Training in progress, step 400
Browse files- chat_template.jinja +4 -0
- config.json +55 -0
- generation_config.json +10 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +0 -0
- special_tokens_map.json +36 -0
- tokenizer.json +0 -0
- tokenizer_config.json +83 -0
- trainer_log.jsonl +410 -0
- training_args.bin +3 -0
chat_template.jinja
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{bos_token}}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
|
| 2 |
+
' + message['content'] + '<|im_end|>' + '
|
| 3 |
+
'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
|
| 4 |
+
' }}{% endif %}
|
config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BailingMoeV2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"auto_map": {
|
| 7 |
+
"AutoConfig": "configuration_bailing_moe_v2.BailingMoeV2Config",
|
| 8 |
+
"AutoModel": "modeling_bailing_moe_v2.BailingMoeV2ForCausalLM",
|
| 9 |
+
"AutoModelForCausalLM": "modeling_bailing_moe_v2.BailingMoeV2ForCausalLM"
|
| 10 |
+
},
|
| 11 |
+
"bos_token_id": 1,
|
| 12 |
+
"dtype": "float32",
|
| 13 |
+
"embedding_dropout": 0.0,
|
| 14 |
+
"eos_token_id": 4,
|
| 15 |
+
"first_k_dense_replace": 1,
|
| 16 |
+
"head_dim": 128,
|
| 17 |
+
"hidden_act": "silu",
|
| 18 |
+
"hidden_size": 2048,
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 2048,
|
| 21 |
+
"max_position_embeddings": 8192,
|
| 22 |
+
"max_window_layers": 20,
|
| 23 |
+
"moe_intermediate_size": 320,
|
| 24 |
+
"moe_router_enable_expert_bias": true,
|
| 25 |
+
"moe_shared_expert_intermediate_size": 320,
|
| 26 |
+
"mtp_loss_scaling_factor": 0,
|
| 27 |
+
"n_group": 8,
|
| 28 |
+
"norm_topk_prob": true,
|
| 29 |
+
"num_attention_heads": 16,
|
| 30 |
+
"num_experts": 128,
|
| 31 |
+
"num_experts_per_tok": 4,
|
| 32 |
+
"num_hidden_layers": 16,
|
| 33 |
+
"num_key_value_heads": 4,
|
| 34 |
+
"num_nextn_predict_layers": 0,
|
| 35 |
+
"num_shared_experts": 1,
|
| 36 |
+
"output_dropout": 0.0,
|
| 37 |
+
"output_router_logits": false,
|
| 38 |
+
"pad_token_id": 2,
|
| 39 |
+
"partial_rotary_factor": 0.5,
|
| 40 |
+
"rms_norm_eps": 1e-06,
|
| 41 |
+
"rope_scaling": null,
|
| 42 |
+
"rope_theta": 84000,
|
| 43 |
+
"routed_scaling_factor": 2.5,
|
| 44 |
+
"router_dtype": "fp32",
|
| 45 |
+
"score_function": "sigmoid",
|
| 46 |
+
"tie_word_embeddings": false,
|
| 47 |
+
"topk_group": 2,
|
| 48 |
+
"transformers_version": "4.57.1",
|
| 49 |
+
"use_bias": false,
|
| 50 |
+
"use_cache": false,
|
| 51 |
+
"use_qk_norm": true,
|
| 52 |
+
"use_qkv_bias": false,
|
| 53 |
+
"use_rmsnorm": true,
|
| 54 |
+
"vocab_size": 32000
|
| 55 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
4,
|
| 6 |
+
2
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 2,
|
| 9 |
+
"transformers_version": "4.57.1"
|
| 10 |
+
}
|
model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf5276170a8313c02d11eca56f9933f29cad58c7e62298850bfffd3833ffd97d
|
| 3 |
+
size 4998862488
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:301fbf39d1136c39bf8d90bff16beb99819e563a7ea7ab7f53a13d38236e4481
|
| 3 |
+
size 4999401880
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eff7a35a85f5ae9d26d3621d059dc5a84b2d0ced3e9573fab888cc745bcde2a8
|
| 3 |
+
size 4998338416
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5256cbea3bb3d076d6b246e13742f02f7797eb2ced6d28f3218be9b4d629d67
|
| 3 |
+
size 1483309808
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<tool_call>",
|
| 6 |
+
"</tool_call>"
|
| 7 |
+
],
|
| 8 |
+
"bos_token": {
|
| 9 |
+
"content": "<s>",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": false,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
},
|
| 15 |
+
"eos_token": {
|
| 16 |
+
"content": "<|im_end|>",
|
| 17 |
+
"lstrip": false,
|
| 18 |
+
"normalized": false,
|
| 19 |
+
"rstrip": false,
|
| 20 |
+
"single_word": false
|
| 21 |
+
},
|
| 22 |
+
"pad_token": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false
|
| 28 |
+
},
|
| 29 |
+
"unk_token": {
|
| 30 |
+
"content": "<unk>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false
|
| 35 |
+
}
|
| 36 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"3": {
|
| 31 |
+
"content": "<|im_start|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"4": {
|
| 39 |
+
"content": "<|im_end|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"5": {
|
| 47 |
+
"content": "<tool_call>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"6": {
|
| 55 |
+
"content": "</tool_call>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": true
|
| 61 |
+
}
|
| 62 |
+
},
|
| 63 |
+
"additional_special_tokens": [
|
| 64 |
+
"<|im_start|>",
|
| 65 |
+
"<|im_end|>",
|
| 66 |
+
"<tool_call>",
|
| 67 |
+
"</tool_call>"
|
| 68 |
+
],
|
| 69 |
+
"bos_token": "<s>",
|
| 70 |
+
"clean_up_tokenization_spaces": false,
|
| 71 |
+
"eos_token": "<|im_end|>",
|
| 72 |
+
"extra_special_tokens": {},
|
| 73 |
+
"legacy": true,
|
| 74 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 75 |
+
"pad_token": "</s>",
|
| 76 |
+
"padding_side": "right",
|
| 77 |
+
"sp_model_kwargs": {},
|
| 78 |
+
"spaces_between_special_tokens": false,
|
| 79 |
+
"split_special_tokens": false,
|
| 80 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 81 |
+
"unk_token": "<unk>",
|
| 82 |
+
"use_default_system_prompt": false
|
| 83 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,410 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 1, "total_steps": 6821, "loss": 3.9321, "lr": 7.5e-05, "epoch": 0.00014660606949127694, "percentage": 0.01, "elapsed_time": "0:00:10", "remaining_time": "19:15:37"}
|
| 2 |
+
{"current_steps": 2, "total_steps": 6821, "loss": 3.4287, "lr": 7.5e-05, "epoch": 0.00029321213898255387, "percentage": 0.03, "elapsed_time": "0:00:18", "remaining_time": "17:38:01"}
|
| 3 |
+
{"current_steps": 3, "total_steps": 6821, "loss": 3.2257, "lr": 7.5e-05, "epoch": 0.00043981820847383083, "percentage": 0.04, "elapsed_time": "0:00:27", "remaining_time": "17:05:15"}
|
| 4 |
+
{"current_steps": 4, "total_steps": 6821, "loss": 3.3636, "lr": 7.5e-05, "epoch": 0.0005864242779651077, "percentage": 0.06, "elapsed_time": "0:00:35", "remaining_time": "16:48:56"}
|
| 5 |
+
{"current_steps": 5, "total_steps": 6821, "loss": 2.9323, "lr": 7.5e-05, "epoch": 0.0007330303474563847, "percentage": 0.07, "elapsed_time": "0:00:43", "remaining_time": "16:39:32"}
|
| 6 |
+
{"current_steps": 6, "total_steps": 6821, "loss": 2.8705, "lr": 7.5e-05, "epoch": 0.0008796364169476617, "percentage": 0.09, "elapsed_time": "0:00:52", "remaining_time": "16:33:26"}
|
| 7 |
+
{"current_steps": 7, "total_steps": 6821, "loss": 2.6756, "lr": 7.5e-05, "epoch": 0.0010262424864389385, "percentage": 0.1, "elapsed_time": "0:01:00", "remaining_time": "16:28:52"}
|
| 8 |
+
{"current_steps": 8, "total_steps": 6821, "loss": 2.8735, "lr": 7.5e-05, "epoch": 0.0011728485559302155, "percentage": 0.12, "elapsed_time": "0:01:09", "remaining_time": "16:25:13"}
|
| 9 |
+
{"current_steps": 9, "total_steps": 6821, "loss": 2.7283, "lr": 7.5e-05, "epoch": 0.0013194546254214924, "percentage": 0.13, "elapsed_time": "0:01:17", "remaining_time": "16:22:34"}
|
| 10 |
+
{"current_steps": 10, "total_steps": 6821, "loss": 2.6417, "lr": 7.5e-05, "epoch": 0.0014660606949127694, "percentage": 0.15, "elapsed_time": "0:01:26", "remaining_time": "16:20:31"}
|
| 11 |
+
{"current_steps": 11, "total_steps": 6821, "loss": 2.7931, "lr": 7.5e-05, "epoch": 0.0016126667644040464, "percentage": 0.16, "elapsed_time": "0:01:34", "remaining_time": "16:18:45"}
|
| 12 |
+
{"current_steps": 12, "total_steps": 6821, "loss": 2.563, "lr": 7.5e-05, "epoch": 0.0017592728338953233, "percentage": 0.18, "elapsed_time": "0:01:43", "remaining_time": "16:17:17"}
|
| 13 |
+
{"current_steps": 13, "total_steps": 6821, "loss": 2.7372, "lr": 7.5e-05, "epoch": 0.0019058789033866003, "percentage": 0.19, "elapsed_time": "0:01:51", "remaining_time": "16:15:55"}
|
| 14 |
+
{"current_steps": 14, "total_steps": 6821, "loss": 2.6044, "lr": 7.5e-05, "epoch": 0.002052484972877877, "percentage": 0.21, "elapsed_time": "0:02:00", "remaining_time": "16:14:50"}
|
| 15 |
+
{"current_steps": 15, "total_steps": 6821, "loss": 2.5687, "lr": 7.5e-05, "epoch": 0.002199091042369154, "percentage": 0.22, "elapsed_time": "0:02:09", "remaining_time": "16:15:35"}
|
| 16 |
+
{"current_steps": 16, "total_steps": 6821, "loss": 2.7366, "lr": 7.5e-05, "epoch": 0.002345697111860431, "percentage": 0.23, "elapsed_time": "0:02:17", "remaining_time": "16:14:37"}
|
| 17 |
+
{"current_steps": 17, "total_steps": 6821, "loss": 2.741, "lr": 7.5e-05, "epoch": 0.002492303181351708, "percentage": 0.25, "elapsed_time": "0:02:25", "remaining_time": "16:13:46"}
|
| 18 |
+
{"current_steps": 18, "total_steps": 6821, "loss": 2.4769, "lr": 7.5e-05, "epoch": 0.002638909250842985, "percentage": 0.26, "elapsed_time": "0:02:34", "remaining_time": "16:12:54"}
|
| 19 |
+
{"current_steps": 19, "total_steps": 6821, "loss": 2.5892, "lr": 7.5e-05, "epoch": 0.002785515320334262, "percentage": 0.28, "elapsed_time": "0:02:42", "remaining_time": "16:12:11"}
|
| 20 |
+
{"current_steps": 20, "total_steps": 6821, "loss": 2.63, "lr": 7.5e-05, "epoch": 0.002932121389825539, "percentage": 0.29, "elapsed_time": "0:02:51", "remaining_time": "16:11:37"}
|
| 21 |
+
{"current_steps": 21, "total_steps": 6821, "loss": 2.4919, "lr": 7.5e-05, "epoch": 0.0030787274593168158, "percentage": 0.31, "elapsed_time": "0:03:00", "remaining_time": "16:12:31"}
|
| 22 |
+
{"current_steps": 22, "total_steps": 6821, "loss": 2.5155, "lr": 7.5e-05, "epoch": 0.0032253335288080927, "percentage": 0.32, "elapsed_time": "0:03:08", "remaining_time": "16:11:53"}
|
| 23 |
+
{"current_steps": 23, "total_steps": 6821, "loss": 2.5791, "lr": 7.5e-05, "epoch": 0.0033719395982993697, "percentage": 0.34, "elapsed_time": "0:03:17", "remaining_time": "16:11:17"}
|
| 24 |
+
{"current_steps": 24, "total_steps": 6821, "loss": 2.5228, "lr": 7.5e-05, "epoch": 0.0035185456677906467, "percentage": 0.35, "elapsed_time": "0:03:25", "remaining_time": "16:10:44"}
|
| 25 |
+
{"current_steps": 25, "total_steps": 6821, "loss": 2.3439, "lr": 7.5e-05, "epoch": 0.0036651517372819236, "percentage": 0.37, "elapsed_time": "0:03:34", "remaining_time": "16:10:11"}
|
| 26 |
+
{"current_steps": 26, "total_steps": 6821, "loss": 2.3244, "lr": 7.5e-05, "epoch": 0.0038117578067732006, "percentage": 0.38, "elapsed_time": "0:03:42", "remaining_time": "16:09:39"}
|
| 27 |
+
{"current_steps": 27, "total_steps": 6821, "loss": 2.3578, "lr": 7.5e-05, "epoch": 0.003958363876264477, "percentage": 0.4, "elapsed_time": "0:03:51", "remaining_time": "16:09:10"}
|
| 28 |
+
