Training in progress, step 250
Browse files- .gitattributes +1 -0
- config.json +28 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +20 -0
- tokenizer.json +3 -0
- tokenizer_config.json +77 -0
- trainer_log.jsonl +261 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"eos_token_id": 151643,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 896,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 4864,
|
| 12 |
+
"max_position_embeddings": 131072,
|
| 13 |
+
"max_window_layers": 24,
|
| 14 |
+
"model_type": "qwen2",
|
| 15 |
+
"num_attention_heads": 14,
|
| 16 |
+
"num_hidden_layers": 24,
|
| 17 |
+
"num_key_value_heads": 2,
|
| 18 |
+
"rms_norm_eps": 1e-06,
|
| 19 |
+
"rope_scaling": null,
|
| 20 |
+
"rope_theta": 1000000.0,
|
| 21 |
+
"sliding_window": null,
|
| 22 |
+
"tie_word_embeddings": true,
|
| 23 |
+
"torch_dtype": "bfloat16",
|
| 24 |
+
"transformers_version": "4.51.2",
|
| 25 |
+
"use_cache": false,
|
| 26 |
+
"use_sliding_window": false,
|
| 27 |
+
"vocab_size": 194498
|
| 28 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6ebb962b4756ede11afddc4dceb05822fa38f7b1244ca525aff1434029043f3
|
| 3 |
+
size 1064369000
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>"
|
| 5 |
+
],
|
| 6 |
+
"eos_token": {
|
| 7 |
+
"content": "<|im_end|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"pad_token": {
|
| 14 |
+
"content": "<|endoftext|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
}
|
| 20 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8ec123df4ff5fd027294ce9931a2709a061268c399250056437627ea20e304f
|
| 3 |
+
size 27868597
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"11370": {
|
| 5 |
+
"content": "/************************************************************************",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"16395": {
|
| 13 |
+
"content": "%%%%%%%%%%%%%%%%",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"33009": {
|
| 21 |
+
"content": "%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"65080": {
|
| 29 |
+
"content": "//************************************************************************",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"151643": {
|
| 37 |
+
"content": "<|endoftext|>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"151644": {
|
| 45 |
+
"content": "<|im_start|>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"151645": {
|
| 53 |
+
"content": "<|im_end|>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
}
|
| 60 |
+
},
|
| 61 |
+
"additional_special_tokens": [
|
| 62 |
+
"<|im_start|>",
|
| 63 |
+
"<|im_end|>"
|
| 64 |
+
],
|
| 65 |
+
"bos_token": null,
|
| 66 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are BanglaQwen, developed by AI4BD. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within /************************************************************************//************************************************************************ XML tags:\\n/************************************************************************\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n//************************************************************************<|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are BanglaQwen, developed by AI4BD. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n/************************************************************************\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n//************************************************************************' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n%%%%%%%%%%%%%%%%\\n' }}\n {{- message.content }}\n {{- '\\n%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
| 67 |
+
"clean_up_tokenization_spaces": false,
|
| 68 |
+
"eos_token": "<|im_end|>",
|
| 69 |
+
"errors": "replace",
|
| 70 |
+
"extra_special_tokens": {},
|
| 71 |
+
"model_max_length": 4096,
|
| 72 |
+
"pad_token": "<|endoftext|>",
|
| 73 |
+
"padding_side": "right",
|
| 74 |
+
"split_special_tokens": false,
|
| 75 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 76 |
+
"unk_token": null
|
| 77 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,261 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 1, "total_steps": 32405, "loss": 1.7607, "lr": 0.0, "epoch": 0.0001542781326174828, "percentage": 0.0, "elapsed_time": "0:00:17", "remaining_time": "6 days, 13:35:24"}
|
| 2 |
+
{"current_steps": 2, "total_steps": 32405, "loss": 1.6516, "lr": 1.0000000000000001e-07, "epoch": 0.0003085562652349656, "percentage": 0.01, "elapsed_time": "0:00:21", "remaining_time": "3 days, 23:28:42"}
|
| 3 |
+
{"current_steps": 3, "total_steps": 32405, "loss": 1.6305, "lr": 2.0000000000000002e-07, "epoch": 0.0004628343978524484, "percentage": 0.01, "elapsed_time": "0:00:25", "remaining_time": "3 days, 3:46:52"}
|
| 4 |
+
{"current_steps": 4, "total_steps": 32405, "loss": 1.7983, "lr": 3.0000000000000004e-07, "epoch": 0.0006171125304699312, "percentage": 0.01, "elapsed_time": "0:00:29", "remaining_time": "2 days, 17:21:31"}
|
| 5 |
+
{"current_steps": 5, "total_steps": 32405, "loss": 1.7083, "lr": 4.0000000000000003e-07, "epoch": 0.000771390663087414, "percentage": 0.02, "elapsed_time": "0:00:34", "remaining_time": "2 days, 14:08:58"}
|
| 6 |
+
{"current_steps": 6, "total_steps": 32405, "loss": 1.7242, "lr": 5.000000000000001e-07, "epoch": 0.0009256687957048968, "percentage": 0.02, "elapsed_time": "0:00:38", "remaining_time": "2 days, 10:27:49"}
|
| 7 |
+
{"current_steps": 7, "total_steps": 32405, "loss": 1.8766, "lr": 6.000000000000001e-07, "epoch": 0.0010799469283223795, "percentage": 0.02, "elapsed_time": "0:00:43", "remaining_time": "2 days, 7:38:42"}
|
| 8 |
+
{"current_steps": 8, "total_steps": 32405, "loss": 1.7725, "lr": 7.000000000000001e-07, "epoch": 0.0012342250609398623, "percentage": 0.02, "elapsed_time": "0:00:47", "remaining_time": "2 days, 5:01:38"}
|
| 9 |
+
{"current_steps": 9, "total_steps": 32405, "loss": 1.7809, "lr": 8.000000000000001e-07, "epoch": 0.0013885031935573452, "percentage": 0.03, "elapsed_time": "0:00:51", "remaining_time": "2 days, 3:21:34"}
|
| 10 |
+
{"current_steps": 10, "total_steps": 32405, "loss": 1.7843, "lr": 9.000000000000001e-07, "epoch": 0.001542781326174828, "percentage": 0.03, "elapsed_time": "0:00:58", "remaining_time": "2 days, 4:19:07"}
|
| 11 |
+
{"current_steps": 11, "total_steps": 32405, "loss": 1.7162, "lr": 1.0000000000000002e-06, "epoch": 0.0016970594587923107, "percentage": 0.03, "elapsed_time": "0:01:01", "remaining_time": "2 days, 2:35:29"}
|
| 12 |
+
{"current_steps": 12, "total_steps": 32405, "loss": 1.7664, "lr": 1.1e-06, "epoch": 0.0018513375914097935, "percentage": 0.04, "elapsed_time": "0:01:06", "remaining_time": "2 days, 1:40:09"}
|
| 13 |
+
{"current_steps": 13, "total_steps": 32405, "loss": 1.7768, "lr": 1.2000000000000002e-06, "epoch": 0.0020056157240272766, "percentage": 0.04, "elapsed_time": "0:01:10", "remaining_time": "2 days, 0:44:50"}
|
| 14 |
+
{"current_steps": 14, "total_steps": 32405, "loss": 1.8879, "lr": 1.3e-06, "epoch": 0.002159893856644759, "percentage": 0.04, "elapsed_time": "0:01:16", "remaining_time": "2 days, 0:59:51"}
|
| 15 |
+
{"current_steps": 15, "total_steps": 32405, "loss": 1.9438, "lr": 1.4000000000000001e-06, "epoch": 0.002314171989262242, "percentage": 0.05, "elapsed_time": "0:01:21", "remaining_time": "2 days, 0:46:47"}
|
| 16 |
+
{"current_steps": 16, "total_steps": 32405, "loss": 1.7083, "lr": 1.5e-06, "epoch": 0.0024684501218797247, "percentage": 0.05, "elapsed_time": "0:01:25", "remaining_time": "1 day, 23:57:52"}
|
| 17 |
+
