|
| 1367 |
+
"loss": 0.9495641708374023,
|
| 1368 |
+
"step": 1940
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.6730907521932978,
|
| 1372 |
+
"grad_norm": 0.7578125,
|
| 1373 |
+
"learning_rate": 2.0466365084539355e-05,
|
| 1374 |
+
"loss": 0.9549238204956054,
|
| 1375 |
+
"step": 1950
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.676542499640443,
|
| 1379 |
+
"grad_norm": 0.765625,
|
| 1380 |
+
"learning_rate": 2.0077479966210633e-05,
|
| 1381 |
+
"loss": 0.9436851501464844,
|
| 1382 |
+
"step": 1960
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.679994247087588,
|
| 1386 |
+
"grad_norm": 0.78515625,
|
| 1387 |
+
"learning_rate": 1.9691083234206597e-05,
|
| 1388 |
+
"loss": 0.9507623672485351,
|
| 1389 |
+
"step": 1970
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.6834459945347332,
|
| 1393 |
+
"grad_norm": 0.7578125,
|
| 1394 |
+
"learning_rate": 1.930722315071203e-05,
|
| 1395 |
+
"loss": 0.9325309753417969,
|
| 1396 |
+
"step": 1980
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.6868977419818784,
|
| 1400 |
+
"grad_norm": 0.765625,
|
| 1401 |
+
"learning_rate": 1.8925947661076265e-05,
|
| 1402 |
+
"loss": 0.9526151657104492,
|
| 1403 |
+
"step": 1990
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.6903494894290234,
|
| 1407 |
+
"grad_norm": 0.75,
|
| 1408 |
+
"learning_rate": 1.854730438782461e-05,
|
| 1409 |
+
"loss": 0.935435676574707,
|
| 1410 |
+
"step": 2000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.6938012368761686,
|
| 1414 |
+
"grad_norm": 0.76171875,
|
| 1415 |
+
"learning_rate": 1.817134062471015e-05,
|
| 1416 |
+
"loss": 0.9497850418090821,
|
| 1417 |
+
"step": 2010
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.6972529843233137,
|
| 1421 |
+
"grad_norm": 0.7890625,
|
| 1422 |
+
"learning_rate": 1.7798103330806566e-05,
|
| 1423 |
+
"loss": 0.9456364631652832,
|
| 1424 |
+
"step": 2020
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.7007047317704588,
|
| 1428 |
+
"grad_norm": 0.75,
|
| 1429 |
+
"learning_rate": 1.7427639124642866e-05,
|
| 1430 |
+
"loss": 0.9500192642211914,
|
| 1431 |
+
"step": 2030
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.7041564792176039,
|
| 1435 |
+
"grad_norm": 0.7578125,
|
| 1436 |
+
"learning_rate": 1.7059994278380552e-05,
|
| 1437 |
+
"loss": 0.9443693161010742,
|
| 1438 |
+
"step": 2040
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.707608226664749,
|
| 1442 |
+
"grad_norm": 0.75390625,
|
| 1443 |
+
"learning_rate": 1.669521471203407e-05,
|
| 1444 |
+
"loss": 0.9334108352661132,
|
| 1445 |
+
"step": 2050
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.7110599741118941,
|
| 1449 |
+
"grad_norm": 0.8125,
|
| 1450 |
+
"learning_rate": 1.633334598773528e-05,
|
| 1451 |
+
"loss": 0.9649259567260742,
|
| 1452 |
+
"step": 2060
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.7145117215590393,
|
| 1456 |
+
"grad_norm": 0.78125,
|
| 1457 |
+
"learning_rate": 1.597443330404253e-05,
|
| 1458 |
+
"loss": 0.9337587356567383,
|
| 1459 |
+
"step": 2070
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.7179634690061844,
|
| 1463 |
+
"grad_norm": 0.765625,
|
| 1464 |
+
"learning_rate": 1.561852149029532e-05,
|
| 1465 |
+
"loss": 0.9440608978271484,
|
| 1466 |
+
"step": 2080