{"current_steps": 28, "total_steps": 6821, "loss": 2.2824, "lr": 7.5e-05, "epoch": 0.004104969945755754, "percentage": 0.41, "elapsed_time": "0:03:59", "remaining_time": "16:08:43"}
|
| 29 |
+
{"current_steps": 29, "total_steps": 6821, "loss": 2.5229, "lr": 7.5e-05, "epoch": 0.004251576015247031, "percentage": 0.43, "elapsed_time": "0:04:08", "remaining_time": "16:08:17"}
|
| 30 |
+
{"current_steps": 30, "total_steps": 6821, "loss": 2.5119, "lr": 7.5e-05, "epoch": 0.004398182084738308, "percentage": 0.44, "elapsed_time": "0:04:16", "remaining_time": "16:07:52"}
|
| 31 |
+
{"current_steps": 31, "total_steps": 6821, "loss": 2.3244, "lr": 7.5e-05, "epoch": 0.004544788154229585, "percentage": 0.45, "elapsed_time": "0:04:25", "remaining_time": "16:07:28"}
|
| 32 |
+
{"current_steps": 32, "total_steps": 6821, "loss": 2.3711, "lr": 7.5e-05, "epoch": 0.004691394223720862, "percentage": 0.47, "elapsed_time": "0:04:33", "remaining_time": "16:07:03"}
|
| 33 |
+
{"current_steps": 33, "total_steps": 6821, "loss": 2.2577, "lr": 7.5e-05, "epoch": 0.004838000293212139, "percentage": 0.48, "elapsed_time": "0:04:41", "remaining_time": "16:06:39"}
|
| 34 |
+
{"current_steps": 34, "total_steps": 6821, "loss": 2.3205, "lr": 7.5e-05, "epoch": 0.004984606362703416, "percentage": 0.5, "elapsed_time": "0:04:50", "remaining_time": "16:06:18"}
|
| 35 |
+
{"current_steps": 35, "total_steps": 6821, "loss": 2.3126, "lr": 7.5e-05, "epoch": 0.005131212432194693, "percentage": 0.51, "elapsed_time": "0:04:58", "remaining_time": "16:05:59"}
|
| 36 |
+
{"current_steps": 36, "total_steps": 6821, "loss": 2.2259, "lr": 7.5e-05, "epoch": 0.00527781850168597, "percentage": 0.53, "elapsed_time": "0:05:07", "remaining_time": "16:05:39"}
|
| 37 |
+
{"current_steps": 37, "total_steps": 6821, "loss": 2.3142, "lr": 7.5e-05, "epoch": 0.005424424571177247, "percentage": 0.54, "elapsed_time": "0:05:15", "remaining_time": "16:05:20"}
|
| 38 |
+
{"current_steps": 38, "total_steps": 6821, "loss": 2.3066, "lr": 7.5e-05, "epoch": 0.005571030640668524, "percentage": 0.56, "elapsed_time": "0:05:24", "remaining_time": "16:05:43"}
|
| 39 |
+
{"current_steps": 39, "total_steps": 6821, "loss": 2.2539, "lr": 7.5e-05, "epoch": 0.005717636710159801, "percentage": 0.57, "elapsed_time": "0:05:33", "remaining_time": "16:05:24"}
|
| 40 |
+
{"current_steps": 40, "total_steps": 6821, "loss": 2.3533, "lr": 7.5e-05, "epoch": 0.005864242779651078, "percentage": 0.59, "elapsed_time": "0:05:41", "remaining_time": "16:05:06"}
|
| 41 |
+
{"current_steps": 41, "total_steps": 6821, "loss": 2.3421, "lr": 7.5e-05, "epoch": 0.006010848849142355, "percentage": 0.6, "elapsed_time": "0:05:50", "remaining_time": "16:04:46"}
|
| 42 |
+
{"current_steps": 42, "total_steps": 6821, "loss": 2.3791, "lr": 7.5e-05, "epoch": 0.0061574549186336315, "percentage": 0.62, "elapsed_time": "0:05:58", "remaining_time": "16:04:28"}
|
| 43 |
+
{"current_steps": 43, "total_steps": 6821, "loss": 2.2347, "lr": 7.5e-05, "epoch": 0.0063040609881249085, "percentage": 0.63, "elapsed_time": "0:06:06", "remaining_time": "16:04:08"}
|
| 44 |
+
{"current_steps": 44, "total_steps": 6821, "loss": 2.173, "lr": 7.5e-05, "epoch": 0.0064506670576161855, "percentage": 0.65, "elapsed_time": "0:06:15", "remaining_time": "16:03:50"}
|
| 45 |
+
{"current_steps": 45, "total_steps": 6821, "loss": 2.2916, "lr": 7.5e-05, "epoch": 0.006597273127107462, "percentage": 0.66, "elapsed_time": "0:06:23", "remaining_time": "16:03:35"}
|
| 46 |
+
{"current_steps": 46, "total_steps": 6821, "loss": 2.3169, "lr": 7.5e-05, "epoch": 0.006743879196598739, "percentage": 0.67, "elapsed_time": "0:06:32", "remaining_time": "16:03:18"}
|
| 47 |
+
{"current_steps": 47, "total_steps": 6821, "loss": 2.2583, "lr": 7.5e-05, "epoch": 0.006890485266090016, "percentage": 0.69, "elapsed_time": "0:06:40", "remaining_time": "16:03:02"}
|
| 48 |
+
{"current_steps": 48, "total_steps": 6821, "loss": 2.3349, "lr": 7.5e-05, "epoch": 0.007037091335581293, "percentage": 0.7, "elapsed_time": "0:06:49", "remaining_time": "16:02:48"}
|
| 49 |
+
{"current_steps": 49, "total_steps": 6821, "loss": 2.255, "lr": 7.5e-05, "epoch": 0.00718369740507257, "percentage": 0.72, "elapsed_time": "0:06:57", "remaining_time": "16:02:30"}
|
| 50 |
+
{"current_steps": 50, "total_steps": 6821, "loss": 2.1964, "lr": 7.5e-05, "epoch": 0.007330303474563847, "percentage": 0.73, "elapsed_time": "0:07:06", "remaining_time": "16:02:13"}
|
| 51 |
+
{"current_steps": 51, "total_steps": 6821, "loss": 2.4647, "lr": 7.5e-05, "epoch": 0.007476909544055124, "percentage": 0.75, "elapsed_time": "0:07:14", "remaining_time": "16:01:57"}
|
| 52 |
+
{"current_steps": 52, "total_steps": 6821, "loss": 2.2066, "lr": 7.5e-05, "epoch": 0.007623515613546401, "percentage": 0.76, "elapsed_time": "0:07:23", "remaining_time": "16:01:41"}
|
| 53 |
+
{"current_steps": 53, "total_steps": 6821, "loss": 2.0961, "lr": 7.5e-05, "epoch": 0.007770121683037678, "percentage": 0.78, "elapsed_time": "0:07:31", "remaining_time": "16:01:26"}
|
| 54 |
+
{"current_steps": 54, "total_steps": 6821, "loss": 2.2117, "lr": 7.5e-05, "epoch": 0.007916727752528954, "percentage": 0.79, "elapsed_time": "0:07:40", "remaining_time": "16:01:11"}
|
| 55 |
+
{"current_steps": 55, "total_steps": 6821, "loss": 2.3412, "lr": 7.5e-05, "epoch": 0.008063333822020232, "percentage": 0.81, "elapsed_time": "0:07:48", "remaining_time": "16:01:31"}
|
| 56 |
+
{"current_steps": 56, "total_steps": 6821, "loss": 2.2027, "lr": 7.5e-05, "epoch": 0.008209939891511508, "percentage": 0.82, "elapsed_time": "0:07:57", "remaining_time": "16:01:17"}
|
| 57 |
+
{"current_steps": 57, "total_steps": 6821, "loss": 2.2667, "lr": 7.5e-05, "epoch": 0.008356545961002786, "percentage": 0.84, "elapsed_time": "0:08:05", "remaining_time": "16:01:01"}
|
| 58 |
+
{"current_steps": 58, "total_steps": 6821, "loss": 2.2747, "lr": 7.5e-05, "epoch": 0.008503152030494062, "percentage": 0.85, "elapsed_time": "0:08:14", "remaining_time": "16:00:46"}
|
| 59 |
+
{"current_steps": 59, "total_steps": 6821, "loss": 2.135, "lr": 7.5e-05, "epoch": 0.00864975809998534, "percentage": 0.86, "elapsed_time": "0:08:22", "remaining_time": "16:00:33"}
|
| 60 |
+
{"current_steps": 60, "total_steps": 6821, "loss": 2.2351, "lr": 7.5e-05, "epoch": 0.008796364169476616, "percentage": 0.88, "elapsed_time": "0:08:31", "remaining_time": "16:00:48"}
|
| 61 |
+
{"current_steps": 61, "total_steps": 6821, "loss": 2.1285, "lr": 7.5e-05, "epoch": 0.008942970238967894, "percentage": 0.89, "elapsed_time": "0:08:40", "remaining_time": "16:00:34"}
|
| 62 |
+
{"current_steps": 62, "total_steps": 6821, "loss": 2.2665, "lr": 7.5e-05, "epoch": 0.00908957630845917, "percentage": 0.91, "elapsed_time": "0:08:48", "remaining_time": "16:00:20"}
|
| 63 |
+
{"current_steps": 63, "total_steps": 6821, "loss": 2.1546, "lr": 7.5e-05, "epoch": 0.009236182377950448, "percentage": 0.92, "elapsed_time": "0:08:57", "remaining_time": "16:00:07"}
|
| 64 |
+
{"current_steps": 64, "total_steps": 6821, "loss": 2.0642, "lr": 7.5e-05, "epoch": 0.009382788447441724, "percentage": 0.94, "elapsed_time": "0:09:05", "remaining_time": "15:59:54"}
|
| 65 |
+
{"current_steps": 65, "total_steps": 6821, "loss": 2.2058, "lr": 7.5e-05, "epoch": 0.009529394516933002, "percentage": 0.95, "elapsed_time": "0:09:14", "remaining_time": "15:59:42"}
|
| 66 |
+
{"current_steps": 66, "total_steps": 6821, "loss": 2.0865, "lr": 7.5e-05, "epoch": 0.009676000586424278, "percentage": 0.97, "elapsed_time": "0:09:22", "remaining_time": "15:59:30"}
|
| 67 |
+
{"current_steps": 67, "total_steps": 6821, "loss": 2.2392, "lr": 7.5e-05, "epoch": 0.009822606655915556, "percentage": 0.98, "elapsed_time": "0:09:30", "remaining_time": "15:59:17"}
|
| 68 |
+
{"current_steps": 68, "total_steps": 6821, "loss": 2.1105, "lr": 7.5e-05, "epoch": 0.009969212725406832, "percentage": 1.0, "elapsed_time": "0:09:39", "remaining_time": "15:59:03"}
|
| 69 |
+
{"current_steps": 69, "total_steps": 6821, "loss": 2.1991, "lr": 7.5e-05, "epoch": 0.01011581879489811, "percentage": 1.01, "elapsed_time": "0:09:47", "remaining_time": "15:58:51"}
|
| 70 |
+
{"current_steps": 70, "total_steps": 6821, "loss": 2.1375, "lr": 7.5e-05, "epoch": 0.010262424864389386, "percentage": 1.03, "elapsed_time": "0:09:56", "remaining_time": "15:58:37"}
|
| 71 |
+
{"current_steps": 71, "total_steps": 6821, "loss": 2.0043, "lr": 7.5e-05, "epoch": 0.010409030933880663, "percentage": 1.04, "elapsed_time": "0:10:04", "remaining_time": "15:58:22"}
|
| 72 |
+
{"current_steps": 72, "total_steps": 6821, "loss": 2.1635, "lr": 7.5e-05, "epoch": 0.01055563700337194, "percentage": 1.06, "elapsed_time": "0:10:13", "remaining_time": "15:58:09"}
|
| 73 |
+
{"current_steps": 73, "total_steps": 6821, "loss": 2.236, "lr": 7.5e-05, "epoch": 0.010702243072863217, "percentage": 1.07, "elapsed_time": "0:10:21", "remaining_time": "15:57:57"}
|
| 74 |
+
{"current_steps": 74, "total_steps": 6821, "loss": 2.3342, "lr": 7.5e-05, "epoch": 0.010848849142354493, "percentage": 1.08, "elapsed_time": "0:10:30", "remaining_time": "15:57:45"}
|
| 75 |
+
{"current_steps": 75, "total_steps": 6821, "loss": 2.2978, "lr": 7.5e-05, "epoch": 0.01099545521184577, "percentage": 1.1, "elapsed_time": "0:10:38", "remaining_time": "15:57:32"}
|
| 76 |
+
{"current_steps": 76, "total_steps": 6821, "loss": 2.1702, "lr": 7.5e-05, "epoch": 0.011142061281337047, "percentage": 1.11, "elapsed_time": "0:10:47", "remaining_time": "15:57:20"}
|
| 77 |
+
{"current_steps": 77, "total_steps": 6821, "loss": 2.113, "lr": 7.5e-05, "epoch": 0.011288667350828323, "percentage": 1.13, "elapsed_time": "0:10:55", "remaining_time": "15:57:08"}
|
| 78 |
+
{"current_steps": 78, "total_steps": 6821, "loss": 2.1104, "lr": 7.5e-05, "epoch": 0.011435273420319601, "percentage": 1.14, "elapsed_time": "0:11:04", "remaining_time": "15:56:56"}
|
| 79 |
+
{"current_steps": 79, "total_steps": 6821, "loss": 2.2726, "lr": 7.5e-05, "epoch": 0.011581879489810877, "percentage": 1.16, "elapsed_time": "0:11:12", "remaining_time": "15:56:45"}
|
| 80 |
+
{"current_steps": 80, "total_steps": 6821, "loss": 2.2536, "lr": 7.5e-05, "epoch": 0.011728485559302155, "percentage": 1.17, "elapsed_time": "0:11:21", "remaining_time": "15:56:31"}
|
| 81 |
+
{"current_steps": 81, "total_steps": 6821, "loss": 2.061, "lr": 7.5e-05, "epoch": 0.011875091628793431, "percentage": 1.19, "elapsed_time": "0:11:29", "remaining_time": "15:56:19"}
|
| 82 |
+
{"current_steps": 82, "total_steps": 6821, "loss": 2.1805, "lr": 7.5e-05, "epoch": 0.01202169769828471, "percentage": 1.2, "elapsed_time": "0:11:38", "remaining_time": "15:56:29"}
|
| 83 |
+
{"current_steps": 83, "total_steps": 6821, "loss": 2.203, "lr": 7.5e-05, "epoch": 0.012168303767775985, "percentage": 1.22, "elapsed_time": "0:11:46", "remaining_time": "15:56:17"}