{"current_steps": 17, "total_steps": 32405, "loss": 1.7394, "lr": 1.6000000000000001e-06, "epoch": 0.0026227282544972075, "percentage": 0.05, "elapsed_time": "0:01:29", "remaining_time": "1 day, 23:26:10"}
|
| 18 |
+
{"current_steps": 18, "total_steps": 32405, "loss": 1.7541, "lr": 1.7000000000000002e-06, "epoch": 0.0027770063871146904, "percentage": 0.06, "elapsed_time": "0:01:34", "remaining_time": "1 day, 23:15:40"}
|
| 19 |
+
{"current_steps": 19, "total_steps": 32405, "loss": 1.6979, "lr": 1.8000000000000001e-06, "epoch": 0.0029312845197321732, "percentage": 0.06, "elapsed_time": "0:01:40", "remaining_time": "1 day, 23:22:28"}
|
| 20 |
+
{"current_steps": 20, "total_steps": 32405, "loss": 1.7423, "lr": 1.9000000000000002e-06, "epoch": 0.003085562652349656, "percentage": 0.06, "elapsed_time": "0:01:44", "remaining_time": "1 day, 22:47:59"}
|
| 21 |
+
{"current_steps": 21, "total_steps": 32405, "loss": 1.7952, "lr": 2.0000000000000003e-06, "epoch": 0.003239840784967139, "percentage": 0.06, "elapsed_time": "0:01:47", "remaining_time": "1 day, 22:10:09"}
|
| 22 |
+
{"current_steps": 22, "total_steps": 32405, "loss": 1.6515, "lr": 2.1000000000000002e-06, "epoch": 0.0033941189175846214, "percentage": 0.07, "elapsed_time": "0:01:51", "remaining_time": "1 day, 21:39:42"}
|
| 23 |
+
{"current_steps": 23, "total_steps": 32405, "loss": 1.6121, "lr": 2.2e-06, "epoch": 0.003548397050202104, "percentage": 0.07, "elapsed_time": "0:01:56", "remaining_time": "1 day, 21:42:39"}
|
| 24 |
+
{"current_steps": 24, "total_steps": 32405, "loss": 1.8055, "lr": 2.3000000000000004e-06, "epoch": 0.003702675182819587, "percentage": 0.07, "elapsed_time": "0:02:00", "remaining_time": "1 day, 21:20:13"}
|
| 25 |
+
{"current_steps": 25, "total_steps": 32405, "loss": 1.7852, "lr": 2.4000000000000003e-06, "epoch": 0.00385695331543707, "percentage": 0.08, "elapsed_time": "0:02:04", "remaining_time": "1 day, 20:54:31"}
|
| 26 |
+
{"current_steps": 26, "total_steps": 32405, "loss": 1.683, "lr": 2.5e-06, "epoch": 0.004011231448054553, "percentage": 0.08, "elapsed_time": "0:02:08", "remaining_time": "1 day, 20:36:26"}
|
| 27 |
+
{"current_steps": 27, "total_steps": 32405, "loss": 1.8958, "lr": 2.6e-06, "epoch": 0.004165509580672035, "percentage": 0.08, "elapsed_time": "0:02:13", "remaining_time": "1 day, 20:24:47"}
|
| 28 |
+
{"current_steps": 28, "total_steps": 32405, "loss": 1.642, "lr": 2.7000000000000004e-06, "epoch": 0.004319787713289518, "percentage": 0.09, "elapsed_time": "0:02:17", "remaining_time": "1 day, 20:15:13"}
|
| 29 |
+
{"current_steps": 29, "total_steps": 32405, "loss": 1.7918, "lr": 2.8000000000000003e-06, "epoch": 0.004474065845907001, "percentage": 0.09, "elapsed_time": "0:02:21", "remaining_time": "1 day, 20:01:32"}
|
| 30 |
+
{"current_steps": 30, "total_steps": 32405, "loss": 1.6053, "lr": 2.9e-06, "epoch": 0.004628343978524484, "percentage": 0.09, "elapsed_time": "0:02:26", "remaining_time": "1 day, 19:49:35"}
|
| 31 |
+
{"current_steps": 31, "total_steps": 32405, "loss": 1.726, "lr": 3e-06, "epoch": 0.0047826221111419666, "percentage": 0.1, "elapsed_time": "0:02:29", "remaining_time": "1 day, 19:30:11"}
|
| 32 |
+
{"current_steps": 32, "total_steps": 32405, "loss": 1.7726, "lr": 3.1000000000000004e-06, "epoch": 0.004936900243759449, "percentage": 0.1, "elapsed_time": "0:02:35", "remaining_time": "1 day, 19:41:45"}
|
| 33 |
+
{"current_steps": 33, "total_steps": 32405, "loss": 1.796, "lr": 3.2000000000000003e-06, "epoch": 0.005091178376376932, "percentage": 0.1, "elapsed_time": "0:02:39", "remaining_time": "1 day, 19:24:03"}
|
| 34 |
+
{"current_steps": 34, "total_steps": 32405, "loss": 1.8129, "lr": 3.3000000000000006e-06, "epoch": 0.005245456508994415, "percentage": 0.1, "elapsed_time": "0:02:43", "remaining_time": "1 day, 19:21:28"}
|
| 35 |
+
{"current_steps": 35, "total_steps": 32405, "loss": 1.7199, "lr": 3.4000000000000005e-06, "epoch": 0.005399734641611898, "percentage": 0.11, "elapsed_time": "0:02:48", "remaining_time": "1 day, 19:12:57"}
|
| 36 |
+
{"current_steps": 36, "total_steps": 32405, "loss": 1.7054, "lr": 3.5e-06, "epoch": 0.005554012774229381, "percentage": 0.11, "elapsed_time": "0:02:52", "remaining_time": "1 day, 19:07:55"}
|
| 37 |
+
{"current_steps": 37, "total_steps": 32405, "loss": 1.7898, "lr": 3.6000000000000003e-06, "epoch": 0.005708290906846864, "percentage": 0.11, "elapsed_time": "0:02:56", "remaining_time": "1 day, 18:55:40"}
|
| 38 |
+
{"current_steps": 38, "total_steps": 32405, "loss": 1.7197, "lr": 3.7e-06, "epoch": 0.0058625690394643465, "percentage": 0.12, "elapsed_time": "0:03:00", "remaining_time": "1 day, 18:39:00"}
|
| 39 |
+
{"current_steps": 39, "total_steps": 32405, "loss": 1.7256, "lr": 3.8000000000000005e-06, "epoch": 0.006016847172081829, "percentage": 0.12, "elapsed_time": "0:03:05", "remaining_time": "1 day, 18:42:13"}
|
| 40 |
+
{"current_steps": 40, "total_steps": 32405, "loss": 1.6892, "lr": 3.900000000000001e-06, "epoch": 0.006171125304699312, "percentage": 0.12, "elapsed_time": "0:03:08", "remaining_time": "1 day, 18:25:32"}
|
| 41 |
+
{"current_steps": 41, "total_steps": 32405, "loss": 1.825, "lr": 4.000000000000001e-06, "epoch": 0.006325403437316795, "percentage": 0.13, "elapsed_time": "0:03:12", "remaining_time": "1 day, 18:17:39"}
|
| 42 |
+
{"current_steps": 42, "total_steps": 32405, "loss": 1.8063, "lr": 4.1e-06, "epoch": 0.006479681569934278, "percentage": 0.13, "elapsed_time": "0:03:16", "remaining_time": "1 day, 18:04:26"}
|
| 43 |
+
{"current_steps": 43, "total_steps": 32405, "loss": 1.6723, "lr": 4.2000000000000004e-06, "epoch": 0.006633959702551761, "percentage": 0.13, "elapsed_time": "0:03:21", "remaining_time": "1 day, 18:02:40"}
|
| 44 |
+
{"current_steps": 44, "total_steps": 32405, "loss": 1.8058, "lr": 4.3e-06, "epoch": 0.006788237835169243, "percentage": 0.14, "elapsed_time": "0:03:25", "remaining_time": "1 day, 17:54:15"}
|
| 45 |
+
{"current_steps": 45, "total_steps": 32405, "loss": 1.7628, "lr": 4.4e-06, "epoch": 0.0069425159677867256, "percentage": 0.14, "elapsed_time": "0:03:29", "remaining_time": "1 day, 17:56:15"}
|
| 46 |
+
{"current_steps": 46, "total_steps": 32405, "loss": 1.6962, "lr": 4.5e-06, "epoch": 0.007096794100404208, "percentage": 0.14, "elapsed_time": "0:03:35", "remaining_time": "1 day, 18:05:52"}
|
| 47 |
+
{"current_steps": 47, "total_steps": 32405, "loss": 1.803, "lr": 4.600000000000001e-06, "epoch": 0.007251072233021691, "percentage": 0.15, "elapsed_time": "0:03:39", "remaining_time": "1 day, 17:55:30"}
|
| 48 |
+
{"current_steps": 48, "total_steps": 32405, "loss": 1.8422, "lr": 4.7e-06, "epoch": 0.007405350365639174, "percentage": 0.15, "elapsed_time": "0:03:44", "remaining_time": "1 day, 17:57:06"}
|
| 49 |
+
{"current_steps": 49, "total_steps": 32405, "loss": 1.7857, "lr": 4.800000000000001e-06, "epoch": 0.007559628498256657, "percentage": 0.15, "elapsed_time": "0:03:47", "remaining_time": "1 day, 17:46:36"}
|
| 50 |
+
{"current_steps": 50, "total_steps": 32405, "loss": 1.6888, "lr": 4.9000000000000005e-06, "epoch": 0.00771390663087414, "percentage": 0.15, "elapsed_time": "0:03:51", "remaining_time": "1 day, 17:37:49"}
|
| 51 |
+
{"current_steps": 51, "total_steps": 32405, "loss": 1.7818, "lr": 5e-06, "epoch": 0.007868184763491623, "percentage": 0.16, "elapsed_time": "0:03:55", "remaining_time": "1 day, 17:30:51"}
|
| 52 |
+
{"current_steps": 52, "total_steps": 32405, "loss": 1.7894, "lr": 4.999999988215072e-06, "epoch": 0.008022462896109106, "percentage": 0.16, "elapsed_time": "0:03:59", "remaining_time": "1 day, 17:26:29"}
|
| 53 |
+