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.7214152164533295,
|
| 1470 |
+
"grad_norm": 0.78125,
|
| 1471 |
+
"learning_rate": 1.526565500101489e-05,
|
| 1472 |
+
"loss": 0.9614963531494141,
|
| 1473 |
+
"step": 2090
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.7248669639004747,
|
| 1477 |
+
"grad_norm": 0.78515625,
|
| 1478 |
+
"learning_rate": 1.491587791035174e-05,
|
| 1479 |
+
"loss": 0.9500024795532227,
|
| 1480 |
+
"step": 2100
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.7283187113476197,
|
| 1484 |
+
"grad_norm": 0.75390625,
|
| 1485 |
+
"learning_rate": 1.4569233906580649e-05,
|
| 1486 |
+
"loss": 0.9378911972045898,
|
| 1487 |
+
"step": 2110
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.7317704587947649,
|
| 1491 |
+
"grad_norm": 0.78125,
|
| 1492 |
+
"learning_rate": 1.4225766286643792e-05,
|
| 1493 |
+
"loss": 0.9389601707458496,
|
| 1494 |
+
"step": 2120
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.7352222062419099,
|
| 1498 |
+
"grad_norm": 0.74609375,
|
| 1499 |
+
"learning_rate": 1.3885517950742915e-05,
|
| 1500 |
+
"loss": 0.9419396400451661,
|
| 1501 |
+
"step": 2130
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.7386739536890551,
|
| 1505 |
+
"grad_norm": 0.75,
|
| 1506 |
+
"learning_rate": 1.3548531396980895e-05,
|
| 1507 |
+
"loss": 0.9491300582885742,
|
| 1508 |
+
"step": 2140
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.7421257011362002,
|
| 1512 |
+
"grad_norm": 0.7578125,
|
| 1513 |
+
"learning_rate": 1.3214848716053616e-05,
|
| 1514 |
+
"loss": 0.9364492416381835,
|
| 1515 |
+
"step": 2150
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.7455774485833453,
|
| 1519 |
+
"grad_norm": 0.78125,
|
| 1520 |
+
"learning_rate": 1.2884511585992718e-05,
|
| 1521 |
+
"loss": 0.9492175102233886,
|
| 1522 |
+
"step": 2160
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.7490291960304905,
|
| 1526 |
+
"grad_norm": 0.74609375,
|
| 1527 |
+
"learning_rate": 1.2557561266959821e-05,
|
| 1528 |
+
"loss": 0.9309873580932617,
|
| 1529 |
+
"step": 2170
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.7524809434776355,
|
| 1533 |
+
"grad_norm": 0.7578125,
|
| 1534 |
+
"learning_rate": 1.2234038596093076e-05,
|
| 1535 |
+
"loss": 0.9388093948364258,
|
| 1536 |
+
"step": 2180
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.7559326909247807,
|
| 1540 |
+
"grad_norm": 0.7890625,
|
| 1541 |
+
"learning_rate": 1.1913983982406432e-05,
|
| 1542 |
+
"loss": 0.9374133110046386,
|
| 1543 |
+
"step": 2190
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.7593844383719258,
|
| 1547 |
+
"grad_norm": 0.765625,
|
| 1548 |
+
"learning_rate": 1.1597437401742426e-05,
|
| 1549 |
+
"loss": 0.9536163330078125,
|
| 1550 |
+
"step": 2200
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.7628361858190709,
|
| 1554 |
+
"grad_norm": 0.76953125,
|
| 1555 |
+
"learning_rate": 1.1284438391779093e-05,
|
| 1556 |
+
"loss": 0.9425058364868164,
|
| 1557 |
+
"step": 2210
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.766287933266216,
|
| 1561 |
+
"grad_norm": 0.77734375,
|
| 1562 |
+
"learning_rate": 1.0975026047091522e-05,
|
| 1563 |
+
"loss": 0.9437975883483887,
|
| 1564 |
+
"step": 2220
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.7697396807133612,