|
| 84 |
+
{"current_steps": 84, "total_steps": 6821, "loss": 2.2029, "lr": 7.5e-05, "epoch": 0.012314909837267263, "percentage": 1.23, "elapsed_time": "0:11:55", "remaining_time": "15:56:05"}
|
| 85 |
+
{"current_steps": 85, "total_steps": 6821, "loss": 2.1265, "lr": 7.5e-05, "epoch": 0.01246151590675854, "percentage": 1.25, "elapsed_time": "0:12:03", "remaining_time": "15:55:54"}
|
| 86 |
+
{"current_steps": 86, "total_steps": 6821, "loss": 2.1051, "lr": 7.5e-05, "epoch": 0.012608121976249817, "percentage": 1.26, "elapsed_time": "0:12:12", "remaining_time": "15:55:42"}
|
| 87 |
+
{"current_steps": 87, "total_steps": 6821, "loss": 1.9945, "lr": 7.5e-05, "epoch": 0.012754728045741093, "percentage": 1.28, "elapsed_time": "0:12:20", "remaining_time": "15:55:50"}
|
| 88 |
+
{"current_steps": 88, "total_steps": 6821, "loss": 2.3127, "lr": 7.5e-05, "epoch": 0.012901334115232371, "percentage": 1.29, "elapsed_time": "0:12:29", "remaining_time": "15:55:38"}
|
| 89 |
+
{"current_steps": 89, "total_steps": 6821, "loss": 2.1633, "lr": 7.5e-05, "epoch": 0.013047940184723647, "percentage": 1.3, "elapsed_time": "0:12:37", "remaining_time": "15:55:26"}
|
| 90 |
+
{"current_steps": 90, "total_steps": 6821, "loss": 2.0703, "lr": 7.5e-05, "epoch": 0.013194546254214925, "percentage": 1.32, "elapsed_time": "0:12:46", "remaining_time": "15:55:14"}
|
| 91 |
+
{"current_steps": 91, "total_steps": 6821, "loss": 2.0783, "lr": 7.5e-05, "epoch": 0.013341152323706201, "percentage": 1.33, "elapsed_time": "0:12:54", "remaining_time": "15:55:02"}
|
| 92 |
+
{"current_steps": 92, "total_steps": 6821, "loss": 2.145, "lr": 7.5e-05, "epoch": 0.013487758393197479, "percentage": 1.35, "elapsed_time": "0:13:03", "remaining_time": "15:54:50"}
|
| 93 |
+
{"current_steps": 93, "total_steps": 6821, "loss": 2.2827, "lr": 7.5e-05, "epoch": 0.013634364462688755, "percentage": 1.36, "elapsed_time": "0:13:11", "remaining_time": "15:54:39"}
|
| 94 |
+
{"current_steps": 94, "total_steps": 6821, "loss": 2.0141, "lr": 7.5e-05, "epoch": 0.013780970532180033, "percentage": 1.38, "elapsed_time": "0:13:20", "remaining_time": "15:54:28"}
|
| 95 |
+
{"current_steps": 95, "total_steps": 6821, "loss": 1.9025, "lr": 7.5e-05, "epoch": 0.013927576601671309, "percentage": 1.39, "elapsed_time": "0:13:28", "remaining_time": "15:54:17"}
|
| 96 |
+
{"current_steps": 96, "total_steps": 6821, "loss": 2.1828, "lr": 7.5e-05, "epoch": 0.014074182671162587, "percentage": 1.41, "elapsed_time": "0:13:37", "remaining_time": "15:54:07"}
|
| 97 |
+
{"current_steps": 97, "total_steps": 6821, "loss": 2.1164, "lr": 7.5e-05, "epoch": 0.014220788740653863, "percentage": 1.42, "elapsed_time": "0:13:45", "remaining_time": "15:53:55"}
|
| 98 |
+
{"current_steps": 98, "total_steps": 6821, "loss": 2.1558, "lr": 7.5e-05, "epoch": 0.01436739481014514, "percentage": 1.44, "elapsed_time": "0:13:54", "remaining_time": "15:53:44"}
|
| 99 |
+
{"current_steps": 99, "total_steps": 6821, "loss": 1.8609, "lr": 7.5e-05, "epoch": 0.014514000879636417, "percentage": 1.45, "elapsed_time": "0:14:02", "remaining_time": "15:53:33"}
|
| 100 |
+
{"current_steps": 100, "total_steps": 6821, "loss": 2.2808, "lr": 7.5e-05, "epoch": 0.014660606949127694, "percentage": 1.47, "elapsed_time": "0:14:11", "remaining_time": "15:53:22"}
|
| 101 |
+
{"current_steps": 101, "total_steps": 6821, "loss": 2.1713, "lr": 7.5e-05, "epoch": 0.01480721301861897, "percentage": 1.48, "elapsed_time": "0:14:19", "remaining_time": "15:53:12"}
|
| 102 |
+
{"current_steps": 102, "total_steps": 6821, "loss": 2.1225, "lr": 7.5e-05, "epoch": 0.014953819088110248, "percentage": 1.5, "elapsed_time": "0:14:28", "remaining_time": "15:53:01"}
|
| 103 |
+
{"current_steps": 103, "total_steps": 6821, "loss": 2.1107, "lr": 7.5e-05, "epoch": 0.015100425157601524, "percentage": 1.51, "elapsed_time": "0:14:36", "remaining_time": "15:53:07"}
|
| 104 |
+
{"current_steps": 104, "total_steps": 6821, "loss": 2.1518, "lr": 7.5e-05, "epoch": 0.015247031227092802, "percentage": 1.52, "elapsed_time": "0:14:45", "remaining_time": "15:52:55"}
|
| 105 |
+
{"current_steps": 105, "total_steps": 6821, "loss": 2.1841, "lr": 7.5e-05, "epoch": 0.015393637296584078, "percentage": 1.54, "elapsed_time": "0:14:53", "remaining_time": "15:52:44"}
|
| 106 |
+
{"current_steps": 106, "total_steps": 6821, "loss": 2.0889, "lr": 7.5e-05, "epoch": 0.015540243366075356, "percentage": 1.55, "elapsed_time": "0:15:02", "remaining_time": "15:52:33"}
|
| 107 |
+
{"current_steps": 107, "total_steps": 6821, "loss": 2.1551, "lr": 7.5e-05, "epoch": 0.015686849435566634, "percentage": 1.57, "elapsed_time": "0:15:10", "remaining_time": "15:52:22"}
|
| 108 |
+
{"current_steps": 108, "total_steps": 6821, "loss": 2.0577, "lr": 7.5e-05, "epoch": 0.01583345550505791, "percentage": 1.58, "elapsed_time": "0:15:19", "remaining_time": "15:52:11"}
|
| 109 |
+
{"current_steps": 109, "total_steps": 6821, "loss": 1.9942, "lr": 7.5e-05, "epoch": 0.015980061574549186, "percentage": 1.6, "elapsed_time": "0:15:27", "remaining_time": "15:52:00"}
|
| 110 |
+
{"current_steps": 110, "total_steps": 6821, "loss": 2.108, "lr": 7.5e-05, "epoch": 0.016126667644040464, "percentage": 1.61, "elapsed_time": "0:15:36", "remaining_time": "15:51:49"}
|
| 111 |
+
{"current_steps": 111, "total_steps": 6821, "loss": 2.1457, "lr": 7.5e-05, "epoch": 0.016273273713531742, "percentage": 1.63, "elapsed_time": "0:15:44", "remaining_time": "15:51:38"}
|
| 112 |
+
{"current_steps": 112, "total_steps": 6821, "loss": 2.1422, "lr": 7.5e-05, "epoch": 0.016419879783023016, "percentage": 1.64, "elapsed_time": "0:15:53", "remaining_time": "15:51:27"}
|
| 113 |
+
{"current_steps": 113, "total_steps": 6821, "loss": 2.0935, "lr": 7.5e-05, "epoch": 0.016566485852514294, "percentage": 1.66, "elapsed_time": "0:16:01", "remaining_time": "15:51:16"}
|
| 114 |
+
{"current_steps": 114, "total_steps": 6821, "loss": 2.0195, "lr": 7.5e-05, "epoch": 0.016713091922005572, "percentage": 1.67, "elapsed_time": "0:16:09", "remaining_time": "15:51:06"}
|
| 115 |
+
{"current_steps": 115, "total_steps": 6821, "loss": 1.8611, "lr": 7.5e-05, "epoch": 0.016859697991496846, "percentage": 1.69, "elapsed_time": "0:16:18", "remaining_time": "15:50:55"}
|
| 116 |
+
{"current_steps": 116, "total_steps": 6821, "loss": 2.0722, "lr": 7.5e-05, "epoch": 0.017006304060988124, "percentage": 1.7, "elapsed_time": "0:16:26", "remaining_time": "15:50:44"}
|
| 117 |
+
{"current_steps": 117, "total_steps": 6821, "loss": 2.2016, "lr": 7.5e-05, "epoch": 0.017152910130479402, "percentage": 1.72, "elapsed_time": "0:16:35", "remaining_time": "15:50:49"}
|
| 118 |
+
{"current_steps": 118, "total_steps": 6821, "loss": 2.2106, "lr": 7.5e-05, "epoch": 0.01729951619997068, "percentage": 1.73, "elapsed_time": "0:16:44", "remaining_time": "15:50:39"}
|
| 119 |
+
{"current_steps": 119, "total_steps": 6821, "loss": 2.0271, "lr": 7.5e-05, "epoch": 0.017446122269461954, "percentage": 1.74, "elapsed_time": "0:16:52", "remaining_time": "15:50:28"}
|
| 120 |
+
{"current_steps": 120, "total_steps": 6821, "loss": 2.1961, "lr": 7.5e-05, "epoch": 0.017592728338953232, "percentage": 1.76, "elapsed_time": "0:17:01", "remaining_time": "15:50:18"}
|
| 121 |
+
{"current_steps": 121, "total_steps": 6821, "loss": 2.0957, "lr": 7.5e-05, "epoch": 0.01773933440844451, "percentage": 1.77, "elapsed_time": "0:17:09", "remaining_time": "15:50:08"}
|
| 122 |
+
{"current_steps": 122, "total_steps": 6821, "loss": 2.0852, "lr": 7.5e-05, "epoch": 0.017885940477935788, "percentage": 1.79, "elapsed_time": "0:17:18", "remaining_time": "15:49:58"}
|
| 123 |
+
{"current_steps": 123, "total_steps": 6821, "loss": 2.1426, "lr": 7.5e-05, "epoch": 0.018032546547427062, "percentage": 1.8, "elapsed_time": "0:17:26", "remaining_time": "15:49:47"}
|
| 124 |
+
{"current_steps": 124, "total_steps": 6821, "loss": 2.0483, "lr": 7.5e-05, "epoch": 0.01817915261691834, "percentage": 1.82, "elapsed_time": "0:17:35", "remaining_time": "15:49:50"}
|
| 125 |
+
{"current_steps": 125, "total_steps": 6821, "loss": 1.8722, "lr": 7.5e-05, "epoch": 0.018325758686409618, "percentage": 1.83, "elapsed_time": "0:17:43", "remaining_time": "15:49:39"}
|
| 126 |
+
{"current_steps": 126, "total_steps": 6821, "loss": 1.9746, "lr": 7.5e-05, "epoch": 0.018472364755900895, "percentage": 1.85, "elapsed_time": "0:17:52", "remaining_time": "15:49:29"}
|
| 127 |
+
{"current_steps": 127, "total_steps": 6821, "loss": 2.072, "lr": 7.5e-05, "epoch": 0.01861897082539217, "percentage": 1.86, "elapsed_time": "0:18:00", "remaining_time": "15:49:18"}
|
| 128 |
+
{"current_steps": 128, "total_steps": 6821, "loss": 1.9591, "lr": 7.5e-05, "epoch": 0.018765576894883448, "percentage": 1.88, "elapsed_time": "0:18:09", "remaining_time": "15:49:08"}
|
| 129 |
+
{"current_steps": 129, "total_steps": 6821, "loss": 2.0391, "lr": 7.5e-05, "epoch": 0.018912182964374726, "percentage": 1.89, "elapsed_time": "0:18:17", "remaining_time": "15:48:57"}
|
| 130 |
+
{"current_steps": 130, "total_steps": 6821, "loss": 2.0232, "lr": 7.5e-05, "epoch": 0.019058789033866003, "percentage": 1.91, "elapsed_time": "0:18:26", "remaining_time": "15:48:47"}
|
| 131 |
+
{"current_steps": 131, "total_steps": 6821, "loss": 1.9756, "lr": 7.5e-05, "epoch": 0.019205395103357278, "percentage": 1.92, "elapsed_time": "0:18:34", "remaining_time": "15:48:36"}
|
| 132 |
+
{"current_steps": 132, "total_steps": 6821, "loss": 2.1631, "lr": 7.5e-05, "epoch": 0.019352001172848556, "percentage": 1.94, "elapsed_time": "0:18:42", "remaining_time": "15:48:27"}
|
| 133 |
+
{"current_steps": 133, "total_steps": 6821, "loss": 2.1718, "lr": 7.5e-05, "epoch": 0.019498607242339833, "percentage": 1.95, "elapsed_time": "0:18:51", "remaining_time": "15:48:16"}
|
| 134 |
+
{"current_steps": 134, "total_steps": 6821, "loss": 2.0615, "lr": 7.5e-05, "epoch": 0.01964521331183111, "percentage": 1.96, "elapsed_time": "0:18:59", "remaining_time": "15:48:06"}
|
| 135 |
+
{"current_steps": 135, "total_steps": 6821, "loss": 2.2379, "lr": 7.5e-05, "epoch": 0.019791819381322386, "percentage": 1.98, "elapsed_time": "0:19:08", "remaining_time": "15:47:56"}
|
| 136 |
+
{"current_steps": 136, "total_steps": 6821, "loss": 2.0977, "lr": 7.5e-05, "epoch": 0.019938425450813663, "percentage": 1.99, "elapsed_time": "0:19:16", "remaining_time": "15:47:46"}
|
| 137 |
+
{"current_steps": 137, "total_steps": 6821, "loss": 2.1296, "lr": 7.5e-05, "epoch": 0.02008503152030494, "percentage": 2.01, "elapsed_time": "0:19:25", "remaining_time": "15:47:36"}
|
| 138 |
+