{"current_steps": 53, "total_steps": 32405, "loss": 1.7278, "lr": 4.9999999528602876e-06, "epoch": 0.008176741028726588, "percentage": 0.16, "elapsed_time": "0:04:03", "remaining_time": "1 day, 17:21:35"}
|
| 54 |
+
{"current_steps": 54, "total_steps": 32405, "loss": 1.7331, "lr": 4.999999893935645e-06, "epoch": 0.00833101916134407, "percentage": 0.17, "elapsed_time": "0:04:08", "remaining_time": "1 day, 17:20:13"}
|
| 55 |
+
{"current_steps": 55, "total_steps": 32405, "loss": 1.7426, "lr": 4.999999811441147e-06, "epoch": 0.008485297293961554, "percentage": 0.17, "elapsed_time": "0:04:13", "remaining_time": "1 day, 17:29:10"}
|
| 56 |
+
{"current_steps": 56, "total_steps": 32405, "loss": 1.7025, "lr": 4.999999705376795e-06, "epoch": 0.008639575426579036, "percentage": 0.17, "elapsed_time": "0:04:18", "remaining_time": "1 day, 17:32:36"}
|
| 57 |
+
{"current_steps": 57, "total_steps": 32405, "loss": 1.6907, "lr": 4.999999575742588e-06, "epoch": 0.00879385355919652, "percentage": 0.18, "elapsed_time": "0:04:22", "remaining_time": "1 day, 17:21:30"}
|
| 58 |
+
{"current_steps": 58, "total_steps": 32405, "loss": 1.6969, "lr": 4.9999994225385285e-06, "epoch": 0.008948131691814002, "percentage": 0.18, "elapsed_time": "0:04:26", "remaining_time": "1 day, 17:14:35"}
|
| 59 |
+
{"current_steps": 59, "total_steps": 32405, "loss": 1.6433, "lr": 4.999999245764618e-06, "epoch": 0.009102409824431485, "percentage": 0.18, "elapsed_time": "0:04:30", "remaining_time": "1 day, 17:08:35"}
|
| 60 |
+
{"current_steps": 60, "total_steps": 32405, "loss": 1.6803, "lr": 4.999999045420857e-06, "epoch": 0.009256687957048967, "percentage": 0.19, "elapsed_time": "0:04:34", "remaining_time": "1 day, 17:04:06"}
|
| 61 |
+
{"current_steps": 61, "total_steps": 32405, "loss": 1.8559, "lr": 4.9999988215072485e-06, "epoch": 0.009410966089666451, "percentage": 0.19, "elapsed_time": "0:04:40", "remaining_time": "1 day, 17:19:01"}
|
| 62 |
+
{"current_steps": 62, "total_steps": 32405, "loss": 1.7455, "lr": 4.999998574023794e-06, "epoch": 0.009565244222283933, "percentage": 0.19, "elapsed_time": "0:04:44", "remaining_time": "1 day, 17:16:51"}
|
| 63 |
+
{"current_steps": 63, "total_steps": 32405, "loss": 1.6383, "lr": 4.999998302970496e-06, "epoch": 0.009719522354901417, "percentage": 0.19, "elapsed_time": "0:04:49", "remaining_time": "1 day, 17:13:13"}
|
| 64 |
+
{"current_steps": 64, "total_steps": 32405, "loss": 1.7546, "lr": 4.999998008347357e-06, "epoch": 0.009873800487518899, "percentage": 0.2, "elapsed_time": "0:04:53", "remaining_time": "1 day, 17:10:47"}
|
| 65 |
+
{"current_steps": 65, "total_steps": 32405, "loss": 1.6962, "lr": 4.99999769015438e-06, "epoch": 0.010028078620136383, "percentage": 0.2, "elapsed_time": "0:04:57", "remaining_time": "1 day, 17:06:25"}
|
| 66 |
+
{"current_steps": 66, "total_steps": 32405, "loss": 1.7275, "lr": 4.999997348391568e-06, "epoch": 0.010182356752753864, "percentage": 0.2, "elapsed_time": "0:05:02", "remaining_time": "1 day, 17:10:19"}
|
| 67 |
+
{"current_steps": 67, "total_steps": 32405, "loss": 1.7569, "lr": 4.999996983058925e-06, "epoch": 0.010336634885371348, "percentage": 0.21, "elapsed_time": "0:05:06", "remaining_time": "1 day, 17:06:52"}
|
| 68 |
+
{"current_steps": 68, "total_steps": 32405, "loss": 1.702, "lr": 4.999996594156452e-06, "epoch": 0.01049091301798883, "percentage": 0.21, "elapsed_time": "0:05:10", "remaining_time": "1 day, 17:02:53"}
|
| 69 |
+
{"current_steps": 69, "total_steps": 32405, "loss": 1.6592, "lr": 4.9999961816841544e-06, "epoch": 0.010645191150606314, "percentage": 0.21, "elapsed_time": "0:05:14", "remaining_time": "1 day, 16:57:46"}
|
| 70 |
+
{"current_steps": 70, "total_steps": 32405, "loss": 1.8212, "lr": 4.999995745642037e-06, "epoch": 0.010799469283223796, "percentage": 0.22, "elapsed_time": "0:05:18", "remaining_time": "1 day, 16:51:24"}
|
| 71 |
+
{"current_steps": 71, "total_steps": 32405, "loss": 1.755, "lr": 4.999995286030102e-06, "epoch": 0.010953747415841278, "percentage": 0.22, "elapsed_time": "0:05:22", "remaining_time": "1 day, 16:48:49"}
|
| 72 |
+
{"current_steps": 72, "total_steps": 32405, "loss": 1.7986, "lr": 4.999994802848355e-06, "epoch": 0.011108025548458762, "percentage": 0.22, "elapsed_time": "0:05:27", "remaining_time": "1 day, 16:51:52"}
|
| 73 |
+
{"current_steps": 73, "total_steps": 32405, "loss": 1.7207, "lr": 4.999994296096801e-06, "epoch": 0.011262303681076244, "percentage": 0.23, "elapsed_time": "0:05:32", "remaining_time": "1 day, 16:53:07"}
|
| 74 |
+
{"current_steps": 74, "total_steps": 32405, "loss": 1.7604, "lr": 4.999993765775442e-06, "epoch": 0.011416581813693727, "percentage": 0.23, "elapsed_time": "0:05:37", "remaining_time": "1 day, 16:54:59"}
|
| 75 |
+
{"current_steps": 75, "total_steps": 32405, "loss": 1.628, "lr": 4.999993211884286e-06, "epoch": 0.01157085994631121, "percentage": 0.23, "elapsed_time": "0:05:42", "remaining_time": "1 day, 17:04:10"}
|
| 76 |
+
{"current_steps": 76, "total_steps": 32405, "loss": 1.7417, "lr": 4.999992634423337e-06, "epoch": 0.011725138078928693, "percentage": 0.23, "elapsed_time": "0:05:47", "remaining_time": "1 day, 17:01:30"}
|
| 77 |
+
{"current_steps": 77, "total_steps": 32405, "loss": 1.8426, "lr": 4.9999920333926e-06, "epoch": 0.011879416211546175, "percentage": 0.24, "elapsed_time": "0:05:51", "remaining_time": "1 day, 16:57:34"}
|
| 78 |
+
{"current_steps": 78, "total_steps": 32405, "loss": 1.8011, "lr": 4.999991408792082e-06, "epoch": 0.012033694344163659, "percentage": 0.24, "elapsed_time": "0:05:55", "remaining_time": "1 day, 16:53:40"}
|
| 79 |
+
{"current_steps": 79, "total_steps": 32405, "loss": 1.8153, "lr": 4.999990760621788e-06, "epoch": 0.01218797247678114, "percentage": 0.24, "elapsed_time": "0:05:59", "remaining_time": "1 day, 16:52:23"}
|
| 80 |
+
{"current_steps": 80, "total_steps": 32405, "loss": 1.6757, "lr": 4.999990088881724e-06, "epoch": 0.012342250609398624, "percentage": 0.25, "elapsed_time": "0:06:03", "remaining_time": "1 day, 16:47:26"}
|
| 81 |
+
{"current_steps": 81, "total_steps": 32405, "loss": 1.7416, "lr": 4.999989393571897e-06, "epoch": 0.012496528742016106, "percentage": 0.25, "elapsed_time": "0:06:07", "remaining_time": "1 day, 16:46:04"}
|
| 82 |
+
{"current_steps": 82, "total_steps": 32405, "loss": 1.9033, "lr": 4.999988674692312e-06, "epoch": 0.01265080687463359, "percentage": 0.25, "elapsed_time": "0:06:12", "remaining_time": "1 day, 16:50:02"}
|
| 83 |
+
{"current_steps": 83, "total_steps": 32405, "loss": 1.712, "lr": 4.999987932242978e-06, "epoch": 0.012805085007251072, "percentage": 0.26, "elapsed_time": "0:06:16", "remaining_time": "1 day, 16:44:53"}
|
| 84 |
+
{"current_steps": 84, "total_steps": 32405, "loss": 1.7396, "lr": 4.9999871662239e-06, "epoch": 0.012959363139868556, "percentage": 0.26, "elapsed_time": "0:06:21", "remaining_time": "1 day, 16:44:23"}
|
| 85 |
+
{"current_steps": 85, "total_steps": 32405, "loss": 1.7, "lr": 4.999986376635087e-06, "epoch": 0.013113641272486038, "percentage": 0.26, "elapsed_time": "0:06:24", "remaining_time": "1 day, 16:39:07"}
|
| 86 |
+
{"current_steps": 86, "total_steps": 32405, "loss": 1.6602, "lr": 4.999985563476545e-06, "epoch": 0.013267919405103521, "percentage": 0.27, "elapsed_time": "0:06:28", "remaining_time": "1 day, 16:34:45"}
|
| 87 |
+
{"current_steps": 87, "total_steps": 32405, "loss": 1.7066, "lr": 4.999984726748283e-06, "epoch": 0.013422197537721003, "percentage": 0.27, "elapsed_time": "0:06:32", "remaining_time": "1 day, 16:30:42"}
|
| 88 |
+