|
| 1568 |
+
"grad_norm": 0.75390625,
|
| 1569 |
+
"learning_rate": 1.0669239014268915e-05,
|
| 1570 |
+
"loss": 0.9394214630126954,
|
| 1571 |
+
"step": 2230
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.7731914281605062,
|
| 1575 |
+
"grad_norm": 0.7578125,
|
| 1576 |
+
"learning_rate": 1.0367115487087425e-05,
|
| 1577 |
+
"loss": 0.9354355812072754,
|
| 1578 |
+
"step": 2240
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.7766431756076514,
|
| 1582 |
+
"grad_norm": 0.76171875,
|
| 1583 |
+
"learning_rate": 1.0068693201739675e-05,
|
| 1584 |
+
"loss": 0.9477321624755859,
|
| 1585 |
+
"step": 2250
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.7800949230547964,
|
| 1589 |
+
"grad_norm": 0.77734375,
|
| 1590 |
+
"learning_rate": 9.774009432121376e-06,
|
| 1591 |
+
"loss": 0.9568775177001954,
|
| 1592 |
+
"step": 2260
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.7835466705019416,
|
| 1596 |
+
"grad_norm": 0.7734375,
|
| 1597 |
+
"learning_rate": 9.483100985175655e-06,
|
| 1598 |
+
"loss": 0.9508476257324219,
|
| 1599 |
+
"step": 2270
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.7869984179490868,
|
| 1603 |
+
"grad_norm": 0.76953125,
|
| 1604 |
+
"learning_rate": 9.19600419629584e-06,
|
| 1605 |
+
"loss": 0.9462928771972656,
|
| 1606 |
+
"step": 2280
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.7904501653962318,
|
| 1610 |
+
"grad_norm": 0.78125,
|
| 1611 |
+
"learning_rate": 8.912754924786982e-06,
|
| 1612 |
+
"loss": 0.9318842887878418,
|
| 1613 |
+
"step": 2290
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.793901912843377,
|
| 1617 |
+
"grad_norm": 0.7578125,
|
| 1618 |
+
"learning_rate": 8.633388549386943e-06,
|
| 1619 |
+
"loss": 0.9289694786071777,
|
| 1620 |
+
"step": 2300
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.7973536602905221,
|
| 1624 |
+
"grad_norm": 0.7734375,
|
| 1625 |
+
"learning_rate": 8.357939963847447e-06,
|
| 1626 |
+
"loss": 0.943126106262207,
|
| 1627 |
+
"step": 2310
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.8008054077376672,
|
| 1631 |
+
"grad_norm": 0.7734375,
|
| 1632 |
+
"learning_rate": 8.086443572575789e-06,
|
| 1633 |
+
"loss": 0.9459014892578125,
|
| 1634 |
+
"step": 2320
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.8042571551848123,
|
| 1638 |
+
"grad_norm": 0.76953125,
|
| 1639 |
+
"learning_rate": 7.818933286337578e-06,
|
| 1640 |
+
"loss": 0.932429313659668,
|
| 1641 |
+
"step": 2330
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.8077089026319574,
|
| 1645 |
+
"grad_norm": 0.7578125,
|
| 1646 |
+
"learning_rate": 7.555442518021188e-06,
|
| 1647 |
+
"loss": 0.9372527122497558,
|
| 1648 |
+
"step": 2340
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.8111606500791025,
|
| 1652 |
+
"grad_norm": 0.76171875,
|
| 1653 |
+
"learning_rate": 7.296004178464389e-06,
|
| 1654 |
+
"loss": 0.9385522842407227,
|
| 1655 |
+
"step": 2350
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.8146123975262477,
|
| 1659 |
+
"grad_norm": 0.75390625,
|
| 1660 |
+
"learning_rate": 7.040650672343629e-06,
|
| 1661 |
+
"loss": 0.9442752838134766,
|
| 1662 |
+
"step": 2360
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.8180641449733927,
|
| 1666 |
+