{"current_steps": 138, "total_steps": 6821, "loss": 1.9683, "lr": 7.5e-05, "epoch": 0.02023163758979622, "percentage": 2.02, "elapsed_time": "0:19:33", "remaining_time": "15:47:26"}
|
| 139 |
+
{"current_steps": 139, "total_steps": 6821, "loss": 1.9183, "lr": 7.5e-05, "epoch": 0.020378243659287493, "percentage": 2.04, "elapsed_time": "0:19:42", "remaining_time": "15:47:15"}
|
| 140 |
+
{"current_steps": 140, "total_steps": 6821, "loss": 1.9961, "lr": 7.5e-05, "epoch": 0.02052484972877877, "percentage": 2.05, "elapsed_time": "0:19:50", "remaining_time": "15:47:05"}
|
| 141 |
+
{"current_steps": 141, "total_steps": 6821, "loss": 2.0988, "lr": 7.5e-05, "epoch": 0.02067145579827005, "percentage": 2.07, "elapsed_time": "0:19:59", "remaining_time": "15:46:55"}
|
| 142 |
+
{"current_steps": 142, "total_steps": 6821, "loss": 1.983, "lr": 7.5e-05, "epoch": 0.020818061867761327, "percentage": 2.08, "elapsed_time": "0:20:07", "remaining_time": "15:46:58"}
|
| 143 |
+
{"current_steps": 143, "total_steps": 6821, "loss": 2.0671, "lr": 7.5e-05, "epoch": 0.0209646679372526, "percentage": 2.1, "elapsed_time": "0:20:16", "remaining_time": "15:46:48"}
|
| 144 |
+
{"current_steps": 144, "total_steps": 6821, "loss": 2.0031, "lr": 7.5e-05, "epoch": 0.02111127400674388, "percentage": 2.11, "elapsed_time": "0:20:24", "remaining_time": "15:46:38"}
|
| 145 |
+
{"current_steps": 145, "total_steps": 6821, "loss": 2.1657, "lr": 7.5e-05, "epoch": 0.021257880076235157, "percentage": 2.13, "elapsed_time": "0:20:33", "remaining_time": "15:46:28"}
|
| 146 |
+
{"current_steps": 146, "total_steps": 6821, "loss": 1.9859, "lr": 7.5e-05, "epoch": 0.021404486145726435, "percentage": 2.14, "elapsed_time": "0:20:41", "remaining_time": "15:46:18"}
|
| 147 |
+
{"current_steps": 147, "total_steps": 6821, "loss": 2.0518, "lr": 7.5e-05, "epoch": 0.02155109221521771, "percentage": 2.16, "elapsed_time": "0:20:50", "remaining_time": "15:46:09"}
|
| 148 |
+
{"current_steps": 148, "total_steps": 6821, "loss": 2.0045, "lr": 7.5e-05, "epoch": 0.021697698284708987, "percentage": 2.17, "elapsed_time": "0:20:58", "remaining_time": "15:45:59"}
|
| 149 |
+
{"current_steps": 149, "total_steps": 6821, "loss": 2.1193, "lr": 7.5e-05, "epoch": 0.021844304354200265, "percentage": 2.18, "elapsed_time": "0:21:07", "remaining_time": "15:45:49"}
|
| 150 |
+
{"current_steps": 150, "total_steps": 6821, "loss": 2.0137, "lr": 7.5e-05, "epoch": 0.02199091042369154, "percentage": 2.2, "elapsed_time": "0:21:15", "remaining_time": "15:45:39"}
|
| 151 |
+
{"current_steps": 151, "total_steps": 6821, "loss": 2.1477, "lr": 7.5e-05, "epoch": 0.022137516493182817, "percentage": 2.21, "elapsed_time": "0:21:24", "remaining_time": "15:45:29"}
|
| 152 |
+
{"current_steps": 152, "total_steps": 6821, "loss": 1.8343, "lr": 7.5e-05, "epoch": 0.022284122562674095, "percentage": 2.23, "elapsed_time": "0:21:32", "remaining_time": "15:45:19"}
|
| 153 |
+
{"current_steps": 153, "total_steps": 6821, "loss": 2.087, "lr": 7.5e-05, "epoch": 0.022430728632165373, "percentage": 2.24, "elapsed_time": "0:21:41", "remaining_time": "15:45:10"}
|
| 154 |
+
{"current_steps": 154, "total_steps": 6821, "loss": 2.2673, "lr": 7.5e-05, "epoch": 0.022577334701656647, "percentage": 2.26, "elapsed_time": "0:21:49", "remaining_time": "15:45:00"}
|
| 155 |
+
{"current_steps": 155, "total_steps": 6821, "loss": 2.2203, "lr": 7.5e-05, "epoch": 0.022723940771147925, "percentage": 2.27, "elapsed_time": "0:21:58", "remaining_time": "15:44:50"}
|
| 156 |
+
{"current_steps": 156, "total_steps": 6821, "loss": 2.0032, "lr": 7.5e-05, "epoch": 0.022870546840639203, "percentage": 2.29, "elapsed_time": "0:22:06", "remaining_time": "15:44:40"}
|
| 157 |
+
{"current_steps": 157, "total_steps": 6821, "loss": 1.9783, "lr": 7.5e-05, "epoch": 0.02301715291013048, "percentage": 2.3, "elapsed_time": "0:22:15", "remaining_time": "15:44:31"}
|
| 158 |
+
{"current_steps": 158, "total_steps": 6821, "loss": 2.2654, "lr": 7.5e-05, "epoch": 0.023163758979621755, "percentage": 2.32, "elapsed_time": "0:22:23", "remaining_time": "15:44:20"}
|
| 159 |
+
{"current_steps": 159, "total_steps": 6821, "loss": 2.001, "lr": 7.5e-05, "epoch": 0.023310365049113033, "percentage": 2.33, "elapsed_time": "0:22:32", "remaining_time": "15:44:10"}
|
| 160 |
+
{"current_steps": 160, "total_steps": 6821, "loss": 2.1075, "lr": 7.5e-05, "epoch": 0.02345697111860431, "percentage": 2.35, "elapsed_time": "0:22:40", "remaining_time": "15:44:00"}
|
| 161 |
+
{"current_steps": 161, "total_steps": 6821, "loss": 2.0632, "lr": 7.5e-05, "epoch": 0.02360357718809559, "percentage": 2.36, "elapsed_time": "0:22:49", "remaining_time": "15:43:50"}
|
| 162 |
+
{"current_steps": 162, "total_steps": 6821, "loss": 1.8188, "lr": 7.5e-05, "epoch": 0.023750183257586863, "percentage": 2.38, "elapsed_time": "0:22:57", "remaining_time": "15:43:40"}
|
| 163 |
+
{"current_steps": 163, "total_steps": 6821, "loss": 2.1217, "lr": 7.5e-05, "epoch": 0.02389678932707814, "percentage": 2.39, "elapsed_time": "0:23:05", "remaining_time": "15:43:31"}
|
| 164 |
+
{"current_steps": 164, "total_steps": 6821, "loss": 2.1454, "lr": 7.5e-05, "epoch": 0.02404339539656942, "percentage": 2.4, "elapsed_time": "0:23:14", "remaining_time": "15:43:21"}
|
| 165 |
+
{"current_steps": 165, "total_steps": 6821, "loss": 2.081, "lr": 7.5e-05, "epoch": 0.024190001466060696, "percentage": 2.42, "elapsed_time": "0:23:22", "remaining_time": "15:43:11"}
|
| 166 |
+
{"current_steps": 166, "total_steps": 6821, "loss": 2.1135, "lr": 7.5e-05, "epoch": 0.02433660753555197, "percentage": 2.43, "elapsed_time": "0:23:31", "remaining_time": "15:43:02"}
|
| 167 |
+
{"current_steps": 167, "total_steps": 6821, "loss": 2.0341, "lr": 7.5e-05, "epoch": 0.02448321360504325, "percentage": 2.45, "elapsed_time": "0:23:40", "remaining_time": "15:43:02"}
|
| 168 |
+
{"current_steps": 168, "total_steps": 6821, "loss": 2.0308, "lr": 7.5e-05, "epoch": 0.024629819674534526, "percentage": 2.46, "elapsed_time": "0:23:48", "remaining_time": "15:42:53"}
|
| 169 |
+
{"current_steps": 169, "total_steps": 6821, "loss": 1.946, "lr": 7.5e-05, "epoch": 0.024776425744025804, "percentage": 2.48, "elapsed_time": "0:23:57", "remaining_time": "15:42:43"}
|
| 170 |
+
{"current_steps": 170, "total_steps": 6821, "loss": 1.8912, "lr": 7.5e-05, "epoch": 0.02492303181351708, "percentage": 2.49, "elapsed_time": "0:24:05", "remaining_time": "15:42:33"}
|
| 171 |
+
{"current_steps": 171, "total_steps": 6821, "loss": 2.1345, "lr": 7.5e-05, "epoch": 0.025069637883008356, "percentage": 2.51, "elapsed_time": "0:24:13", "remaining_time": "15:42:23"}
|
| 172 |
+
{"current_steps": 172, "total_steps": 6821, "loss": 1.9857, "lr": 7.5e-05, "epoch": 0.025216243952499634, "percentage": 2.52, "elapsed_time": "0:24:22", "remaining_time": "15:42:14"}
|
| 173 |
+
{"current_steps": 173, "total_steps": 6821, "loss": 2.2985, "lr": 7.5e-05, "epoch": 0.025362850021990912, "percentage": 2.54, "elapsed_time": "0:24:30", "remaining_time": "15:42:04"}
|
| 174 |
+
{"current_steps": 174, "total_steps": 6821, "loss": 2.0616, "lr": 7.5e-05, "epoch": 0.025509456091482186, "percentage": 2.55, "elapsed_time": "0:24:39", "remaining_time": "15:41:55"}
|
| 175 |
+
{"current_steps": 175, "total_steps": 6821, "loss": 2.0837, "lr": 7.5e-05, "epoch": 0.025656062160973464, "percentage": 2.57, "elapsed_time": "0:24:47", "remaining_time": "15:41:45"}
|
| 176 |
+
{"current_steps": 176, "total_steps": 6821, "loss": 1.9485, "lr": 7.5e-05, "epoch": 0.025802668230464742, "percentage": 2.58, "elapsed_time": "0:24:56", "remaining_time": "15:41:36"}
|
| 177 |
+
{"current_steps": 177, "total_steps": 6821, "loss": 2.0481, "lr": 7.5e-05, "epoch": 0.02594927429995602, "percentage": 2.59, "elapsed_time": "0:25:04", "remaining_time": "15:41:26"}
|
| 178 |
+
{"current_steps": 178, "total_steps": 6821, "loss": 2.0739, "lr": 7.5e-05, "epoch": 0.026095880369447294, "percentage": 2.61, "elapsed_time": "0:25:13", "remaining_time": "15:41:17"}
|
| 179 |
+
{"current_steps": 179, "total_steps": 6821, "loss": 1.9752, "lr": 7.5e-05, "epoch": 0.026242486438938572, "percentage": 2.62, "elapsed_time": "0:25:21", "remaining_time": "15:41:08"}
|
| 180 |
+
{"current_steps": 180, "total_steps": 6821, "loss": 1.9936, "lr": 7.5e-05, "epoch": 0.02638909250842985, "percentage": 2.64, "elapsed_time": "0:25:30", "remaining_time": "15:40:58"}
|
| 181 |
+
{"current_steps": 181, "total_steps": 6821, "loss": 2.1459, "lr": 7.5e-05, "epoch": 0.026535698577921128, "percentage": 2.65, "elapsed_time": "0:25:38", "remaining_time": "15:40:49"}
|
| 182 |
+
{"current_steps": 182, "total_steps": 6821, "loss": 1.8207, "lr": 7.5e-05, "epoch": 0.026682304647412402, "percentage": 2.67, "elapsed_time": "0:25:47", "remaining_time": "15:40:40"}
|
| 183 |
+
{"current_steps": 183, "total_steps": 6821, "loss": 1.8318, "lr": 7.5e-05, "epoch": 0.02682891071690368, "percentage": 2.68, "elapsed_time": "0:25:55", "remaining_time": "15:40:30"}
|
| 184 |
+
{"current_steps": 184, "total_steps": 6821, "loss": 2.214, "lr": 7.5e-05, "epoch": 0.026975516786394958, "percentage": 2.7, "elapsed_time": "0:26:04", "remaining_time": "15:40:21"}
|
| 185 |
+
{"current_steps": 185, "total_steps": 6821, "loss": 2.0237, "lr": 7.5e-05, "epoch": 0.027122122855886235, "percentage": 2.71, "elapsed_time": "0:26:12", "remaining_time": "15:40:11"}
|
| 186 |
+
{"current_steps": 186, "total_steps": 6821, "loss": 1.9279, "lr": 7.5e-05, "epoch": 0.02726872892537751, "percentage": 2.73, "elapsed_time": "0:26:21", "remaining_time": "15:40:02"}
|
| 187 |
+
{"current_steps": 187, "total_steps": 6821, "loss": 2.1235, "lr": 7.5e-05, "epoch": 0.027415334994868788, "percentage": 2.74, "elapsed_time": "0:26:29", "remaining_time": "15:39:52"}
|
| 188 |
+
{"current_steps": 188, "total_steps": 6821, "loss": 2.0662, "lr": 7.5e-05, "epoch": 0.027561941064360065, "percentage": 2.76, "elapsed_time": "0:26:38", "remaining_time": "15:39:42"}
|
| 189 |
+
{"current_steps": 189, "total_steps": 6821, "loss": 2.076, "lr": 7.5e-05, "epoch": 0.02770854713385134, "percentage": 2.77, "elapsed_time": "0:26:46", "remaining_time": "15:39:33"}
|
| 190 |
+
{"current_steps": 190, "total_steps": 6821, "loss": 2.0147, "lr": 7.5e-05, "epoch": 0.027855153203342618, "percentage": 2.79, "elapsed_time": "0:26:55", "remaining_time": "15:39:24"}
|
| 191 |
+
{"current_steps": 191, "total_steps": 6821, "loss": 1.9912, "lr": 7.5e-05, "epoch": 0.028001759272833895, "percentage": 2.8, "elapsed_time": "0:27:03", "remaining_time": "15:39:23"}
|
| 192 |
+
{"current_steps": 192, "total_steps": 6821, "loss": 2.0087, "lr": 7.5e-05, "epoch": 0.028148365342325173, "percentage": 2.81, "elapsed_time": "0:27:12", "remaining_time": "15:39:14"}