{"current_steps": 88, "total_steps": 32405, "loss": 1.6847, "lr": 4.999983866450307e-06, "epoch": 0.013576475670338485, "percentage": 0.27, "elapsed_time": "0:06:36", "remaining_time": "1 day, 16:29:21"}
|
| 89 |
+
{"current_steps": 89, "total_steps": 32405, "loss": 1.6088, "lr": 4.999982982582626e-06, "epoch": 0.013730753802955969, "percentage": 0.27, "elapsed_time": "0:06:40", "remaining_time": "1 day, 16:26:28"}
|
| 90 |
+
{"current_steps": 90, "total_steps": 32405, "loss": 1.8511, "lr": 4.99998207514525e-06, "epoch": 0.013885031935573451, "percentage": 0.28, "elapsed_time": "0:06:46", "remaining_time": "1 day, 16:33:47"}
|
| 91 |
+
{"current_steps": 91, "total_steps": 32405, "loss": 1.7509, "lr": 4.999981144138185e-06, "epoch": 0.014039310068190935, "percentage": 0.28, "elapsed_time": "0:06:51", "remaining_time": "1 day, 16:37:33"}
|
| 92 |
+
{"current_steps": 92, "total_steps": 32405, "loss": 1.7742, "lr": 4.999980189561442e-06, "epoch": 0.014193588200808417, "percentage": 0.28, "elapsed_time": "0:06:56", "remaining_time": "1 day, 16:36:55"}
|
| 93 |
+
{"current_steps": 93, "total_steps": 32405, "loss": 1.6739, "lr": 4.999979211415028e-06, "epoch": 0.0143478663334259, "percentage": 0.29, "elapsed_time": "0:07:01", "remaining_time": "1 day, 16:37:54"}
|
| 94 |
+
{"current_steps": 94, "total_steps": 32405, "loss": 1.7675, "lr": 4.999978209698953e-06, "epoch": 0.014502144466043383, "percentage": 0.29, "elapsed_time": "0:07:05", "remaining_time": "1 day, 16:36:30"}
|
| 95 |
+
{"current_steps": 95, "total_steps": 32405, "loss": 1.7769, "lr": 4.999977184413227e-06, "epoch": 0.014656422598660866, "percentage": 0.29, "elapsed_time": "0:07:10", "remaining_time": "1 day, 16:38:16"}
|
| 96 |
+
{"current_steps": 96, "total_steps": 32405, "loss": 1.7028, "lr": 4.999976135557859e-06, "epoch": 0.014810700731278348, "percentage": 0.3, "elapsed_time": "0:07:14", "remaining_time": "1 day, 16:35:39"}
|
| 97 |
+
{"current_steps": 97, "total_steps": 32405, "loss": 1.7932, "lr": 4.99997506313286e-06, "epoch": 0.014964978863895832, "percentage": 0.3, "elapsed_time": "0:07:18", "remaining_time": "1 day, 16:34:46"}
|
| 98 |
+
{"current_steps": 98, "total_steps": 32405, "loss": 1.7011, "lr": 4.999973967138239e-06, "epoch": 0.015119256996513314, "percentage": 0.3, "elapsed_time": "0:07:22", "remaining_time": "1 day, 16:30:11"}
|
| 99 |
+
{"current_steps": 99, "total_steps": 32405, "loss": 1.7103, "lr": 4.999972847574005e-06, "epoch": 0.015273535129130798, "percentage": 0.31, "elapsed_time": "0:07:27", "remaining_time": "1 day, 16:32:44"}
|
| 100 |
+
{"current_steps": 100, "total_steps": 32405, "loss": 1.7628, "lr": 4.999971704440171e-06, "epoch": 0.01542781326174828, "percentage": 0.31, "elapsed_time": "0:07:31", "remaining_time": "1 day, 16:29:04"}
|
| 101 |
+
{"current_steps": 101, "total_steps": 32405, "loss": 1.716, "lr": 4.999970537736747e-06, "epoch": 0.015582091394365763, "percentage": 0.31, "elapsed_time": "0:07:35", "remaining_time": "1 day, 16:26:55"}
|
| 102 |
+
{"current_steps": 102, "total_steps": 32405, "loss": 1.7415, "lr": 4.999969347463745e-06, "epoch": 0.015736369526983245, "percentage": 0.31, "elapsed_time": "0:07:40", "remaining_time": "1 day, 16:29:05"}
|
| 103 |
+
{"current_steps": 103, "total_steps": 32405, "loss": 1.5827, "lr": 4.999968133621173e-06, "epoch": 0.01589064765960073, "percentage": 0.32, "elapsed_time": "0:07:45", "remaining_time": "1 day, 16:31:21"}
|
| 104 |
+
{"current_steps": 104, "total_steps": 32405, "loss": 1.7971, "lr": 4.999966896209046e-06, "epoch": 0.016044925792218213, "percentage": 0.32, "elapsed_time": "0:07:49", "remaining_time": "1 day, 16:32:10"}
|
| 105 |
+
{"current_steps": 105, "total_steps": 32405, "loss": 1.7671, "lr": 4.999965635227374e-06, "epoch": 0.016199203924835693, "percentage": 0.32, "elapsed_time": "0:07:53", "remaining_time": "1 day, 16:28:01"}
|
| 106 |
+
{"current_steps": 106, "total_steps": 32405, "loss": 1.6721, "lr": 4.999964350676169e-06, "epoch": 0.016353482057453177, "percentage": 0.33, "elapsed_time": "0:07:57", "remaining_time": "1 day, 16:24:17"}
|
| 107 |
+
{"current_steps": 107, "total_steps": 32405, "loss": 1.8067, "lr": 4.999963042555443e-06, "epoch": 0.01650776019007066, "percentage": 0.33, "elapsed_time": "0:08:02", "remaining_time": "1 day, 16:26:15"}
|
| 108 |
+
{"current_steps": 108, "total_steps": 32405, "loss": 1.6678, "lr": 4.999961710865208e-06, "epoch": 0.01666203832268814, "percentage": 0.33, "elapsed_time": "0:08:06", "remaining_time": "1 day, 16:22:30"}
|
| 109 |
+
{"current_steps": 109, "total_steps": 32405, "loss": 1.7737, "lr": 4.9999603556054785e-06, "epoch": 0.016816316455305624, "percentage": 0.34, "elapsed_time": "0:08:11", "remaining_time": "1 day, 16:26:20"}
|
| 110 |
+
{"current_steps": 110, "total_steps": 32405, "loss": 1.8095, "lr": 4.999958976776265e-06, "epoch": 0.016970594587923108, "percentage": 0.34, "elapsed_time": "0:08:15", "remaining_time": "1 day, 16:24:14"}
|
| 111 |
+
{"current_steps": 111, "total_steps": 32405, "loss": 1.7734, "lr": 4.999957574377581e-06, "epoch": 0.017124872720540592, "percentage": 0.34, "elapsed_time": "0:08:19", "remaining_time": "1 day, 16:22:52"}
|
| 112 |
+
{"current_steps": 112, "total_steps": 32405, "loss": 1.6344, "lr": 4.9999561484094415e-06, "epoch": 0.017279150853158072, "percentage": 0.35, "elapsed_time": "0:08:24", "remaining_time": "1 day, 16:22:39"}
|
| 113 |
+
{"current_steps": 113, "total_steps": 32405, "loss": 1.7568, "lr": 4.999954698871857e-06, "epoch": 0.017433428985775556, "percentage": 0.35, "elapsed_time": "0:08:29", "remaining_time": "1 day, 16:25:08"}
|
| 114 |
+
{"current_steps": 114, "total_steps": 32405, "loss": 1.7429, "lr": 4.999953225764843e-06, "epoch": 0.01758770711839304, "percentage": 0.35, "elapsed_time": "0:08:33", "remaining_time": "1 day, 16:22:32"}
|
| 115 |
+
{"current_steps": 115, "total_steps": 32405, "loss": 1.8423, "lr": 4.999951729088414e-06, "epoch": 0.017741985251010523, "percentage": 0.35, "elapsed_time": "0:08:37", "remaining_time": "1 day, 16:21:25"}
|
| 116 |
+
{"current_steps": 116, "total_steps": 32405, "loss": 1.9152, "lr": 4.999950208842584e-06, "epoch": 0.017896263383628003, "percentage": 0.36, "elapsed_time": "0:08:42", "remaining_time": "1 day, 16:22:48"}
|
| 117 |
+
{"current_steps": 117, "total_steps": 32405, "loss": 1.6836, "lr": 4.999948665027364e-06, "epoch": 0.018050541516245487, "percentage": 0.36, "elapsed_time": "0:08:47", "remaining_time": "1 day, 16:24:41"}
|
| 118 |
+
{"current_steps": 118, "total_steps": 32405, "loss": 1.6686, "lr": 4.999947097642773e-06, "epoch": 0.01820481964886297, "percentage": 0.36, "elapsed_time": "0:08:51", "remaining_time": "1 day, 16:22:05"}
|
| 119 |
+
{"current_steps": 119, "total_steps": 32405, "loss": 1.6848, "lr": 4.999945506688823e-06, "epoch": 0.018359097781480455, "percentage": 0.37, "elapsed_time": "0:08:55", "remaining_time": "1 day, 16:23:01"}
|
| 120 |
+
{"current_steps": 120, "total_steps": 32405, "loss": 1.7532, "lr": 4.99994389216553e-06, "epoch": 0.018513375914097935, "percentage": 0.37, "elapsed_time": "0:08:59", "remaining_time": "1 day, 16:19:43"}
|
| 121 |
+
{"current_steps": 121, "total_steps": 32405, "loss": 1.7237, "lr": 4.9999422540729096e-06, "epoch": 0.01866765404671542, "percentage": 0.37, "elapsed_time": "0:09:03", "remaining_time": "1 day, 16:18:30"}
|
| 122 |
+
{"current_steps": 122, "total_steps": 32405, "loss": 1.7609, "lr": 4.999940592410977e-06, "epoch": 0.018821932179332902, "percentage": 0.38, "elapsed_time": "0:09:08", "remaining_time": "1 day, 16:19:29"}
|
| 123 |
+