"grad_norm": 0.76171875,
|
| 1667 |
+
"learning_rate": 6.7894138941266665e-06,
|
| 1668 |
+
"loss": 0.950474739074707,
|
| 1669 |
+
"step": 2370
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.8215158924205379,
|
| 1673 |
+
"grad_norm": 0.76171875,
|
| 1674 |
+
"learning_rate": 6.542325224088797e-06,
|
| 1675 |
+
"loss": 0.9400257110595703,
|
| 1676 |
+
"step": 2380
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.8249676398676831,
|
| 1680 |
+
"grad_norm": 0.796875,
|
| 1681 |
+
"learning_rate": 6.299415524393353e-06,
|
| 1682 |
+
"loss": 0.9504306793212891,
|
| 1683 |
+
"step": 2390
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.8284193873148281,
|
| 1687 |
+
"grad_norm": 0.76171875,
|
| 1688 |
+
"learning_rate": 6.06071513523697e-06,
|
| 1689 |
+
"loss": 0.9445967674255371,
|
| 1690 |
+
"step": 2400
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.8318711347619733,
|
| 1694 |
+
"grad_norm": 0.7578125,
|
| 1695 |
+
"learning_rate": 5.8262538710599145e-06,
|
| 1696 |
+
"loss": 0.9407167434692383,
|
| 1697 |
+
"step": 2410
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.8353228822091183,
|
| 1701 |
+
"grad_norm": 0.74609375,
|
| 1702 |
+
"learning_rate": 5.596061016822259e-06,
|
| 1703 |
+
"loss": 0.9380212783813476,
|
| 1704 |
+
"step": 2420
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.8387746296562635,
|
| 1708 |
+
"grad_norm": 0.78125,
|
| 1709 |
+
"learning_rate": 5.370165324346035e-06,
|
| 1710 |
+
"loss": 0.9472208023071289,
|
| 1711 |
+
"step": 2430
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.8422263771034086,
|
| 1715 |
+
"grad_norm": 0.7578125,
|
| 1716 |
+
"learning_rate": 5.1485950087240665e-06,
|
| 1717 |
+
"loss": 0.9303070068359375,
|
| 1718 |
+
"step": 2440
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.8456781245505537,
|
| 1722 |
+
"grad_norm": 0.7578125,
|
| 1723 |
+
"learning_rate": 4.931377744795809e-06,
|
| 1724 |
+
"loss": 0.9381135940551758,
|
| 1725 |
+
"step": 2450
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.8491298719976988,
|
| 1729 |
+
"grad_norm": 0.7734375,
|
| 1730 |
+
"learning_rate": 4.718540663690649e-06,
|
| 1731 |
+
"loss": 0.9244848251342773,
|
| 1732 |
+
"step": 2460
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 0.852581619444844,
|
| 1736 |
+
"grad_norm": 0.75,
|
| 1737 |
+
"learning_rate": 4.510110349439183e-06,
|
| 1738 |
+
"loss": 0.9374746322631836,
|
| 1739 |
+
"step": 2470
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 0.8560333668919891,
|
| 1743 |
+
"grad_norm": 0.80078125,
|
| 1744 |
+
"learning_rate": 4.306112835652756e-06,
|
| 1745 |
+
"loss": 0.9379067420959473,
|
| 1746 |
+
"step": 2480
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.8594851143391342,
|
| 1750 |
+
"grad_norm": 0.765625,
|
| 1751 |
+
"learning_rate": 4.106573602271801e-06,
|
| 1752 |
+
"loss": 0.951326560974121,
|
| 1753 |
+
"step": 2490
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.8629368617862793,
|
| 1757 |
+
"grad_norm": 0.75390625,
|
| 1758 |
+
"learning_rate": 3.911517572383292e-06,
|
| 1759 |
+
"loss": 0.9295871734619141,
|
| 1760 |
+
"step": 2500
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 0.8663886092334244,
|
| 1764 |
+
"grad_norm": 0.78125,
|
| 1765 |
+