|
| 193 |
+
{"current_steps": 193, "total_steps": 6821, "loss": 1.9228, "lr": 7.5e-05, "epoch": 0.028294971411816448, "percentage": 2.83, "elapsed_time": "0:27:20", "remaining_time": "15:39:04"}
|
| 194 |
+
{"current_steps": 194, "total_steps": 6821, "loss": 1.9774, "lr": 7.5e-05, "epoch": 0.028441577481307725, "percentage": 2.84, "elapsed_time": "0:27:29", "remaining_time": "15:38:55"}
|
| 195 |
+
{"current_steps": 195, "total_steps": 6821, "loss": 2.181, "lr": 7.5e-05, "epoch": 0.028588183550799003, "percentage": 2.86, "elapsed_time": "0:27:37", "remaining_time": "15:38:45"}
|
| 196 |
+
{"current_steps": 196, "total_steps": 6821, "loss": 2.0971, "lr": 7.5e-05, "epoch": 0.02873478962029028, "percentage": 2.87, "elapsed_time": "0:27:46", "remaining_time": "15:38:35"}
|
| 197 |
+
{"current_steps": 197, "total_steps": 6821, "loss": 2.1297, "lr": 7.5e-05, "epoch": 0.028881395689781555, "percentage": 2.89, "elapsed_time": "0:27:54", "remaining_time": "15:38:26"}
|
| 198 |
+
{"current_steps": 198, "total_steps": 6821, "loss": 2.2093, "lr": 7.5e-05, "epoch": 0.029028001759272833, "percentage": 2.9, "elapsed_time": "0:28:03", "remaining_time": "15:38:16"}
|
| 199 |
+
{"current_steps": 199, "total_steps": 6821, "loss": 2.0813, "lr": 7.5e-05, "epoch": 0.02917460782876411, "percentage": 2.92, "elapsed_time": "0:28:11", "remaining_time": "15:38:06"}
|
| 200 |
+
{"current_steps": 200, "total_steps": 6821, "loss": 1.9147, "lr": 7.5e-05, "epoch": 0.02932121389825539, "percentage": 2.93, "elapsed_time": "0:28:19", "remaining_time": "15:37:56"}
|
| 201 |
+
{"current_steps": 201, "total_steps": 6821, "loss": 1.9568, "lr": 7.5e-05, "epoch": 0.029467819967746663, "percentage": 2.95, "elapsed_time": "0:28:28", "remaining_time": "15:37:47"}
|
| 202 |
+
{"current_steps": 202, "total_steps": 6821, "loss": 2.0418, "lr": 7.5e-05, "epoch": 0.02961442603723794, "percentage": 2.96, "elapsed_time": "0:28:36", "remaining_time": "15:37:38"}
|
| 203 |
+
{"current_steps": 203, "total_steps": 6821, "loss": 1.9958, "lr": 7.5e-05, "epoch": 0.02976103210672922, "percentage": 2.98, "elapsed_time": "0:28:45", "remaining_time": "15:37:37"}
|
| 204 |
+
{"current_steps": 204, "total_steps": 6821, "loss": 2.0697, "lr": 7.5e-05, "epoch": 0.029907638176220497, "percentage": 2.99, "elapsed_time": "0:28:54", "remaining_time": "15:37:27"}
|
| 205 |
+
{"current_steps": 205, "total_steps": 6821, "loss": 2.0666, "lr": 7.5e-05, "epoch": 0.03005424424571177, "percentage": 3.01, "elapsed_time": "0:29:02", "remaining_time": "15:37:18"}
|
| 206 |
+
{"current_steps": 206, "total_steps": 6821, "loss": 1.9611, "lr": 7.5e-05, "epoch": 0.03020085031520305, "percentage": 3.02, "elapsed_time": "0:29:11", "remaining_time": "15:37:08"}
|
| 207 |
+
{"current_steps": 207, "total_steps": 6821, "loss": 1.8659, "lr": 7.5e-05, "epoch": 0.030347456384694327, "percentage": 3.03, "elapsed_time": "0:29:19", "remaining_time": "15:36:59"}
|
| 208 |
+
{"current_steps": 208, "total_steps": 6821, "loss": 2.0872, "lr": 7.5e-05, "epoch": 0.030494062454185605, "percentage": 3.05, "elapsed_time": "0:29:27", "remaining_time": "15:36:50"}
|
| 209 |
+
{"current_steps": 209, "total_steps": 6821, "loss": 2.0558, "lr": 7.5e-05, "epoch": 0.03064066852367688, "percentage": 3.06, "elapsed_time": "0:29:36", "remaining_time": "15:36:41"}
|
| 210 |
+
{"current_steps": 210, "total_steps": 6821, "loss": 1.8467, "lr": 7.5e-05, "epoch": 0.030787274593168157, "percentage": 3.08, "elapsed_time": "0:29:44", "remaining_time": "15:36:31"}
|
| 211 |
+
{"current_steps": 211, "total_steps": 6821, "loss": 2.0432, "lr": 7.5e-05, "epoch": 0.030933880662659435, "percentage": 3.09, "elapsed_time": "0:29:53", "remaining_time": "15:36:22"}
|
| 212 |
+
{"current_steps": 212, "total_steps": 6821, "loss": 2.1271, "lr": 7.5e-05, "epoch": 0.031080486732150713, "percentage": 3.11, "elapsed_time": "0:30:01", "remaining_time": "15:36:13"}
|
| 213 |
+
{"current_steps": 213, "total_steps": 6821, "loss": 2.0517, "lr": 7.5e-05, "epoch": 0.031227092801641987, "percentage": 3.12, "elapsed_time": "0:30:10", "remaining_time": "15:36:03"}
|
| 214 |
+
{"current_steps": 214, "total_steps": 6821, "loss": 2.1021, "lr": 7.5e-05, "epoch": 0.03137369887113327, "percentage": 3.14, "elapsed_time": "0:30:18", "remaining_time": "15:35:54"}
|
| 215 |
+
{"current_steps": 215, "total_steps": 6821, "loss": 2.0156, "lr": 7.5e-05, "epoch": 0.03152030494062454, "percentage": 3.15, "elapsed_time": "0:30:27", "remaining_time": "15:35:54"}
|
| 216 |
+
{"current_steps": 216, "total_steps": 6821, "loss": 2.1472, "lr": 7.5e-05, "epoch": 0.03166691101011582, "percentage": 3.17, "elapsed_time": "0:30:36", "remaining_time": "15:35:45"}
|
| 217 |
+
{"current_steps": 217, "total_steps": 6821, "loss": 2.0312, "lr": 7.5e-05, "epoch": 0.0318135170796071, "percentage": 3.18, "elapsed_time": "0:30:44", "remaining_time": "15:35:35"}
|
| 218 |
+
{"current_steps": 218, "total_steps": 6821, "loss": 1.9423, "lr": 7.5e-05, "epoch": 0.03196012314909837, "percentage": 3.2, "elapsed_time": "0:30:53", "remaining_time": "15:35:25"}
|
| 219 |
+
{"current_steps": 219, "total_steps": 6821, "loss": 1.973, "lr": 7.5e-05, "epoch": 0.03210672921858965, "percentage": 3.21, "elapsed_time": "0:31:01", "remaining_time": "15:35:16"}
|
| 220 |
+
{"current_steps": 220, "total_steps": 6821, "loss": 2.1178, "lr": 7.5e-05, "epoch": 0.03225333528808093, "percentage": 3.23, "elapsed_time": "0:31:09", "remaining_time": "15:35:07"}
|
| 221 |
+
{"current_steps": 221, "total_steps": 6821, "loss": 2.0244, "lr": 7.5e-05, "epoch": 0.0323999413575722, "percentage": 3.24, "elapsed_time": "0:31:18", "remaining_time": "15:34:57"}
|
| 222 |
+
{"current_steps": 222, "total_steps": 6821, "loss": 1.9321, "lr": 7.5e-05, "epoch": 0.032546547427063484, "percentage": 3.25, "elapsed_time": "0:31:26", "remaining_time": "15:34:48"}
|
| 223 |
+
{"current_steps": 223, "total_steps": 6821, "loss": 1.9824, "lr": 7.5e-05, "epoch": 0.03269315349655476, "percentage": 3.27, "elapsed_time": "0:31:35", "remaining_time": "15:34:39"}
|
| 224 |
+
{"current_steps": 224, "total_steps": 6821, "loss": 2.0477, "lr": 7.5e-05, "epoch": 0.03283975956604603, "percentage": 3.28, "elapsed_time": "0:31:43", "remaining_time": "15:34:29"}
|
| 225 |
+
{"current_steps": 225, "total_steps": 6821, "loss": 2.0382, "lr": 7.5e-05, "epoch": 0.032986365635537314, "percentage": 3.3, "elapsed_time": "0:31:52", "remaining_time": "15:34:20"}
|
| 226 |
+
{"current_steps": 226, "total_steps": 6821, "loss": 2.0819, "lr": 7.5e-05, "epoch": 0.03313297170502859, "percentage": 3.31, "elapsed_time": "0:32:00", "remaining_time": "15:34:11"}
|
| 227 |
+
{"current_steps": 227, "total_steps": 6821, "loss": 2.0042, "lr": 7.5e-05, "epoch": 0.03327957777451986, "percentage": 3.33, "elapsed_time": "0:32:09", "remaining_time": "15:34:01"}
|
| 228 |
+
{"current_steps": 228, "total_steps": 6821, "loss": 1.9566, "lr": 7.5e-05, "epoch": 0.033426183844011144, "percentage": 3.34, "elapsed_time": "0:32:17", "remaining_time": "15:33:52"}
|
| 229 |
+
{"current_steps": 229, "total_steps": 6821, "loss": 1.868, "lr": 7.5e-05, "epoch": 0.03357278991350242, "percentage": 3.36, "elapsed_time": "0:32:26", "remaining_time": "15:33:43"}
|
| 230 |
+
{"current_steps": 230, "total_steps": 6821, "loss": 2.1045, "lr": 7.5e-05, "epoch": 0.03371939598299369, "percentage": 3.37, "elapsed_time": "0:32:34", "remaining_time": "15:33:33"}
|
| 231 |
+
{"current_steps": 231, "total_steps": 6821, "loss": 1.9538, "lr": 7.5e-05, "epoch": 0.033866002052484974, "percentage": 3.39, "elapsed_time": "0:32:43", "remaining_time": "15:33:24"}
|
| 232 |
+
{"current_steps": 232, "total_steps": 6821, "loss": 1.8945, "lr": 7.5e-05, "epoch": 0.03401260812197625, "percentage": 3.4, "elapsed_time": "0:32:51", "remaining_time": "15:33:15"}
|
| 233 |
+
{"current_steps": 233, "total_steps": 6821, "loss": 2.0934, "lr": 7.5e-05, "epoch": 0.03415921419146753, "percentage": 3.42, "elapsed_time": "0:33:00", "remaining_time": "15:33:06"}
|
| 234 |
+
{"current_steps": 234, "total_steps": 6821, "loss": 2.0817, "lr": 7.5e-05, "epoch": 0.034305820260958804, "percentage": 3.43, "elapsed_time": "0:33:08", "remaining_time": "15:32:57"}
|
| 235 |
+
{"current_steps": 235, "total_steps": 6821, "loss": 2.1362, "lr": 7.5e-05, "epoch": 0.03445242633045008, "percentage": 3.45, "elapsed_time": "0:33:17", "remaining_time": "15:32:47"}
|
| 236 |
+
{"current_steps": 236, "total_steps": 6821, "loss": 1.985, "lr": 7.5e-05, "epoch": 0.03459903239994136, "percentage": 3.46, "elapsed_time": "0:33:25", "remaining_time": "15:32:38"}
|
| 237 |
+
{"current_steps": 237, "total_steps": 6821, "loss": 2.0723, "lr": 7.5e-05, "epoch": 0.034745638469432634, "percentage": 3.47, "elapsed_time": "0:33:34", "remaining_time": "15:32:43"}
|
| 238 |
+
{"current_steps": 238, "total_steps": 6821, "loss": 1.9576, "lr": 7.5e-05, "epoch": 0.03489224453892391, "percentage": 3.49, "elapsed_time": "0:33:42", "remaining_time": "15:32:33"}
|
| 239 |
+
{"current_steps": 239, "total_steps": 6821, "loss": 1.9268, "lr": 7.5e-05, "epoch": 0.03503885060841519, "percentage": 3.5, "elapsed_time": "0:33:51", "remaining_time": "15:32:23"}
|
| 240 |
+
{"current_steps": 240, "total_steps": 6821, "loss": 1.8983, "lr": 7.5e-05, "epoch": 0.035185456677906464, "percentage": 3.52, "elapsed_time": "0:33:59", "remaining_time": "15:32:14"}
|
| 241 |
+
{"current_steps": 241, "total_steps": 6821, "loss": 2.024, "lr": 7.5e-05, "epoch": 0.035332062747397745, "percentage": 3.53, "elapsed_time": "0:34:08", "remaining_time": "15:32:05"}
|
| 242 |
+
{"current_steps": 242, "total_steps": 6821, "loss": 2.0077, "lr": 7.5e-05, "epoch": 0.03547866881688902, "percentage": 3.55, "elapsed_time": "0:34:16", "remaining_time": "15:31:56"}
|
| 243 |
+
{"current_steps": 243, "total_steps": 6821, "loss": 1.9355, "lr": 7.5e-05, "epoch": 0.035625274886380294, "percentage": 3.56, "elapsed_time": "0:34:25", "remaining_time": "15:31:47"}
|
| 244 |
+
{"current_steps": 244, "total_steps": 6821, "loss": 2.1393, "lr": 7.5e-05, "epoch": 0.035771880955871575, "percentage": 3.58, "elapsed_time": "0:34:33", "remaining_time": "15:31:38"}
|
| 245 |
+
{"current_steps": 245, "total_steps": 6821, "loss": 1.8837, "lr": 7.5e-05, "epoch": 0.03591848702536285, "percentage": 3.59, "elapsed_time": "0:34:42", "remaining_time": "15:31:29"}
|
| 246 |
+
{"current_steps": 246, "total_steps": 6821, "loss": 2.0528, "lr": 7.5e-05, "epoch": 0.036065093094854124, "percentage": 3.61, "elapsed_time": "0:34:50", "remaining_time": "15:31:20"}
|
| 247 |
+
{"current_steps": 247, "total_steps": 6821, "loss": 2.0402, "lr": 7.5e-05, "epoch": 0.036211699164345405, "percentage": 3.62, "elapsed_time": "0:34:59", "remaining_time": "15:31:10"}