{"current_steps": 123, "total_steps": 32405, "loss": 1.6799, "lr": 4.999938907179746e-06, "epoch": 0.018976210311950382, "percentage": 0.38, "elapsed_time": "0:09:12", "remaining_time": "1 day, 16:15:11"}
|
| 124 |
+
{"current_steps": 124, "total_steps": 32405, "loss": 1.718, "lr": 4.999937198379236e-06, "epoch": 0.019130488444567866, "percentage": 0.38, "elapsed_time": "0:09:15", "remaining_time": "1 day, 16:11:29"}
|
| 125 |
+
{"current_steps": 125, "total_steps": 32405, "loss": 1.8111, "lr": 4.99993546600946e-06, "epoch": 0.01928476657718535, "percentage": 0.39, "elapsed_time": "0:09:19", "remaining_time": "1 day, 16:09:46"}
|
| 126 |
+
{"current_steps": 126, "total_steps": 32405, "loss": 1.7556, "lr": 4.999933710070436e-06, "epoch": 0.019439044709802834, "percentage": 0.39, "elapsed_time": "0:09:24", "remaining_time": "1 day, 16:09:00"}
|
| 127 |
+
{"current_steps": 127, "total_steps": 32405, "loss": 1.6019, "lr": 4.99993193056218e-06, "epoch": 0.019593322842420314, "percentage": 0.39, "elapsed_time": "0:09:28", "remaining_time": "1 day, 16:06:49"}
|
| 128 |
+
{"current_steps": 128, "total_steps": 32405, "loss": 1.7384, "lr": 4.9999301274847086e-06, "epoch": 0.019747600975037798, "percentage": 0.4, "elapsed_time": "0:09:31", "remaining_time": "1 day, 16:03:39"}
|
| 129 |
+
{"current_steps": 129, "total_steps": 32405, "loss": 1.7887, "lr": 4.999928300838039e-06, "epoch": 0.01990187910765528, "percentage": 0.4, "elapsed_time": "0:09:36", "remaining_time": "1 day, 16:03:51"}
|
| 130 |
+
{"current_steps": 130, "total_steps": 32405, "loss": 1.7518, "lr": 4.999926450622189e-06, "epoch": 0.020056157240272765, "percentage": 0.4, "elapsed_time": "0:09:40", "remaining_time": "1 day, 16:03:51"}
|
| 131 |
+
{"current_steps": 131, "total_steps": 32405, "loss": 1.8069, "lr": 4.999924576837176e-06, "epoch": 0.020210435372890245, "percentage": 0.4, "elapsed_time": "0:09:45", "remaining_time": "1 day, 16:04:44"}
|
| 132 |
+
{"current_steps": 132, "total_steps": 32405, "loss": 1.7565, "lr": 4.999922679483016e-06, "epoch": 0.02036471350550773, "percentage": 0.41, "elapsed_time": "0:09:50", "remaining_time": "1 day, 16:04:55"}
|
| 133 |
+
{"current_steps": 133, "total_steps": 32405, "loss": 1.7071, "lr": 4.999920758559729e-06, "epoch": 0.020518991638125213, "percentage": 0.41, "elapsed_time": "0:09:54", "remaining_time": "1 day, 16:04:44"}
|
| 134 |
+
{"current_steps": 134, "total_steps": 32405, "loss": 1.6922, "lr": 4.9999188140673315e-06, "epoch": 0.020673269770742696, "percentage": 0.41, "elapsed_time": "0:09:59", "remaining_time": "1 day, 16:04:58"}
|
| 135 |
+
{"current_steps": 135, "total_steps": 32405, "loss": 1.6519, "lr": 4.999916846005843e-06, "epoch": 0.020827547903360177, "percentage": 0.42, "elapsed_time": "0:10:03", "remaining_time": "1 day, 16:03:02"}
|
| 136 |
+
{"current_steps": 136, "total_steps": 32405, "loss": 1.7143, "lr": 4.999914854375281e-06, "epoch": 0.02098182603597766, "percentage": 0.42, "elapsed_time": "0:10:06", "remaining_time": "1 day, 15:59:48"}
|
| 137 |
+
{"current_steps": 137, "total_steps": 32405, "loss": 1.7016, "lr": 4.999912839175666e-06, "epoch": 0.021136104168595144, "percentage": 0.42, "elapsed_time": "0:10:10", "remaining_time": "1 day, 15:56:25"}
|
| 138 |
+
{"current_steps": 138, "total_steps": 32405, "loss": 1.7985, "lr": 4.999910800407016e-06, "epoch": 0.021290382301212628, "percentage": 0.43, "elapsed_time": "0:10:15", "remaining_time": "1 day, 15:58:07"}
|
| 139 |
+
{"current_steps": 139, "total_steps": 32405, "loss": 1.8294, "lr": 4.999908738069349e-06, "epoch": 0.021444660433830108, "percentage": 0.43, "elapsed_time": "0:10:20", "remaining_time": "1 day, 15:58:44"}
|
| 140 |
+
{"current_steps": 140, "total_steps": 32405, "loss": 1.6855, "lr": 4.999906652162686e-06, "epoch": 0.021598938566447592, "percentage": 0.43, "elapsed_time": "0:10:24", "remaining_time": "1 day, 15:59:06"}
|
| 141 |
+
{"current_steps": 141, "total_steps": 32405, "loss": 1.5996, "lr": 4.999904542687046e-06, "epoch": 0.021753216699065075, "percentage": 0.44, "elapsed_time": "0:10:28", "remaining_time": "1 day, 15:56:16"}
|
| 142 |
+
{"current_steps": 142, "total_steps": 32405, "loss": 1.6607, "lr": 4.999902409642449e-06, "epoch": 0.021907494831682556, "percentage": 0.44, "elapsed_time": "0:10:32", "remaining_time": "1 day, 15:56:43"}
|
| 143 |
+
{"current_steps": 143, "total_steps": 32405, "loss": 1.8012, "lr": 4.999900253028915e-06, "epoch": 0.02206177296430004, "percentage": 0.44, "elapsed_time": "0:10:37", "remaining_time": "1 day, 15:57:36"}
|
| 144 |
+
{"current_steps": 144, "total_steps": 32405, "loss": 1.8167, "lr": 4.999898072846465e-06, "epoch": 0.022216051096917523, "percentage": 0.44, "elapsed_time": "0:10:41", "remaining_time": "1 day, 15:56:09"}
|
| 145 |
+
{"current_steps": 145, "total_steps": 32405, "loss": 1.7877, "lr": 4.99989586909512e-06, "epoch": 0.022370329229535007, "percentage": 0.45, "elapsed_time": "0:10:45", "remaining_time": "1 day, 15:53:46"}
|
| 146 |
+
{"current_steps": 146, "total_steps": 32405, "loss": 1.7714, "lr": 4.999893641774897e-06, "epoch": 0.022524607362152487, "percentage": 0.45, "elapsed_time": "0:10:49", "remaining_time": "1 day, 15:50:50"}
|
| 147 |
+
{"current_steps": 147, "total_steps": 32405, "loss": 1.6635, "lr": 4.9998913908858225e-06, "epoch": 0.02267888549476997, "percentage": 0.45, "elapsed_time": "0:10:54", "remaining_time": "1 day, 15:52:19"}
|
| 148 |
+
{"current_steps": 148, "total_steps": 32405, "loss": 1.7919, "lr": 4.999889116427915e-06, "epoch": 0.022833163627387455, "percentage": 0.46, "elapsed_time": "0:10:57", "remaining_time": "1 day, 15:48:55"}
|
| 149 |
+
{"current_steps": 149, "total_steps": 32405, "loss": 1.7657, "lr": 4.999886818401195e-06, "epoch": 0.02298744176000494, "percentage": 0.46, "elapsed_time": "0:11:01", "remaining_time": "1 day, 15:47:31"}
|
| 150 |
+
{"current_steps": 150, "total_steps": 32405, "loss": 1.7454, "lr": 4.999884496805686e-06, "epoch": 0.02314171989262242, "percentage": 0.46, "elapsed_time": "0:11:05", "remaining_time": "1 day, 15:46:24"}
|
| 151 |
+
{"current_steps": 151, "total_steps": 32405, "loss": 1.7539, "lr": 4.999882151641408e-06, "epoch": 0.023295998025239902, "percentage": 0.47, "elapsed_time": "0:11:10", "remaining_time": "1 day, 15:45:30"}
|
| 152 |
+
{"current_steps": 152, "total_steps": 32405, "loss": 1.8156, "lr": 4.999879782908384e-06, "epoch": 0.023450276157857386, "percentage": 0.47, "elapsed_time": "0:11:13", "remaining_time": "1 day, 15:42:45"}
|
| 153 |
+
{"current_steps": 153, "total_steps": 32405, "loss": 1.6586, "lr": 4.999877390606638e-06, "epoch": 0.02360455429047487, "percentage": 0.47, "elapsed_time": "0:11:17", "remaining_time": "1 day, 15:39:42"}
|
| 154 |
+
{"current_steps": 154, "total_steps": 32405, "loss": 1.7956, "lr": 4.9998749747361905e-06, "epoch": 0.02375883242309235, "percentage": 0.48, "elapsed_time": "0:11:22", "remaining_time": "1 day, 15:42:09"}
|
| 155 |
+
{"current_steps": 155, "total_steps": 32405, "loss": 1.7102, "lr": 4.999872535297065e-06, "epoch": 0.023913110555709834, "percentage": 0.48, "elapsed_time": "0:11:27", "remaining_time": "1 day, 15:42:22"}
|
| 156 |
+
{"current_steps": 156, "total_steps": 32405, "loss": 1.7851, "lr": 4.999870072289284e-06, "epoch": 0.024067388688327317, "percentage": 0.48, "elapsed_time": "0:11:31", "remaining_time": "1 day, 15:42:17"}
|
| 157 |
+
{"current_steps": 157, "total_steps": 32405, "loss": 1.5441, "lr": 4.999867585712871e-06, "epoch": 0.024221666820944798, "percentage": 0.48, "elapsed_time": "0:11:36", "remaining_time": "1 day, 15:44:04"}
|
| 158 |
+