"learning_rate": 3.720969109107775e-06,
|
| 1766 |
+
"loss": 0.9208388328552246,
|
| 1767 |
+
"step": 2510
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.8698403566805696,
|
| 1771 |
+
"grad_norm": 0.75,
|
| 1772 |
+
"learning_rate": 3.534952012556354e-06,
|
| 1773 |
+
"loss": 0.9313371658325196,
|
| 1774 |
+
"step": 2520
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 0.8732921041277146,
|
| 1778 |
+
"grad_norm": 0.76171875,
|
| 1779 |
+
"learning_rate": 3.3534895168579663e-06,
|
| 1780 |
+
"loss": 0.9477436065673828,
|
| 1781 |
+
"step": 2530
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 0.8767438515748598,
|
| 1785 |
+
"grad_norm": 0.7578125,
|
| 1786 |
+
"learning_rate": 3.176604287257372e-06,
|
| 1787 |
+
"loss": 0.92279052734375,
|
| 1788 |
+
"step": 2540
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 0.8801955990220048,
|
| 1792 |
+
"grad_norm": 0.75,
|
| 1793 |
+
"learning_rate": 3.004318417284191e-06,
|
| 1794 |
+
"loss": 0.9524429321289063,
|
| 1795 |
+
"step": 2550
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.88364734646915,
|
| 1799 |
+
"grad_norm": 0.765625,
|
| 1800 |
+
"learning_rate": 2.8366534259933255e-06,
|
| 1801 |
+
"loss": 0.948516845703125,
|
| 1802 |
+
"step": 2560
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.8870990939162952,
|
| 1806 |
+
"grad_norm": 0.765625,
|
| 1807 |
+
"learning_rate": 2.6736302552772265e-06,
|
| 1808 |
+
"loss": 0.9425224304199219,
|
| 1809 |
+
"step": 2570
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.8905508413634402,
|
| 1813 |
+
"grad_norm": 0.76953125,
|
| 1814 |
+
"learning_rate": 2.5152692672500936e-06,
|
| 1815 |
+
"loss": 0.9382649421691894,
|
| 1816 |
+
"step": 2580
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.8940025888105854,
|
| 1820 |
+
"grad_norm": 0.7734375,
|
| 1821 |
+
"learning_rate": 2.36159024170469e-06,
|
| 1822 |
+
"loss": 0.9364921569824218,
|
| 1823 |
+
"step": 2590
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 0.8974543362577305,
|
| 1827 |
+
"grad_norm": 0.765625,
|
| 1828 |
+
"learning_rate": 2.2126123736416716e-06,
|
| 1829 |
+
"loss": 0.9333547592163086,
|
| 1830 |
+
"step": 2600
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 0.9009060837048756,
|
| 1834 |
+
"grad_norm": 0.765625,
|
| 1835 |
+
"learning_rate": 2.068354270872153e-06,
|
| 1836 |
+
"loss": 0.9437971115112305,
|
| 1837 |
+
"step": 2610
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 0.9043578311520207,
|
| 1841 |
+
"grad_norm": 0.76171875,
|
| 1842 |
+
"learning_rate": 1.9288339516934986e-06,
|
| 1843 |
+
"loss": 0.9531129837036133,
|
| 1844 |
+
"step": 2620
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 0.9078095785991658,
|
| 1848 |
+
"grad_norm": 0.734375,
|
| 1849 |
+
"learning_rate": 1.7940688426387697e-06,
|
| 1850 |
+
"loss": 0.9300472259521484,
|
| 1851 |
+
"step": 2630
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 0.9112613260463109,
|
| 1855 |
+
"grad_norm": 0.7734375,
|
| 1856 |
+
"learning_rate": 1.6640757763001403e-06,
|
| 1857 |
+
"loss": 0.94761962890625,
|
| 1858 |
+
"step": 2640
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 0.9147130734934561,
|
| 1862 |
+
"grad_norm": 0.7734375,
|
| 1863 |
+
"learning_rate": 1.538870989226382e-06,
|
| 1864 |
+