|
| 248 |
+
{"current_steps": 248, "total_steps": 6821, "loss": 2.1093, "lr": 7.5e-05, "epoch": 0.03635830523383668, "percentage": 3.64, "elapsed_time": "0:35:07", "remaining_time": "15:31:01"}
|
| 249 |
+
{"current_steps": 249, "total_steps": 6821, "loss": 2.0502, "lr": 7.5e-05, "epoch": 0.03650491130332796, "percentage": 3.65, "elapsed_time": "0:35:16", "remaining_time": "15:30:52"}
|
| 250 |
+
{"current_steps": 250, "total_steps": 6821, "loss": 2.0837, "lr": 7.5e-05, "epoch": 0.036651517372819235, "percentage": 3.67, "elapsed_time": "0:35:24", "remaining_time": "15:30:43"}
|
| 251 |
+
{"current_steps": 251, "total_steps": 6821, "loss": 2.0339, "lr": 7.5e-05, "epoch": 0.03679812344231051, "percentage": 3.68, "elapsed_time": "0:35:33", "remaining_time": "15:30:34"}
|
| 252 |
+
{"current_steps": 252, "total_steps": 6821, "loss": 1.956, "lr": 7.5e-05, "epoch": 0.03694472951180179, "percentage": 3.69, "elapsed_time": "0:35:41", "remaining_time": "15:30:24"}
|
| 253 |
+
{"current_steps": 253, "total_steps": 6821, "loss": 1.8557, "lr": 7.5e-05, "epoch": 0.037091335581293065, "percentage": 3.71, "elapsed_time": "0:35:50", "remaining_time": "15:30:15"}
|
| 254 |
+
{"current_steps": 254, "total_steps": 6821, "loss": 2.1068, "lr": 7.5e-05, "epoch": 0.03723794165078434, "percentage": 3.72, "elapsed_time": "0:35:58", "remaining_time": "15:30:07"}
|
| 255 |
+
{"current_steps": 255, "total_steps": 6821, "loss": 1.9371, "lr": 7.5e-05, "epoch": 0.03738454772027562, "percentage": 3.74, "elapsed_time": "0:36:06", "remaining_time": "15:29:57"}
|
| 256 |
+
{"current_steps": 256, "total_steps": 6821, "loss": 1.9046, "lr": 7.5e-05, "epoch": 0.037531153789766895, "percentage": 3.75, "elapsed_time": "0:36:15", "remaining_time": "15:29:48"}
|
| 257 |
+
{"current_steps": 257, "total_steps": 6821, "loss": 1.9013, "lr": 7.5e-05, "epoch": 0.03767775985925818, "percentage": 3.77, "elapsed_time": "0:36:23", "remaining_time": "15:29:39"}
|
| 258 |
+
{"current_steps": 258, "total_steps": 6821, "loss": 2.0771, "lr": 7.5e-05, "epoch": 0.03782436592874945, "percentage": 3.78, "elapsed_time": "0:36:32", "remaining_time": "15:29:37"}
|
| 259 |
+
{"current_steps": 259, "total_steps": 6821, "loss": 1.9495, "lr": 7.5e-05, "epoch": 0.037970971998240725, "percentage": 3.8, "elapsed_time": "0:36:41", "remaining_time": "15:29:28"}
|
| 260 |
+
{"current_steps": 260, "total_steps": 6821, "loss": 2.1077, "lr": 7.5e-05, "epoch": 0.03811757806773201, "percentage": 3.81, "elapsed_time": "0:36:49", "remaining_time": "15:29:19"}
|
| 261 |
+
{"current_steps": 261, "total_steps": 6821, "loss": 1.9283, "lr": 7.5e-05, "epoch": 0.03826418413722328, "percentage": 3.83, "elapsed_time": "0:36:58", "remaining_time": "15:29:11"}
|
| 262 |
+
{"current_steps": 262, "total_steps": 6821, "loss": 1.944, "lr": 7.5e-05, "epoch": 0.038410790206714555, "percentage": 3.84, "elapsed_time": "0:37:06", "remaining_time": "15:29:01"}
|
| 263 |
+
{"current_steps": 263, "total_steps": 6821, "loss": 2.0917, "lr": 7.5e-05, "epoch": 0.03855739627620584, "percentage": 3.86, "elapsed_time": "0:37:15", "remaining_time": "15:28:53"}
|
| 264 |
+
{"current_steps": 264, "total_steps": 6821, "loss": 2.007, "lr": 7.5e-05, "epoch": 0.03870400234569711, "percentage": 3.87, "elapsed_time": "0:37:23", "remaining_time": "15:28:43"}
|
| 265 |
+
{"current_steps": 265, "total_steps": 6821, "loss": 1.982, "lr": 7.5e-05, "epoch": 0.038850608415188385, "percentage": 3.89, "elapsed_time": "0:37:32", "remaining_time": "15:28:34"}
|
| 266 |
+
{"current_steps": 266, "total_steps": 6821, "loss": 1.9517, "lr": 7.5e-05, "epoch": 0.03899721448467967, "percentage": 3.9, "elapsed_time": "0:37:40", "remaining_time": "15:28:26"}
|
| 267 |
+
{"current_steps": 267, "total_steps": 6821, "loss": 1.8839, "lr": 7.5e-05, "epoch": 0.03914382055417094, "percentage": 3.91, "elapsed_time": "0:37:49", "remaining_time": "15:28:23"}
|
| 268 |
+
{"current_steps": 268, "total_steps": 6821, "loss": 1.9456, "lr": 7.5e-05, "epoch": 0.03929042662366222, "percentage": 3.93, "elapsed_time": "0:37:57", "remaining_time": "15:28:14"}
|
| 269 |
+
{"current_steps": 269, "total_steps": 6821, "loss": 1.8654, "lr": 7.5e-05, "epoch": 0.0394370326931535, "percentage": 3.94, "elapsed_time": "0:38:06", "remaining_time": "15:28:05"}
|
| 270 |
+
{"current_steps": 270, "total_steps": 6821, "loss": 1.9814, "lr": 7.5e-05, "epoch": 0.03958363876264477, "percentage": 3.96, "elapsed_time": "0:38:14", "remaining_time": "15:27:56"}
|
| 271 |
+
{"current_steps": 271, "total_steps": 6821, "loss": 1.6925, "lr": 7.5e-05, "epoch": 0.03973024483213605, "percentage": 3.97, "elapsed_time": "0:38:23", "remaining_time": "15:27:47"}
|
| 272 |
+
{"current_steps": 272, "total_steps": 6821, "loss": 2.0999, "lr": 7.5e-05, "epoch": 0.03987685090162733, "percentage": 3.99, "elapsed_time": "0:38:31", "remaining_time": "15:27:38"}
|
| 273 |
+
{"current_steps": 273, "total_steps": 6821, "loss": 2.049, "lr": 7.5e-05, "epoch": 0.0400234569711186, "percentage": 4.0, "elapsed_time": "0:38:40", "remaining_time": "15:27:29"}
|
| 274 |
+
{"current_steps": 274, "total_steps": 6821, "loss": 2.1052, "lr": 7.5e-05, "epoch": 0.04017006304060988, "percentage": 4.02, "elapsed_time": "0:38:48", "remaining_time": "15:27:20"}
|
| 275 |
+
{"current_steps": 275, "total_steps": 6821, "loss": 2.0206, "lr": 7.5e-05, "epoch": 0.04031666911010116, "percentage": 4.03, "elapsed_time": "0:38:57", "remaining_time": "15:27:12"}
|
| 276 |
+
{"current_steps": 276, "total_steps": 6821, "loss": 2.1087, "lr": 7.5e-05, "epoch": 0.04046327517959244, "percentage": 4.05, "elapsed_time": "0:39:05", "remaining_time": "15:27:03"}
|
| 277 |
+
{"current_steps": 277, "total_steps": 6821, "loss": 1.9281, "lr": 7.5e-05, "epoch": 0.04060988124908371, "percentage": 4.06, "elapsed_time": "0:39:14", "remaining_time": "15:26:54"}
|
| 278 |
+
{"current_steps": 278, "total_steps": 6821, "loss": 1.8629, "lr": 7.5e-05, "epoch": 0.04075648731857499, "percentage": 4.08, "elapsed_time": "0:39:22", "remaining_time": "15:26:45"}
|
| 279 |
+
{"current_steps": 279, "total_steps": 6821, "loss": 1.8598, "lr": 7.5e-05, "epoch": 0.04090309338806627, "percentage": 4.09, "elapsed_time": "0:39:31", "remaining_time": "15:26:42"}
|
| 280 |
+
{"current_steps": 280, "total_steps": 6821, "loss": 1.9969, "lr": 7.5e-05, "epoch": 0.04104969945755754, "percentage": 4.1, "elapsed_time": "0:39:39", "remaining_time": "15:26:33"}
|
| 281 |
+
{"current_steps": 281, "total_steps": 6821, "loss": 2.0225, "lr": 7.5e-05, "epoch": 0.04119630552704882, "percentage": 4.12, "elapsed_time": "0:39:48", "remaining_time": "15:26:24"}
|
| 282 |
+
{"current_steps": 282, "total_steps": 6821, "loss": 1.9757, "lr": 7.5e-05, "epoch": 0.0413429115965401, "percentage": 4.13, "elapsed_time": "0:39:56", "remaining_time": "15:26:15"}
|
| 283 |
+
{"current_steps": 283, "total_steps": 6821, "loss": 1.8507, "lr": 7.5e-05, "epoch": 0.04148951766603137, "percentage": 4.15, "elapsed_time": "0:40:05", "remaining_time": "15:26:06"}
|
| 284 |
+
{"current_steps": 284, "total_steps": 6821, "loss": 2.0767, "lr": 7.5e-05, "epoch": 0.041636123735522654, "percentage": 4.16, "elapsed_time": "0:40:13", "remaining_time": "15:25:57"}
|
| 285 |
+
{"current_steps": 285, "total_steps": 6821, "loss": 1.8079, "lr": 7.5e-05, "epoch": 0.04178272980501393, "percentage": 4.18, "elapsed_time": "0:40:22", "remaining_time": "15:25:48"}
|
| 286 |
+
{"current_steps": 286, "total_steps": 6821, "loss": 1.7858, "lr": 7.5e-05, "epoch": 0.0419293358745052, "percentage": 4.19, "elapsed_time": "0:40:30", "remaining_time": "15:25:39"}
|
| 287 |
+
{"current_steps": 287, "total_steps": 6821, "loss": 1.9619, "lr": 7.5e-05, "epoch": 0.042075941943996484, "percentage": 4.21, "elapsed_time": "0:40:39", "remaining_time": "15:25:30"}
|
| 288 |
+
{"current_steps": 288, "total_steps": 6821, "loss": 1.9286, "lr": 7.5e-05, "epoch": 0.04222254801348776, "percentage": 4.22, "elapsed_time": "0:40:47", "remaining_time": "15:25:22"}
|
| 289 |
+
{"current_steps": 289, "total_steps": 6821, "loss": 2.0122, "lr": 7.5e-05, "epoch": 0.04236915408297903, "percentage": 4.24, "elapsed_time": "0:40:56", "remaining_time": "15:25:12"}
|
| 290 |
+
{"current_steps": 290, "total_steps": 6821, "loss": 1.9364, "lr": 7.5e-05, "epoch": 0.042515760152470314, "percentage": 4.25, "elapsed_time": "0:41:04", "remaining_time": "15:25:04"}
|
| 291 |
+
{"current_steps": 291, "total_steps": 6821, "loss": 1.8584, "lr": 7.5e-05, "epoch": 0.04266236622196159, "percentage": 4.27, "elapsed_time": "0:41:13", "remaining_time": "15:24:54"}
|
| 292 |
+
{"current_steps": 292, "total_steps": 6821, "loss": 1.922, "lr": 7.5e-05, "epoch": 0.04280897229145287, "percentage": 4.28, "elapsed_time": "0:41:21", "remaining_time": "15:24:45"}
|
| 293 |
+
{"current_steps": 293, "total_steps": 6821, "loss": 1.9382, "lr": 7.5e-05, "epoch": 0.042955578360944144, "percentage": 4.3, "elapsed_time": "0:41:29", "remaining_time": "15:24:36"}
|
| 294 |
+
{"current_steps": 294, "total_steps": 6821, "loss": 1.8899, "lr": 7.5e-05, "epoch": 0.04310218443043542, "percentage": 4.31, "elapsed_time": "0:41:38", "remaining_time": "15:24:27"}
|
| 295 |
+
{"current_steps": 295, "total_steps": 6821, "loss": 2.0752, "lr": 7.5e-05, "epoch": 0.0432487904999267, "percentage": 4.32, "elapsed_time": "0:41:46", "remaining_time": "15:24:18"}
|
| 296 |
+
{"current_steps": 296, "total_steps": 6821, "loss": 1.9763, "lr": 7.5e-05, "epoch": 0.043395396569417974, "percentage": 4.34, "elapsed_time": "0:41:55", "remaining_time": "15:24:09"}
|
| 297 |
+
{"current_steps": 297, "total_steps": 6821, "loss": 2.0579, "lr": 7.5e-05, "epoch": 0.04354200263890925, "percentage": 4.35, "elapsed_time": "0:42:04", "remaining_time": "15:24:06"}
|
| 298 |
+
{"current_steps": 298, "total_steps": 6821, "loss": 1.9657, "lr": 7.5e-05, "epoch": 0.04368860870840053, "percentage": 4.37, "elapsed_time": "0:42:12", "remaining_time": "15:23:56"}
|
| 299 |
+
{"current_steps": 299, "total_steps": 6821, "loss": 1.8716, "lr": 7.5e-05, "epoch": 0.043835214777891804, "percentage": 4.38, "elapsed_time": "0:42:21", "remaining_time": "15:23:48"}
|
| 300 |
+
{"current_steps": 300, "total_steps": 6821, "loss": 1.6846, "lr": 7.5e-05, "epoch": 0.04398182084738308, "percentage": 4.4, "elapsed_time": "0:42:29", "remaining_time": "15:23:39"}
|
| 301 |
+
{"current_steps": 301, "total_steps": 6821, "loss": 1.9749, "lr": 7.5e-05, "epoch": 0.04412842691687436, "percentage": 4.41, "elapsed_time": "0:42:38", "remaining_time": "15:23:30"}
|
| 302 |
+