{"current_steps": 158, "total_steps": 32405, "loss": 1.6314, "lr": 4.99986507556785e-06, "epoch": 0.02437594495356228, "percentage": 0.49, "elapsed_time": "0:11:40", "remaining_time": "1 day, 15:41:13"}
|
| 159 |
+
{"current_steps": 159, "total_steps": 32405, "loss": 1.7213, "lr": 4.9998625418542435e-06, "epoch": 0.024530223086179765, "percentage": 0.49, "elapsed_time": "0:11:44", "remaining_time": "1 day, 15:41:48"}
|
| 160 |
+
{"current_steps": 160, "total_steps": 32405, "loss": 1.7179, "lr": 4.999859984572077e-06, "epoch": 0.02468450121879725, "percentage": 0.49, "elapsed_time": "0:11:48", "remaining_time": "1 day, 15:38:58"}
|
| 161 |
+
{"current_steps": 161, "total_steps": 32405, "loss": 1.7593, "lr": 4.999857403721372e-06, "epoch": 0.02483877935141473, "percentage": 0.5, "elapsed_time": "0:11:53", "remaining_time": "1 day, 15:40:32"}
|
| 162 |
+
{"current_steps": 162, "total_steps": 32405, "loss": 1.7875, "lr": 4.999854799302156e-06, "epoch": 0.024993057484032213, "percentage": 0.5, "elapsed_time": "0:11:58", "remaining_time": "1 day, 15:42:19"}
|
| 163 |
+
{"current_steps": 163, "total_steps": 32405, "loss": 1.732, "lr": 4.999852171314452e-06, "epoch": 0.025147335616649696, "percentage": 0.5, "elapsed_time": "0:12:02", "remaining_time": "1 day, 15:41:29"}
|
| 164 |
+
{"current_steps": 164, "total_steps": 32405, "loss": 1.72, "lr": 4.999849519758284e-06, "epoch": 0.02530161374926718, "percentage": 0.51, "elapsed_time": "0:12:07", "remaining_time": "1 day, 15:42:47"}
|
| 165 |
+
{"current_steps": 165, "total_steps": 32405, "loss": 1.665, "lr": 4.999846844633679e-06, "epoch": 0.02545589188188466, "percentage": 0.51, "elapsed_time": "0:12:10", "remaining_time": "1 day, 15:40:18"}
|
| 166 |
+
{"current_steps": 166, "total_steps": 32405, "loss": 1.7622, "lr": 4.99984414594066e-06, "epoch": 0.025610170014502144, "percentage": 0.51, "elapsed_time": "0:12:16", "remaining_time": "1 day, 15:43:50"}
|
| 167 |
+
{"current_steps": 167, "total_steps": 32405, "loss": 1.653, "lr": 4.9998414236792535e-06, "epoch": 0.025764448147119628, "percentage": 0.52, "elapsed_time": "0:12:20", "remaining_time": "1 day, 15:43:14"}
|
| 168 |
+
{"current_steps": 168, "total_steps": 32405, "loss": 1.6854, "lr": 4.9998386778494855e-06, "epoch": 0.02591872627973711, "percentage": 0.52, "elapsed_time": "0:12:24", "remaining_time": "1 day, 15:40:32"}
|
| 169 |
+
{"current_steps": 169, "total_steps": 32405, "loss": 1.6766, "lr": 4.999835908451382e-06, "epoch": 0.026073004412354592, "percentage": 0.52, "elapsed_time": "0:12:28", "remaining_time": "1 day, 15:39:50"}
|
| 170 |
+
{"current_steps": 170, "total_steps": 32405, "loss": 1.5154, "lr": 4.999833115484969e-06, "epoch": 0.026227282544972075, "percentage": 0.52, "elapsed_time": "0:12:33", "remaining_time": "1 day, 15:40:55"}
|
| 171 |
+
{"current_steps": 171, "total_steps": 32405, "loss": 1.7991, "lr": 4.999830298950271e-06, "epoch": 0.02638156067758956, "percentage": 0.53, "elapsed_time": "0:12:38", "remaining_time": "1 day, 15:41:47"}
|
| 172 |
+
{"current_steps": 172, "total_steps": 32405, "loss": 1.7147, "lr": 4.999827458847317e-06, "epoch": 0.026535838810207043, "percentage": 0.53, "elapsed_time": "0:12:43", "remaining_time": "1 day, 15:43:28"}
|
| 173 |
+
{"current_steps": 173, "total_steps": 32405, "loss": 1.7371, "lr": 4.999824595176132e-06, "epoch": 0.026690116942824523, "percentage": 0.53, "elapsed_time": "0:12:47", "remaining_time": "1 day, 15:43:36"}
|
| 174 |
+
{"current_steps": 174, "total_steps": 32405, "loss": 1.6453, "lr": 4.999821707936745e-06, "epoch": 0.026844395075442007, "percentage": 0.54, "elapsed_time": "0:12:52", "remaining_time": "1 day, 15:43:23"}
|
| 175 |
+
{"current_steps": 175, "total_steps": 32405, "loss": 1.8491, "lr": 4.999818797129182e-06, "epoch": 0.02699867320805949, "percentage": 0.54, "elapsed_time": "0:12:58", "remaining_time": "1 day, 15:49:11"}
|
| 176 |
+
{"current_steps": 176, "total_steps": 32405, "loss": 1.5844, "lr": 4.99981586275347e-06, "epoch": 0.02715295134067697, "percentage": 0.54, "elapsed_time": "0:13:01", "remaining_time": "1 day, 15:46:36"}
|
| 177 |
+
{"current_steps": 177, "total_steps": 32405, "loss": 1.7463, "lr": 4.9998129048096375e-06, "epoch": 0.027307229473294455, "percentage": 0.55, "elapsed_time": "0:13:05", "remaining_time": "1 day, 15:44:07"}
|
| 178 |
+
{"current_steps": 178, "total_steps": 32405, "loss": 1.7475, "lr": 4.999809923297711e-06, "epoch": 0.027461507605911938, "percentage": 0.55, "elapsed_time": "0:13:09", "remaining_time": "1 day, 15:43:38"}
|
| 179 |
+
{"current_steps": 179, "total_steps": 32405, "loss": 1.6054, "lr": 4.999806918217721e-06, "epoch": 0.027615785738529422, "percentage": 0.55, "elapsed_time": "0:13:14", "remaining_time": "1 day, 15:43:24"}
|
| 180 |
+
{"current_steps": 180, "total_steps": 32405, "loss": 1.9197, "lr": 4.999803889569694e-06, "epoch": 0.027770063871146902, "percentage": 0.56, "elapsed_time": "0:13:18", "remaining_time": "1 day, 15:42:42"}
|
| 181 |
+
{"current_steps": 181, "total_steps": 32405, "loss": 1.6808, "lr": 4.999800837353659e-06, "epoch": 0.027924342003764386, "percentage": 0.56, "elapsed_time": "0:13:22", "remaining_time": "1 day, 15:40:46"}
|
| 182 |
+
{"current_steps": 182, "total_steps": 32405, "loss": 1.5895, "lr": 4.999797761569645e-06, "epoch": 0.02807862013638187, "percentage": 0.56, "elapsed_time": "0:13:26", "remaining_time": "1 day, 15:38:37"}
|
| 183 |
+
{"current_steps": 183, "total_steps": 32405, "loss": 1.7701, "lr": 4.999794662217679e-06, "epoch": 0.028232898268999353, "percentage": 0.56, "elapsed_time": "0:13:30", "remaining_time": "1 day, 15:37:03"}
|
| 184 |
+
{"current_steps": 184, "total_steps": 32405, "loss": 1.6835, "lr": 4.999791539297795e-06, "epoch": 0.028387176401616834, "percentage": 0.57, "elapsed_time": "0:13:33", "remaining_time": "1 day, 15:35:38"}
|
| 185 |
+
{"current_steps": 185, "total_steps": 32405, "loss": 1.7257, "lr": 4.999788392810018e-06, "epoch": 0.028541454534234317, "percentage": 0.57, "elapsed_time": "0:13:39", "remaining_time": "1 day, 15:39:04"}
|
| 186 |
+
{"current_steps": 186, "total_steps": 32405, "loss": 1.6947, "lr": 4.9997852227543785e-06, "epoch": 0.0286957326668518, "percentage": 0.57, "elapsed_time": "0:13:43", "remaining_time": "1 day, 15:37:33"}
|
| 187 |
+
{"current_steps": 187, "total_steps": 32405, "loss": 1.8214, "lr": 4.999782029130909e-06, "epoch": 0.028850010799469285, "percentage": 0.58, "elapsed_time": "0:13:48", "remaining_time": "1 day, 15:37:39"}
|
| 188 |
+
{"current_steps": 188, "total_steps": 32405, "loss": 1.6742, "lr": 4.999778811939635e-06, "epoch": 0.029004288932086765, "percentage": 0.58, "elapsed_time": "0:13:51", "remaining_time": "1 day, 15:35:26"}
|
| 189 |
+
{"current_steps": 189, "total_steps": 32405, "loss": 1.7639, "lr": 4.999775571180592e-06, "epoch": 0.02915856706470425, "percentage": 0.58, "elapsed_time": "0:13:55", "remaining_time": "1 day, 15:33:57"}
|
| 190 |
+
{"current_steps": 190, "total_steps": 32405, "loss": 1.6787, "lr": 4.999772306853806e-06, "epoch": 0.029312845197321732, "percentage": 0.59, "elapsed_time": "0:14:00", "remaining_time": "1 day, 15:34:45"}
|
| 191 |
+
{"current_steps": 191, "total_steps": 32405, "loss": 1.7152, "lr": 4.999769018959311e-06, "epoch": 0.029467123329939213, "percentage": 0.59, "elapsed_time": "0:14:04", "remaining_time": "1 day, 15:33:57"}
|
| 192 |
+
{"current_steps": 192, "total_steps": 32405, "loss": 1.7311, "lr": 4.9997657074971365e-06, "epoch": 0.029621401462556696, "percentage": 0.59, "elapsed_time": "0:14:08", "remaining_time": "1 day, 15:32:16"}
|