"loss": 0.9350144386291503,
|
| 1865 |
+
"step": 2650
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 0.9181648209406011,
|
| 1869 |
+
"grad_norm": 0.7578125,
|
| 1870 |
+
"learning_rate": 1.4184701198949369e-06,
|
| 1871 |
+
"loss": 0.9467386245727539,
|
| 1872 |
+
"step": 2660
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 0.9216165683877463,
|
| 1876 |
+
"grad_norm": 0.76171875,
|
| 1877 |
+
"learning_rate": 1.3028882067585858e-06,
|
| 1878 |
+
"loss": 0.9381326675415039,
|
| 1879 |
+
"step": 2670
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 0.9250683158348915,
|
| 1883 |
+
"grad_norm": 0.76171875,
|
| 1884 |
+
"learning_rate": 1.1921396863670841e-06,
|
| 1885 |
+
"loss": 0.9335201263427735,
|
| 1886 |
+
"step": 2680
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 0.9285200632820365,
|
| 1890 |
+
"grad_norm": 0.75390625,
|
| 1891 |
+
"learning_rate": 1.086238391564045e-06,
|
| 1892 |
+
"loss": 0.944271469116211,
|
| 1893 |
+
"step": 2690
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 0.9319718107291817,
|
| 1897 |
+
"grad_norm": 0.7578125,
|
| 1898 |
+
"learning_rate": 9.851975497591027e-07,
|
| 1899 |
+
"loss": 0.9337182998657226,
|
| 1900 |
+
"step": 2700
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 0.9354235581763267,
|
| 1904 |
+
"grad_norm": 0.76953125,
|
| 1905 |
+
"learning_rate": 8.890297812758253e-07,
|
| 1906 |
+
"loss": 0.945615291595459,
|
| 1907 |
+
"step": 2710
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 0.9388753056234719,
|
| 1911 |
+
"grad_norm": 0.7578125,
|
| 1912 |
+
"learning_rate": 7.977470977753677e-07,
|
| 1913 |
+
"loss": 0.9525587081909179,
|
| 1914 |
+
"step": 2720
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 0.942327053070617,
|
| 1918 |
+
"grad_norm": 0.76171875,
|
| 1919 |
+
"learning_rate": 7.113609007561728e-07,
|
| 1920 |
+
"loss": 0.9303067207336426,
|
| 1921 |
+
"step": 2730
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 0.9457788005177621,
|
| 1925 |
+
"grad_norm": 0.734375,
|
| 1926 |
+
"learning_rate": 6.298819801299205e-07,
|
| 1927 |
+
"loss": 0.9274295806884766,
|
| 1928 |
+
"step": 2740
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 0.9492305479649072,
|
| 1932 |
+
"grad_norm": 0.765625,
|
| 1933 |
+
"learning_rate": 5.533205128737784e-07,
|
| 1934 |
+
"loss": 0.9364825248718261,
|
| 1935 |
+
"step": 2750
|
| 1936 |
+
}
|
| 1937 |
+
],
|
| 1938 |
+
"logging_steps": 10,
|
| 1939 |
+
"max_steps": 2898,
|
| 1940 |
+
"num_input_tokens_seen": 0,
|
| 1941 |
+
"num_train_epochs": 1,
|
| 1942 |
+
"save_steps": 2753,
|
| 1943 |
+
"stateful_callbacks": {
|
| 1944 |
+
"TrainerControl": {
|
| 1945 |
+
"args": {
|
| 1946 |
+
"should_epoch_stop": false,
|
| 1947 |
+
"should_evaluate": false,
|
| 1948 |
+
"should_log": false,
|
| 1949 |
+
"should_save": true,
|
| 1950 |
+
"should_training_stop": false
|
| 1951 |
+
},
|
| 1952 |
+
"attributes": {}
|
| 1953 |
+
}
|
| 1954 |
+
},
|
| 1955 |
+
"total_flos": 2.7642074957894124e+18,
|
| 1956 |
+
"train_batch_size": 1,
|
| 1957 |
+
"trial_name": null,
|
| 1958 |
+
"trial_params": null
|
| 1959 |
+
}
|
checkpoint-2753/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c00323e7d22f125e4284fe279e3e5612f52b1454ed1932570e49d9183383f84c
|
| 3 |
+
size 5265
|