{"current_steps": 302, "total_steps": 6821, "loss": 2.0843, "lr": 7.5e-05, "epoch": 0.044275032986365634, "percentage": 4.43, "elapsed_time": "0:42:46", "remaining_time": "15:23:21"}
|
| 303 |
+
{"current_steps": 303, "total_steps": 6821, "loss": 1.9617, "lr": 7.5e-05, "epoch": 0.044421639055856915, "percentage": 4.44, "elapsed_time": "0:42:54", "remaining_time": "15:23:12"}
|
| 304 |
+
{"current_steps": 304, "total_steps": 6821, "loss": 1.9084, "lr": 7.5e-05, "epoch": 0.04456824512534819, "percentage": 4.46, "elapsed_time": "0:43:03", "remaining_time": "15:23:03"}
|
| 305 |
+
{"current_steps": 305, "total_steps": 6821, "loss": 1.9012, "lr": 7.5e-05, "epoch": 0.044714851194839464, "percentage": 4.47, "elapsed_time": "0:43:11", "remaining_time": "15:22:54"}
|
| 306 |
+
{"current_steps": 306, "total_steps": 6821, "loss": 1.8549, "lr": 7.5e-05, "epoch": 0.044861457264330745, "percentage": 4.49, "elapsed_time": "0:43:20", "remaining_time": "15:22:45"}
|
| 307 |
+
{"current_steps": 307, "total_steps": 6821, "loss": 2.0108, "lr": 7.5e-05, "epoch": 0.04500806333382202, "percentage": 4.5, "elapsed_time": "0:43:28", "remaining_time": "15:22:36"}
|
| 308 |
+
{"current_steps": 308, "total_steps": 6821, "loss": 1.8809, "lr": 7.5e-05, "epoch": 0.045154669403313294, "percentage": 4.52, "elapsed_time": "0:43:37", "remaining_time": "15:22:27"}
|
| 309 |
+
{"current_steps": 309, "total_steps": 6821, "loss": 1.9013, "lr": 7.5e-05, "epoch": 0.045301275472804575, "percentage": 4.53, "elapsed_time": "0:43:45", "remaining_time": "15:22:18"}
|
| 310 |
+
{"current_steps": 310, "total_steps": 6821, "loss": 1.8061, "lr": 7.5e-05, "epoch": 0.04544788154229585, "percentage": 4.54, "elapsed_time": "0:43:54", "remaining_time": "15:22:09"}
|
| 311 |
+
{"current_steps": 311, "total_steps": 6821, "loss": 1.9598, "lr": 7.5e-05, "epoch": 0.04559448761178713, "percentage": 4.56, "elapsed_time": "0:44:02", "remaining_time": "15:22:00"}
|
| 312 |
+
{"current_steps": 312, "total_steps": 6821, "loss": 2.0047, "lr": 7.5e-05, "epoch": 0.045741093681278405, "percentage": 4.57, "elapsed_time": "0:44:11", "remaining_time": "15:21:51"}
|
| 313 |
+
{"current_steps": 313, "total_steps": 6821, "loss": 2.0501, "lr": 7.5e-05, "epoch": 0.04588769975076968, "percentage": 4.59, "elapsed_time": "0:44:19", "remaining_time": "15:21:42"}
|
| 314 |
+
{"current_steps": 314, "total_steps": 6821, "loss": 1.941, "lr": 7.5e-05, "epoch": 0.04603430582026096, "percentage": 4.6, "elapsed_time": "0:44:28", "remaining_time": "15:21:33"}
|
| 315 |
+
{"current_steps": 315, "total_steps": 6821, "loss": 1.924, "lr": 7.5e-05, "epoch": 0.046180911889752235, "percentage": 4.62, "elapsed_time": "0:44:36", "remaining_time": "15:21:24"}
|
| 316 |
+
{"current_steps": 316, "total_steps": 6821, "loss": 1.8175, "lr": 7.5e-05, "epoch": 0.04632751795924351, "percentage": 4.63, "elapsed_time": "0:44:45", "remaining_time": "15:21:15"}
|
| 317 |
+
{"current_steps": 317, "total_steps": 6821, "loss": 1.8965, "lr": 7.5e-05, "epoch": 0.04647412402873479, "percentage": 4.65, "elapsed_time": "0:44:53", "remaining_time": "15:21:06"}
|
| 318 |
+
{"current_steps": 318, "total_steps": 6821, "loss": 1.9611, "lr": 7.5e-05, "epoch": 0.046620730098226065, "percentage": 4.66, "elapsed_time": "0:45:02", "remaining_time": "15:20:58"}
|
| 319 |
+
{"current_steps": 319, "total_steps": 6821, "loss": 1.8096, "lr": 7.5e-05, "epoch": 0.04676733616771735, "percentage": 4.68, "elapsed_time": "0:45:10", "remaining_time": "15:20:49"}
|
| 320 |
+
{"current_steps": 320, "total_steps": 6821, "loss": 2.1315, "lr": 7.5e-05, "epoch": 0.04691394223720862, "percentage": 4.69, "elapsed_time": "0:45:19", "remaining_time": "15:20:40"}
|
| 321 |
+
{"current_steps": 321, "total_steps": 6821, "loss": 1.8833, "lr": 7.5e-05, "epoch": 0.047060548306699895, "percentage": 4.71, "elapsed_time": "0:45:27", "remaining_time": "15:20:31"}
|
| 322 |
+
{"current_steps": 322, "total_steps": 6821, "loss": 1.8662, "lr": 7.5e-05, "epoch": 0.04720715437619118, "percentage": 4.72, "elapsed_time": "0:45:36", "remaining_time": "15:20:22"}
|
| 323 |
+
{"current_steps": 323, "total_steps": 6821, "loss": 1.7324, "lr": 7.5e-05, "epoch": 0.04735376044568245, "percentage": 4.74, "elapsed_time": "0:45:44", "remaining_time": "15:20:18"}
|
| 324 |
+
{"current_steps": 324, "total_steps": 6821, "loss": 2.0917, "lr": 7.5e-05, "epoch": 0.047500366515173725, "percentage": 4.75, "elapsed_time": "0:45:53", "remaining_time": "15:20:09"}
|
| 325 |
+
{"current_steps": 325, "total_steps": 6821, "loss": 2.0445, "lr": 7.5e-05, "epoch": 0.04764697258466501, "percentage": 4.76, "elapsed_time": "0:46:01", "remaining_time": "15:20:01"}
|
| 326 |
+
{"current_steps": 326, "total_steps": 6821, "loss": 2.0522, "lr": 7.5e-05, "epoch": 0.04779357865415628, "percentage": 4.78, "elapsed_time": "0:46:10", "remaining_time": "15:19:52"}
|
| 327 |
+
{"current_steps": 327, "total_steps": 6821, "loss": 2.0347, "lr": 7.5e-05, "epoch": 0.04794018472364756, "percentage": 4.79, "elapsed_time": "0:46:18", "remaining_time": "15:19:43"}
|
| 328 |
+
{"current_steps": 328, "total_steps": 6821, "loss": 2.0271, "lr": 7.5e-05, "epoch": 0.04808679079313884, "percentage": 4.81, "elapsed_time": "0:46:27", "remaining_time": "15:19:34"}
|
| 329 |
+
{"current_steps": 329, "total_steps": 6821, "loss": 1.9173, "lr": 7.5e-05, "epoch": 0.04823339686263011, "percentage": 4.82, "elapsed_time": "0:46:35", "remaining_time": "15:19:25"}
|
| 330 |
+
{"current_steps": 330, "total_steps": 6821, "loss": 1.9021, "lr": 7.5e-05, "epoch": 0.04838000293212139, "percentage": 4.84, "elapsed_time": "0:46:44", "remaining_time": "15:19:16"}
|
| 331 |
+
{"current_steps": 331, "total_steps": 6821, "loss": 1.7721, "lr": 7.5e-05, "epoch": 0.04852660900161267, "percentage": 4.85, "elapsed_time": "0:46:52", "remaining_time": "15:19:07"}
|
| 332 |
+
{"current_steps": 332, "total_steps": 6821, "loss": 1.8143, "lr": 7.5e-05, "epoch": 0.04867321507110394, "percentage": 4.87, "elapsed_time": "0:47:01", "remaining_time": "15:18:58"}
|
| 333 |
+
{"current_steps": 333, "total_steps": 6821, "loss": 1.8947, "lr": 7.5e-05, "epoch": 0.04881982114059522, "percentage": 4.88, "elapsed_time": "0:47:09", "remaining_time": "15:18:49"}
|
| 334 |
+
{"current_steps": 334, "total_steps": 6821, "loss": 1.7843, "lr": 7.5e-05, "epoch": 0.0489664272100865, "percentage": 4.9, "elapsed_time": "0:47:18", "remaining_time": "15:18:41"}
|
| 335 |
+
{"current_steps": 335, "total_steps": 6821, "loss": 1.7458, "lr": 7.5e-05, "epoch": 0.04911303327957778, "percentage": 4.91, "elapsed_time": "0:47:26", "remaining_time": "15:18:32"}
|
| 336 |
+
{"current_steps": 336, "total_steps": 6821, "loss": 2.0543, "lr": 7.5e-05, "epoch": 0.04925963934906905, "percentage": 4.93, "elapsed_time": "0:47:35", "remaining_time": "15:18:23"}
|
| 337 |
+
{"current_steps": 337, "total_steps": 6821, "loss": 1.8529, "lr": 7.5e-05, "epoch": 0.04940624541856033, "percentage": 4.94, "elapsed_time": "0:47:43", "remaining_time": "15:18:14"}
|
| 338 |
+
{"current_steps": 338, "total_steps": 6821, "loss": 2.0786, "lr": 7.5e-05, "epoch": 0.04955285148805161, "percentage": 4.96, "elapsed_time": "0:47:51", "remaining_time": "15:18:05"}
|
| 339 |
+
{"current_steps": 339, "total_steps": 6821, "loss": 1.8429, "lr": 7.5e-05, "epoch": 0.04969945755754288, "percentage": 4.97, "elapsed_time": "0:48:00", "remaining_time": "15:17:57"}
|
| 340 |
+
{"current_steps": 340, "total_steps": 6821, "loss": 2.0066, "lr": 7.5e-05, "epoch": 0.04984606362703416, "percentage": 4.98, "elapsed_time": "0:48:08", "remaining_time": "15:17:48"}
|
| 341 |
+
{"current_steps": 341, "total_steps": 6821, "loss": 1.8996, "lr": 7.5e-05, "epoch": 0.04999266969652544, "percentage": 5.0, "elapsed_time": "0:48:17", "remaining_time": "15:17:39"}
|
| 342 |
+
{"current_steps": 342, "total_steps": 6821, "loss": 1.8577, "lr": 7.5e-05, "epoch": 0.05013927576601671, "percentage": 5.01, "elapsed_time": "0:48:25", "remaining_time": "15:17:30"}
|
| 343 |
+
{"current_steps": 343, "total_steps": 6821, "loss": 1.9743, "lr": 7.5e-05, "epoch": 0.05028588183550799, "percentage": 5.03, "elapsed_time": "0:48:34", "remaining_time": "15:17:21"}
|
| 344 |
+
{"current_steps": 344, "total_steps": 6821, "loss": 1.8597, "lr": 7.5e-05, "epoch": 0.05043248790499927, "percentage": 5.04, "elapsed_time": "0:48:42", "remaining_time": "15:17:12"}
|
| 345 |
+
{"current_steps": 345, "total_steps": 6821, "loss": 1.9777, "lr": 7.5e-05, "epoch": 0.05057909397449054, "percentage": 5.06, "elapsed_time": "0:48:51", "remaining_time": "15:17:03"}
|
| 346 |
+
{"current_steps": 346, "total_steps": 6821, "loss": 1.9094, "lr": 7.5e-05, "epoch": 0.050725700043981824, "percentage": 5.07, "elapsed_time": "0:48:59", "remaining_time": "15:16:54"}
|
| 347 |
+
{"current_steps": 347, "total_steps": 6821, "loss": 2.079, "lr": 7.5e-05, "epoch": 0.0508723061134731, "percentage": 5.09, "elapsed_time": "0:49:08", "remaining_time": "15:16:45"}
|
| 348 |
+
{"current_steps": 348, "total_steps": 6821, "loss": 2.0029, "lr": 7.5e-05, "epoch": 0.05101891218296437, "percentage": 5.1, "elapsed_time": "0:49:16", "remaining_time": "15:16:41"}
|
| 349 |
+
{"current_steps": 349, "total_steps": 6821, "loss": 1.8492, "lr": 7.5e-05, "epoch": 0.051165518252455654, "percentage": 5.12, "elapsed_time": "0:49:25", "remaining_time": "15:16:32"}
|
| 350 |
+
{"current_steps": 350, "total_steps": 6821, "loss": 1.9028, "lr": 7.5e-05, "epoch": 0.05131212432194693, "percentage": 5.13, "elapsed_time": "0:49:33", "remaining_time": "15:16:23"}
|
| 351 |
+
{"current_steps": 351, "total_steps": 6821, "loss": 2.0359, "lr": 7.5e-05, "epoch": 0.0514587303914382, "percentage": 5.15, "elapsed_time": "0:49:42", "remaining_time": "15:16:14"}
|
| 352 |
+
{"current_steps": 352, "total_steps": 6821, "loss": 1.9221, "lr": 7.5e-05, "epoch": 0.051605336460929484, "percentage": 5.16, "elapsed_time": "0:49:50", "remaining_time": "15:16:05"}
|
| 353 |
+
{"current_steps": 353, "total_steps": 6821, "loss": 1.9657, "lr": 7.5e-05, "epoch": 0.05175194253042076, "percentage": 5.18, "elapsed_time": "0:49:59", "remaining_time": "15:15:56"}
|
| 354 |
+
{"current_steps": 354, "total_steps": 6821, "loss": 2.0206, "lr": 7.5e-05, "epoch": 0.05189854859991204, "percentage": 5.19, "elapsed_time": "0:50:07", "remaining_time": "15:15:47"}
|
| 355 |
+
{"current_steps": 355, "total_steps": 6821, "loss": 1.9095, "lr": 7.5e-05, "epoch": 0.052045154669403314, "percentage": 5.2, "elapsed_time": "0:50:16", "remaining_time": "15:15:39"}
|
| 356 |
+
{"current_steps": 356, "total_steps": 6821, "loss": 1.9029, "lr": 7.5e-05, "epoch": 0.05219176073889459, "percentage": 5.22, "elapsed_time": "0:50:24", "remaining_time": "15:15:30"}
|