| 193 |
+
{"current_steps": 193, "total_steps": 32405, "loss": 1.7783, "lr": 4.999762372467314e-06, "epoch": 0.02977567959517418, "percentage": 0.6, "elapsed_time": "0:14:12", "remaining_time": "1 day, 15:30:18"}
|
| 194 |
+
{"current_steps": 194, "total_steps": 32405, "loss": 1.6258, "lr": 4.999759013869875e-06, "epoch": 0.029929957727791664, "percentage": 0.6, "elapsed_time": "0:14:16", "remaining_time": "1 day, 15:30:33"}
|
| 195 |
+
{"current_steps": 195, "total_steps": 32405, "loss": 1.7994, "lr": 4.999755631704851e-06, "epoch": 0.030084235860409144, "percentage": 0.6, "elapsed_time": "0:14:20", "remaining_time": "1 day, 15:28:45"}
|
| 196 |
+
{"current_steps": 196, "total_steps": 32405, "loss": 1.6456, "lr": 4.999752225972274e-06, "epoch": 0.030238513993026628, "percentage": 0.6, "elapsed_time": "0:14:25", "remaining_time": "1 day, 15:29:49"}
|
| 197 |
+
{"current_steps": 197, "total_steps": 32405, "loss": 1.646, "lr": 4.999748796672176e-06, "epoch": 0.03039279212564411, "percentage": 0.61, "elapsed_time": "0:14:30", "remaining_time": "1 day, 15:31:01"}
|
| 198 |
+
{"current_steps": 198, "total_steps": 32405, "loss": 1.7256, "lr": 4.999745343804589e-06, "epoch": 0.030547070258261595, "percentage": 0.61, "elapsed_time": "0:14:34", "remaining_time": "1 day, 15:29:40"}
|
| 199 |
+
{"current_steps": 199, "total_steps": 32405, "loss": 1.7202, "lr": 4.999741867369548e-06, "epoch": 0.030701348390879075, "percentage": 0.61, "elapsed_time": "0:14:37", "remaining_time": "1 day, 15:27:54"}
|
| 200 |
+
{"current_steps": 200, "total_steps": 32405, "loss": 1.6808, "lr": 4.999738367367082e-06, "epoch": 0.03085562652349656, "percentage": 0.62, "elapsed_time": "0:14:41", "remaining_time": "1 day, 15:26:40"}
|
| 201 |
+
{"current_steps": 201, "total_steps": 32405, "loss": 1.6668, "lr": 4.999734843797226e-06, "epoch": 0.031009904656114043, "percentage": 0.62, "elapsed_time": "0:14:46", "remaining_time": "1 day, 15:26:00"}
|
| 202 |
+
{"current_steps": 202, "total_steps": 32405, "loss": 1.8341, "lr": 4.999731296660013e-06, "epoch": 0.031164182788731527, "percentage": 0.62, "elapsed_time": "0:14:50", "remaining_time": "1 day, 15:25:12"}
|
| 203 |
+
{"current_steps": 203, "total_steps": 32405, "loss": 1.8668, "lr": 4.999727725955477e-06, "epoch": 0.03131846092134901, "percentage": 0.63, "elapsed_time": "0:14:54", "remaining_time": "1 day, 15:25:00"}
|
| 204 |
+
{"current_steps": 204, "total_steps": 32405, "loss": 1.7882, "lr": 4.999724131683651e-06, "epoch": 0.03147273905396649, "percentage": 0.63, "elapsed_time": "0:14:59", "remaining_time": "1 day, 15:25:35"}
|
| 205 |
+
{"current_steps": 205, "total_steps": 32405, "loss": 1.8846, "lr": 4.999720513844569e-06, "epoch": 0.03162701718658397, "percentage": 0.63, "elapsed_time": "0:15:04", "remaining_time": "1 day, 15:27:26"}
|
| 206 |
+
{"current_steps": 206, "total_steps": 32405, "loss": 1.7352, "lr": 4.999716872438264e-06, "epoch": 0.03178129531920146, "percentage": 0.64, "elapsed_time": "0:15:09", "remaining_time": "1 day, 15:28:31"}
|
| 207 |
+
{"current_steps": 207, "total_steps": 32405, "loss": 1.798, "lr": 4.999713207464773e-06, "epoch": 0.03193557345181894, "percentage": 0.64, "elapsed_time": "0:15:13", "remaining_time": "1 day, 15:29:24"}
|
| 208 |
+
{"current_steps": 208, "total_steps": 32405, "loss": 1.8165, "lr": 4.999709518924128e-06, "epoch": 0.032089851584436425, "percentage": 0.64, "elapsed_time": "0:15:19", "remaining_time": "1 day, 15:32:57"}
|
| 209 |
+
{"current_steps": 209, "total_steps": 32405, "loss": 1.712, "lr": 4.999705806816365e-06, "epoch": 0.032244129717053906, "percentage": 0.64, "elapsed_time": "0:15:24", "remaining_time": "1 day, 15:33:02"}
|
| 210 |
+
{"current_steps": 210, "total_steps": 32405, "loss": 1.8643, "lr": 4.999702071141519e-06, "epoch": 0.032398407849671386, "percentage": 0.65, "elapsed_time": "0:15:30", "remaining_time": "1 day, 15:38:23"}
|
| 211 |
+
{"current_steps": 211, "total_steps": 32405, "loss": 1.5925, "lr": 4.9996983118996245e-06, "epoch": 0.03255268598228887, "percentage": 0.65, "elapsed_time": "0:15:35", "remaining_time": "1 day, 15:39:39"}
|
| 212 |
+
{"current_steps": 212, "total_steps": 32405, "loss": 1.748, "lr": 4.999694529090718e-06, "epoch": 0.03270696411490635, "percentage": 0.65, "elapsed_time": "0:15:40", "remaining_time": "1 day, 15:39:30"}
|
| 213 |
+
{"current_steps": 213, "total_steps": 32405, "loss": 1.698, "lr": 4.999690722714834e-06, "epoch": 0.032861242247523834, "percentage": 0.66, "elapsed_time": "0:15:43", "remaining_time": "1 day, 15:37:19"}
|
| 214 |
+
{"current_steps": 214, "total_steps": 32405, "loss": 1.787, "lr": 4.99968689277201e-06, "epoch": 0.03301552038014132, "percentage": 0.66, "elapsed_time": "0:15:48", "remaining_time": "1 day, 15:39:02"}
|
| 215 |
+
{"current_steps": 215, "total_steps": 32405, "loss": 1.6545, "lr": 4.99968303926228e-06, "epoch": 0.0331697985127588, "percentage": 0.66, "elapsed_time": "0:15:53", "remaining_time": "1 day, 15:38:45"}
|
| 216 |
+
{"current_steps": 216, "total_steps": 32405, "loss": 1.7305, "lr": 4.999679162185681e-06, "epoch": 0.03332407664537628, "percentage": 0.67, "elapsed_time": "0:15:57", "remaining_time": "1 day, 15:38:37"}
|
| 217 |
+
{"current_steps": 217, "total_steps": 32405, "loss": 1.7449, "lr": 4.9996752615422515e-06, "epoch": 0.03347835477799377, "percentage": 0.67, "elapsed_time": "0:16:01", "remaining_time": "1 day, 15:37:59"}
|
| 218 |
+
{"current_steps": 218, "total_steps": 32405, "loss": 1.7859, "lr": 4.999671337332025e-06, "epoch": 0.03363263291061125, "percentage": 0.67, "elapsed_time": "0:16:05", "remaining_time": "1 day, 15:36:16"}
|
| 219 |
+
{"current_steps": 219, "total_steps": 32405, "loss": 1.7583, "lr": 4.999667389555042e-06, "epoch": 0.033786911043228736, "percentage": 0.68, "elapsed_time": "0:16:10", "remaining_time": "1 day, 15:37:25"}
|
| 220 |
+
{"current_steps": 220, "total_steps": 32405, "loss": 1.783, "lr": 4.999663418211337e-06, "epoch": 0.033941189175846216, "percentage": 0.68, "elapsed_time": "0:16:14", "remaining_time": "1 day, 15:36:20"}
|
| 221 |
+
{"current_steps": 221, "total_steps": 32405, "loss": 1.6475, "lr": 4.999659423300948e-06, "epoch": 0.034095467308463696, "percentage": 0.68, "elapsed_time": "0:16:18", "remaining_time": "1 day, 15:35:17"}
|
| 222 |
+
{"current_steps": 222, "total_steps": 32405, "loss": 1.6065, "lr": 4.999655404823914e-06, "epoch": 0.034249745441081184, "percentage": 0.69, "elapsed_time": "0:16:23", "remaining_time": "1 day, 15:37:00"}
|
| 223 |
+
{"current_steps": 223, "total_steps": 32405, "loss": 1.8277, "lr": 4.999651362780271e-06, "epoch": 0.034404023573698664, "percentage": 0.69, "elapsed_time": "0:16:28", "remaining_time": "1 day, 15:37:45"}
|
| 224 |
+
{"current_steps": 224, "total_steps": 32405, "loss": 1.6764, "lr": 4.999647297170059e-06, "epoch": 0.034558301706316144, "percentage": 0.69, "elapsed_time": "0:16:33", "remaining_time": "1 day, 15:38:06"}
|
| 225 |
+
{"current_steps": 225, "total_steps": 32405, "loss": 1.7146, "lr": 4.999643207993315e-06, "epoch": 0.03471257983893363, "percentage": 0.69, "elapsed_time": "0:16:37", "remaining_time": "1 day, 15:38:02"}
|
| 226 |
+
{"current_steps": 226, "total_steps": 32405, "loss": 1.5972, "lr": 4.999639095250078e-06, "epoch": 0.03486685797155111, "percentage": 0.7, "elapsed_time": "0:16:42", "remaining_time": "1 day, 15:38:59"}
|
| 227 |
+
{"current_steps": 227, "total_steps": 32405, "loss": 1.7017, "lr": 4.9996349589403865e-06, "epoch": 0.03502113610416859, "percentage": 0.7, "elapsed_time": "0:16:48", "remaining_time": "1 day, 15:41:31"}