| 357 |
+
{"current_steps": 357, "total_steps": 6821, "loss": 1.8228, "lr": 7.5e-05, "epoch": 0.05233836680838587, "percentage": 5.23, "elapsed_time": "0:50:33", "remaining_time": "15:15:21"}
|
| 358 |
+
{"current_steps": 358, "total_steps": 6821, "loss": 1.8618, "lr": 7.5e-05, "epoch": 0.052484972877877144, "percentage": 5.25, "elapsed_time": "0:50:41", "remaining_time": "15:15:12"}
|
| 359 |
+
{"current_steps": 359, "total_steps": 6821, "loss": 1.7979, "lr": 7.5e-05, "epoch": 0.05263157894736842, "percentage": 5.26, "elapsed_time": "0:50:50", "remaining_time": "15:15:04"}
|
| 360 |
+
{"current_steps": 360, "total_steps": 6821, "loss": 1.9341, "lr": 7.5e-05, "epoch": 0.0527781850168597, "percentage": 5.28, "elapsed_time": "0:50:58", "remaining_time": "15:15:00"}
|
| 361 |
+
{"current_steps": 361, "total_steps": 6821, "loss": 1.931, "lr": 7.5e-05, "epoch": 0.052924791086350974, "percentage": 5.29, "elapsed_time": "0:51:07", "remaining_time": "15:14:51"}
|
| 362 |
+
{"current_steps": 362, "total_steps": 6821, "loss": 1.9289, "lr": 7.5e-05, "epoch": 0.053071397155842255, "percentage": 5.31, "elapsed_time": "0:51:15", "remaining_time": "15:14:42"}
|
| 363 |
+
{"current_steps": 363, "total_steps": 6821, "loss": 1.9849, "lr": 7.5e-05, "epoch": 0.05321800322533353, "percentage": 5.32, "elapsed_time": "0:51:24", "remaining_time": "15:14:33"}
|
| 364 |
+
{"current_steps": 364, "total_steps": 6821, "loss": 1.6929, "lr": 7.5e-05, "epoch": 0.053364609294824804, "percentage": 5.34, "elapsed_time": "0:51:32", "remaining_time": "15:14:24"}
|
| 365 |
+
{"current_steps": 365, "total_steps": 6821, "loss": 1.9159, "lr": 7.5e-05, "epoch": 0.053511215364316085, "percentage": 5.35, "elapsed_time": "0:51:41", "remaining_time": "15:14:15"}
|
| 366 |
+
{"current_steps": 366, "total_steps": 6821, "loss": 2.0082, "lr": 7.5e-05, "epoch": 0.05365782143380736, "percentage": 5.37, "elapsed_time": "0:51:49", "remaining_time": "15:14:06"}
|
| 367 |
+
{"current_steps": 367, "total_steps": 6821, "loss": 1.9033, "lr": 7.5e-05, "epoch": 0.053804427503298634, "percentage": 5.38, "elapsed_time": "0:51:58", "remaining_time": "15:13:57"}
|
| 368 |
+
{"current_steps": 368, "total_steps": 6821, "loss": 1.9682, "lr": 7.5e-05, "epoch": 0.053951033572789915, "percentage": 5.4, "elapsed_time": "0:52:06", "remaining_time": "15:13:49"}
|
| 369 |
+
{"current_steps": 369, "total_steps": 6821, "loss": 1.9626, "lr": 7.5e-05, "epoch": 0.05409763964228119, "percentage": 5.41, "elapsed_time": "0:52:15", "remaining_time": "15:13:40"}
|
| 370 |
+
{"current_steps": 370, "total_steps": 6821, "loss": 1.8855, "lr": 7.5e-05, "epoch": 0.05424424571177247, "percentage": 5.42, "elapsed_time": "0:52:23", "remaining_time": "15:13:31"}
|
| 371 |
+
{"current_steps": 371, "total_steps": 6821, "loss": 2.0028, "lr": 7.5e-05, "epoch": 0.054390851781263745, "percentage": 5.44, "elapsed_time": "0:52:32", "remaining_time": "15:13:23"}
|
| 372 |
+
{"current_steps": 372, "total_steps": 6821, "loss": 1.9301, "lr": 7.5e-05, "epoch": 0.05453745785075502, "percentage": 5.45, "elapsed_time": "0:52:40", "remaining_time": "15:13:14"}
|
| 373 |
+
{"current_steps": 373, "total_steps": 6821, "loss": 1.7457, "lr": 7.5e-05, "epoch": 0.0546840639202463, "percentage": 5.47, "elapsed_time": "0:52:49", "remaining_time": "15:13:09"}
|
| 374 |
+
{"current_steps": 374, "total_steps": 6821, "loss": 1.855, "lr": 7.5e-05, "epoch": 0.054830669989737575, "percentage": 5.48, "elapsed_time": "0:52:57", "remaining_time": "15:13:01"}
|
| 375 |
+
{"current_steps": 375, "total_steps": 6821, "loss": 1.889, "lr": 7.5e-05, "epoch": 0.05497727605922885, "percentage": 5.5, "elapsed_time": "0:53:06", "remaining_time": "15:12:52"}
|
| 376 |
+
{"current_steps": 376, "total_steps": 6821, "loss": 2.0549, "lr": 7.5e-05, "epoch": 0.05512388212872013, "percentage": 5.51, "elapsed_time": "0:53:14", "remaining_time": "15:12:43"}
|
| 377 |
+
{"current_steps": 377, "total_steps": 6821, "loss": 1.8186, "lr": 7.5e-05, "epoch": 0.055270488198211405, "percentage": 5.53, "elapsed_time": "0:53:23", "remaining_time": "15:12:34"}
|
| 378 |
+
{"current_steps": 378, "total_steps": 6821, "loss": 2.0186, "lr": 7.5e-05, "epoch": 0.05541709426770268, "percentage": 5.54, "elapsed_time": "0:53:31", "remaining_time": "15:12:25"}
|
| 379 |
+
{"current_steps": 379, "total_steps": 6821, "loss": 1.9663, "lr": 7.5e-05, "epoch": 0.05556370033719396, "percentage": 5.56, "elapsed_time": "0:53:40", "remaining_time": "15:12:16"}
|
| 380 |
+
{"current_steps": 380, "total_steps": 6821, "loss": 1.8892, "lr": 7.5e-05, "epoch": 0.055710306406685235, "percentage": 5.57, "elapsed_time": "0:53:48", "remaining_time": "15:12:07"}
|
| 381 |
+
{"current_steps": 381, "total_steps": 6821, "loss": 2.0457, "lr": 7.5e-05, "epoch": 0.055856912476176517, "percentage": 5.59, "elapsed_time": "0:53:57", "remaining_time": "15:11:59"}
|
| 382 |
+
{"current_steps": 382, "total_steps": 6821, "loss": 1.8299, "lr": 7.5e-05, "epoch": 0.05600351854566779, "percentage": 5.6, "elapsed_time": "0:54:05", "remaining_time": "15:11:50"}
|
| 383 |
+
{"current_steps": 383, "total_steps": 6821, "loss": 1.9749, "lr": 7.5e-05, "epoch": 0.056150124615159065, "percentage": 5.62, "elapsed_time": "0:54:14", "remaining_time": "15:11:41"}
|
| 384 |
+
{"current_steps": 384, "total_steps": 6821, "loss": 2.0254, "lr": 7.5e-05, "epoch": 0.056296730684650347, "percentage": 5.63, "elapsed_time": "0:54:22", "remaining_time": "15:11:32"}
|
| 385 |
+
{"current_steps": 385, "total_steps": 6821, "loss": 1.9508, "lr": 7.5e-05, "epoch": 0.05644333675414162, "percentage": 5.64, "elapsed_time": "0:54:31", "remaining_time": "15:11:23"}
|
| 386 |
+
{"current_steps": 386, "total_steps": 6821, "loss": 1.9071, "lr": 7.5e-05, "epoch": 0.056589942823632895, "percentage": 5.66, "elapsed_time": "0:54:39", "remaining_time": "15:11:14"}
|
| 387 |
+
{"current_steps": 387, "total_steps": 6821, "loss": 1.8866, "lr": 7.5e-05, "epoch": 0.05673654889312418, "percentage": 5.67, "elapsed_time": "0:54:48", "remaining_time": "15:11:05"}
|
| 388 |
+
{"current_steps": 388, "total_steps": 6821, "loss": 2.0262, "lr": 7.5e-05, "epoch": 0.05688315496261545, "percentage": 5.69, "elapsed_time": "0:54:56", "remaining_time": "15:10:56"}
|
| 389 |
+
{"current_steps": 389, "total_steps": 6821, "loss": 1.8344, "lr": 7.5e-05, "epoch": 0.05702976103210673, "percentage": 5.7, "elapsed_time": "0:55:05", "remaining_time": "15:10:47"}
|
| 390 |
+
{"current_steps": 390, "total_steps": 6821, "loss": 2.0149, "lr": 7.5e-05, "epoch": 0.05717636710159801, "percentage": 5.72, "elapsed_time": "0:55:13", "remaining_time": "15:10:39"}
|
| 391 |
+
{"current_steps": 391, "total_steps": 6821, "loss": 1.9518, "lr": 7.5e-05, "epoch": 0.05732297317108928, "percentage": 5.73, "elapsed_time": "0:55:21", "remaining_time": "15:10:29"}
|
| 392 |
+
{"current_steps": 392, "total_steps": 6821, "loss": 1.7891, "lr": 7.5e-05, "epoch": 0.05746957924058056, "percentage": 5.75, "elapsed_time": "0:55:30", "remaining_time": "15:10:21"}
|
| 393 |
+
{"current_steps": 393, "total_steps": 6821, "loss": 1.9879, "lr": 7.5e-05, "epoch": 0.05761618531007184, "percentage": 5.76, "elapsed_time": "0:55:38", "remaining_time": "15:10:12"}
|
| 394 |
+
{"current_steps": 394, "total_steps": 6821, "loss": 1.803, "lr": 7.5e-05, "epoch": 0.05776279137956311, "percentage": 5.78, "elapsed_time": "0:55:47", "remaining_time": "15:10:08"}
|
| 395 |
+
{"current_steps": 395, "total_steps": 6821, "loss": 1.8522, "lr": 7.5e-05, "epoch": 0.05790939744905439, "percentage": 5.79, "elapsed_time": "0:55:56", "remaining_time": "15:09:59"}
|
| 396 |
+
{"current_steps": 396, "total_steps": 6821, "loss": 2.0428, "lr": 7.5e-05, "epoch": 0.05805600351854567, "percentage": 5.81, "elapsed_time": "0:56:04", "remaining_time": "15:09:55"}
|
| 397 |
+
{"current_steps": 397, "total_steps": 6821, "loss": 1.9202, "lr": 7.5e-05, "epoch": 0.05820260958803695, "percentage": 5.82, "elapsed_time": "0:56:13", "remaining_time": "15:09:46"}
|
| 398 |
+
{"current_steps": 398, "total_steps": 6821, "loss": 1.752, "lr": 7.5e-05, "epoch": 0.05834921565752822, "percentage": 5.83, "elapsed_time": "0:56:21", "remaining_time": "15:09:37"}
|
| 399 |
+
{"current_steps": 399, "total_steps": 6821, "loss": 1.8941, "lr": 7.5e-05, "epoch": 0.0584958217270195, "percentage": 5.85, "elapsed_time": "0:56:30", "remaining_time": "15:09:28"}
|
| 400 |
+
{"current_steps": 400, "total_steps": 6821, "loss": 1.8073, "lr": 7.5e-05, "epoch": 0.05864242779651078, "percentage": 5.86, "elapsed_time": "0:56:38", "remaining_time": "15:09:19"}
|
| 401 |
+
{"current_steps": 400, "total_steps": 6821, "eval_loss": 1.9215489625930786, "epoch": 0.05864242779651078, "percentage": 5.86, "elapsed_time": "0:57:20", "remaining_time": "15:20:23"}
|
| 402 |
+
{"current_steps": 401, "total_steps": 6821, "loss": 1.9312, "lr": 7.5e-05, "epoch": 0.05878903386600205, "percentage": 5.88, "elapsed_time": "0:58:14", "remaining_time": "15:32:30"}
|
| 403 |
+
{"current_steps": 402, "total_steps": 6821, "loss": 1.9439, "lr": 7.5e-05, "epoch": 0.05893563993549333, "percentage": 5.89, "elapsed_time": "0:58:23", "remaining_time": "15:32:19"}
|
| 404 |
+
{"current_steps": 403, "total_steps": 6821, "loss": 1.8616, "lr": 7.5e-05, "epoch": 0.05908224600498461, "percentage": 5.91, "elapsed_time": "0:58:32", "remaining_time": "15:32:10"}
|
| 405 |
+
{"current_steps": 404, "total_steps": 6821, "loss": 1.88, "lr": 7.5e-05, "epoch": 0.05922885207447588, "percentage": 5.92, "elapsed_time": "0:58:40", "remaining_time": "15:32:01"}
|
| 406 |
+
{"current_steps": 405, "total_steps": 6821, "loss": 1.9305, "lr": 7.5e-05, "epoch": 0.059375458143967164, "percentage": 5.94, "elapsed_time": "0:58:49", "remaining_time": "15:31:55"}
|
| 407 |
+
{"current_steps": 406, "total_steps": 6821, "loss": 1.9504, "lr": 7.5e-05, "epoch": 0.05952206421345844, "percentage": 5.95, "elapsed_time": "0:58:58", "remaining_time": "15:31:45"}
|
| 408 |
+
{"current_steps": 407, "total_steps": 6821, "loss": 1.9252, "lr": 7.5e-05, "epoch": 0.05966867028294971, "percentage": 5.97, "elapsed_time": "0:59:06", "remaining_time": "15:31:34"}
|
| 409 |
+
{"current_steps": 408, "total_steps": 6821, "loss": 1.8077, "lr": 7.5e-05, "epoch": 0.059815276352440994, "percentage": 5.98, "elapsed_time": "0:59:15", "remaining_time": "15:31:24"}
|
| 410 |
+
{"current_steps": 409, "total_steps": 6821, "loss": 2.0051, "lr": 7.5e-05, "epoch": 0.05996188242193227, "percentage": 6.0, "elapsed_time": "0:59:23", "remaining_time": "15:31:13"}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:986b7fa6a0dabca697c9fdd1ee115d0c1f819a2435dd81ce56d4bd32a4b054b0
|
| 3 |
+
size 6353
|