|
| 228 |
+
{"current_steps": 228, "total_steps": 32405, "loss": 1.7357, "lr": 4.9996307990642805e-06, "epoch": 0.03517541423678608, "percentage": 0.7, "elapsed_time": "0:16:51", "remaining_time": "1 day, 15:39:50"}
|
| 229 |
+
{"current_steps": 229, "total_steps": 32405, "loss": 1.6192, "lr": 4.999626615621797e-06, "epoch": 0.03532969236940356, "percentage": 0.71, "elapsed_time": "0:16:55", "remaining_time": "1 day, 15:38:41"}
|
| 230 |
+
{"current_steps": 230, "total_steps": 32405, "loss": 1.6587, "lr": 4.999622408612978e-06, "epoch": 0.035483970502021046, "percentage": 0.71, "elapsed_time": "0:16:59", "remaining_time": "1 day, 15:37:00"}
|
| 231 |
+
{"current_steps": 231, "total_steps": 32405, "loss": 1.6359, "lr": 4.9996181780378616e-06, "epoch": 0.03563824863463853, "percentage": 0.71, "elapsed_time": "0:17:03", "remaining_time": "1 day, 15:35:20"}
|
| 232 |
+
{"current_steps": 232, "total_steps": 32405, "loss": 1.7803, "lr": 4.999613923896488e-06, "epoch": 0.03579252676725601, "percentage": 0.72, "elapsed_time": "0:17:07", "remaining_time": "1 day, 15:35:07"}
|
| 233 |
+
{"current_steps": 233, "total_steps": 32405, "loss": 1.8323, "lr": 4.999609646188898e-06, "epoch": 0.035946804899873494, "percentage": 0.72, "elapsed_time": "0:17:12", "remaining_time": "1 day, 15:35:42"}
|
| 234 |
+
{"current_steps": 234, "total_steps": 32405, "loss": 1.7478, "lr": 4.9996053449151304e-06, "epoch": 0.036101083032490974, "percentage": 0.72, "elapsed_time": "0:17:16", "remaining_time": "1 day, 15:33:56"}
|
| 235 |
+
{"current_steps": 235, "total_steps": 32405, "loss": 1.7607, "lr": 4.999601020075227e-06, "epoch": 0.036255361165108455, "percentage": 0.73, "elapsed_time": "0:17:22", "remaining_time": "1 day, 15:38:36"}
|
| 236 |
+
{"current_steps": 236, "total_steps": 32405, "loss": 1.6596, "lr": 4.999596671669229e-06, "epoch": 0.03640963929772594, "percentage": 0.73, "elapsed_time": "0:17:26", "remaining_time": "1 day, 15:38:14"}
|
| 237 |
+
{"current_steps": 237, "total_steps": 32405, "loss": 1.703, "lr": 4.9995922996971755e-06, "epoch": 0.03656391743034342, "percentage": 0.73, "elapsed_time": "0:17:31", "remaining_time": "1 day, 15:37:44"}
|
| 238 |
+
{"current_steps": 238, "total_steps": 32405, "loss": 1.7711, "lr": 4.99958790415911e-06, "epoch": 0.03671819556296091, "percentage": 0.73, "elapsed_time": "0:17:35", "remaining_time": "1 day, 15:38:11"}
|
| 239 |
+
{"current_steps": 239, "total_steps": 32405, "loss": 1.6819, "lr": 4.999583485055072e-06, "epoch": 0.03687247369557839, "percentage": 0.74, "elapsed_time": "0:17:40", "remaining_time": "1 day, 15:39:08"}
|
| 240 |
+
{"current_steps": 240, "total_steps": 32405, "loss": 1.8093, "lr": 4.999579042385105e-06, "epoch": 0.03702675182819587, "percentage": 0.74, "elapsed_time": "0:17:45", "remaining_time": "1 day, 15:39:31"}
|
| 241 |
+
{"current_steps": 241, "total_steps": 32405, "loss": 1.7196, "lr": 4.999574576149249e-06, "epoch": 0.03718102996081336, "percentage": 0.74, "elapsed_time": "0:17:50", "remaining_time": "1 day, 15:40:02"}
|
| 242 |
+
{"current_steps": 242, "total_steps": 32405, "loss": 1.7357, "lr": 4.9995700863475474e-06, "epoch": 0.03733530809343084, "percentage": 0.75, "elapsed_time": "0:17:53", "remaining_time": "1 day, 15:38:51"}
|
| 243 |
+
{"current_steps": 243, "total_steps": 32405, "loss": 1.7711, "lr": 4.999565572980042e-06, "epoch": 0.03748958622604832, "percentage": 0.75, "elapsed_time": "0:17:58", "remaining_time": "1 day, 15:38:12"}
|
| 244 |
+
{"current_steps": 244, "total_steps": 32405, "loss": 1.5185, "lr": 4.999561036046776e-06, "epoch": 0.037643864358665804, "percentage": 0.75, "elapsed_time": "0:18:03", "remaining_time": "1 day, 15:40:42"}
|
| 245 |
+
{"current_steps": 245, "total_steps": 32405, "loss": 1.8742, "lr": 4.999556475547791e-06, "epoch": 0.037798142491283285, "percentage": 0.76, "elapsed_time": "0:18:09", "remaining_time": "1 day, 15:42:29"}
|
| 246 |
+
{"current_steps": 246, "total_steps": 32405, "loss": 1.6796, "lr": 4.999551891483131e-06, "epoch": 0.037952420623900765, "percentage": 0.76, "elapsed_time": "0:18:12", "remaining_time": "1 day, 15:40:47"}
|
| 247 |
+
{"current_steps": 247, "total_steps": 32405, "loss": 1.7822, "lr": 4.999547283852838e-06, "epoch": 0.03810669875651825, "percentage": 0.76, "elapsed_time": "0:18:18", "remaining_time": "1 day, 15:43:57"}
|
| 248 |
+
{"current_steps": 248, "total_steps": 32405, "loss": 1.7812, "lr": 4.9995426526569565e-06, "epoch": 0.03826097688913573, "percentage": 0.77, "elapsed_time": "0:18:23", "remaining_time": "1 day, 15:45:15"}
|
| 249 |
+
{"current_steps": 249, "total_steps": 32405, "loss": 1.6268, "lr": 4.999537997895531e-06, "epoch": 0.03841525502175322, "percentage": 0.77, "elapsed_time": "0:18:27", "remaining_time": "1 day, 15:43:17"}
|
| 250 |
+
{"current_steps": 250, "total_steps": 32405, "loss": 1.8091, "lr": 4.9995333195686035e-06, "epoch": 0.0385695331543707, "percentage": 0.77, "elapsed_time": "0:18:30", "remaining_time": "1 day, 15:41:05"}
|
| 251 |
+
{"current_steps": 251, "total_steps": 32405, "loss": 1.6501, "lr": 4.9995286176762195e-06, "epoch": 0.03872381128698818, "percentage": 0.77, "elapsed_time": "0:18:41", "remaining_time": "1 day, 15:55:16"}
|
| 252 |
+
{"current_steps": 252, "total_steps": 32405, "loss": 1.8365, "lr": 4.999523892218423e-06, "epoch": 0.03887808941960567, "percentage": 0.78, "elapsed_time": "0:18:46", "remaining_time": "1 day, 15:56:32"}
|
| 253 |
+
{"current_steps": 253, "total_steps": 32405, "loss": 1.8416, "lr": 4.999519143195257e-06, "epoch": 0.03903236755222315, "percentage": 0.78, "elapsed_time": "0:18:51", "remaining_time": "1 day, 15:56:35"}
|
| 254 |
+
{"current_steps": 254, "total_steps": 32405, "loss": 1.7976, "lr": 4.999514370606769e-06, "epoch": 0.03918664568484063, "percentage": 0.78, "elapsed_time": "0:18:55", "remaining_time": "1 day, 15:55:37"}
|
| 255 |
+
{"current_steps": 255, "total_steps": 32405, "loss": 1.756, "lr": 4.999509574453002e-06, "epoch": 0.039340923817458115, "percentage": 0.79, "elapsed_time": "0:19:00", "remaining_time": "1 day, 15:55:42"}
|
| 256 |
+
{"current_steps": 256, "total_steps": 32405, "loss": 1.6261, "lr": 4.999504754734002e-06, "epoch": 0.039495201950075595, "percentage": 0.79, "elapsed_time": "0:19:04", "remaining_time": "1 day, 15:55:41"}
|
| 257 |
+
{"current_steps": 257, "total_steps": 32405, "loss": 1.6508, "lr": 4.999499911449815e-06, "epoch": 0.03964948008269308, "percentage": 0.79, "elapsed_time": "0:19:08", "remaining_time": "1 day, 15:53:52"}
|
| 258 |
+
{"current_steps": 258, "total_steps": 32405, "loss": 1.8314, "lr": 4.999495044600484e-06, "epoch": 0.03980375821531056, "percentage": 0.8, "elapsed_time": "0:19:12", "remaining_time": "1 day, 15:54:02"}
|
| 259 |
+
{"current_steps": 259, "total_steps": 32405, "loss": 1.7651, "lr": 4.999490154186058e-06, "epoch": 0.03995803634792804, "percentage": 0.8, "elapsed_time": "0:19:18", "remaining_time": "1 day, 15:55:30"}
|
| 260 |
+
{"current_steps": 260, "total_steps": 32405, "loss": 1.6905, "lr": 4.999485240206582e-06, "epoch": 0.04011231448054553, "percentage": 0.8, "elapsed_time": "0:19:22", "remaining_time": "1 day, 15:54:49"}
|
| 261 |
+
{"current_steps": 261, "total_steps": 32405, "loss": 1.7039, "lr": 4.999480302662102e-06, "epoch": 0.04026659261316301, "percentage": 0.81, "elapsed_time": "0:19:26", "remaining_time": "1 day, 15:54:23"}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:286a514074eeefecf14dc688a84d3259a5ac400f6e75bb6c41b07674476320bc
|
| 3 |
+
size 7608
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|