Training in progress, epoch 0
Browse files- config.json +3 -4
- model-00001-of-00004.safetensors +1 -1
- model-00002-of-00004.safetensors +1 -1
- model-00003-of-00004.safetensors +1 -1
- model-00004-of-00004.safetensors +1 -1
- special_tokens_map.json +1 -1
- tokenizer_config.json +2 -2
- trainer_log.jsonl +282 -40
- training_args.bin +2 -2
config.json
CHANGED
|
@@ -1,16 +1,16 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "Qwen/Qwen2.5-7B",
|
| 3 |
"architectures": [
|
| 4 |
"Qwen2ForCausalLM"
|
| 5 |
],
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 151643,
|
| 8 |
-
"eos_token_id":
|
| 9 |
"hidden_act": "silu",
|
| 10 |
"hidden_size": 3584,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
"intermediate_size": 18944,
|
| 13 |
-
"max_position_embeddings":
|
| 14 |
"max_window_layers": 28,
|
| 15 |
"model_type": "qwen2",
|
| 16 |
"num_attention_heads": 28,
|
|
@@ -24,7 +24,6 @@
|
|
| 24 |
"torch_dtype": "bfloat16",
|
| 25 |
"transformers_version": "4.46.1",
|
| 26 |
"use_cache": false,
|
| 27 |
-
"use_mrope": false,
|
| 28 |
"use_sliding_window": false,
|
| 29 |
"vocab_size": 152064
|
| 30 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
|
| 3 |
"architectures": [
|
| 4 |
"Qwen2ForCausalLM"
|
| 5 |
],
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
"hidden_act": "silu",
|
| 10 |
"hidden_size": 3584,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
"intermediate_size": 18944,
|
| 13 |
+
"max_position_embeddings": 32768,
|
| 14 |
"max_window_layers": 28,
|
| 15 |
"model_type": "qwen2",
|
| 16 |
"num_attention_heads": 28,
|
|
|
|
| 24 |
"torch_dtype": "bfloat16",
|
| 25 |
"transformers_version": "4.46.1",
|
| 26 |
"use_cache": false,
|
|
|
|
| 27 |
"use_sliding_window": false,
|
| 28 |
"vocab_size": 152064
|
| 29 |
}
|
model-00001-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4877660776
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c1930d76f2293874c86cdb0a1aa38f517f586665a259d3edfb3ffb95ff3e2ea
|
| 3 |
size 4877660776
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4932751008
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:edc547ad489b01055a659a621a34c5dde64b6b7f6e7c0cb6f6e002e32cdbe559
|
| 3 |
size 4932751008
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4330865200
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:edda8c18114cf21122957c4e5f3e0e6e4e29c7b021ba0bcb7d7498a5ec68d0e8
|
| 3 |
size 4330865200
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1089994880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e38f26e1b02f433e79cf97552c2b118d654da944e260f1f109860135c471383
|
| 3 |
size 1089994880
|
special_tokens_map.json
CHANGED
|
@@ -15,7 +15,7 @@
|
|
| 15 |
"<|video_pad|>"
|
| 16 |
],
|
| 17 |
"eos_token": {
|
| 18 |
-
"content": "<|
|
| 19 |
"lstrip": false,
|
| 20 |
"normalized": false,
|
| 21 |
"rstrip": false,
|
|
|
|
| 15 |
"<|video_pad|>"
|
| 16 |
],
|
| 17 |
"eos_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
"lstrip": false,
|
| 20 |
"normalized": false,
|
| 21 |
"rstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -195,9 +195,9 @@
|
|
| 195 |
"<|video_pad|>"
|
| 196 |
],
|
| 197 |
"bos_token": null,
|
| 198 |
-
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- '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 <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|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 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<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\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<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\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",
|
| 199 |
"clean_up_tokenization_spaces": false,
|
| 200 |
-
"eos_token": "<|
|
| 201 |
"errors": "replace",
|
| 202 |
"model_max_length": 131072,
|
| 203 |
"pad_token": "<|endoftext|>",
|
|
|
|
| 195 |
"<|video_pad|>"
|
| 196 |
],
|
| 197 |
"bos_token": null,
|
| 198 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. 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 <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|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 Qwen, created by Alibaba Cloud. 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<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\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<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\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",
|
| 199 |
"clean_up_tokenization_spaces": false,
|
| 200 |
+
"eos_token": "<|endoftext|>",
|
| 201 |
"errors": "replace",
|
| 202 |
"model_max_length": 131072,
|
| 203 |
"pad_token": "<|endoftext|>",
|
trainer_log.jsonl
CHANGED
|
@@ -1,40 +1,282 @@
|
|
| 1 |
-
{"current_steps":
|
| 2 |
-
{"current_steps":
|
| 3 |
-
{"current_steps":
|
| 4 |
-
{"current_steps":
|
| 5 |
-
{"current_steps":
|
| 6 |
-
{"current_steps":
|
| 7 |
-
{"current_steps":
|
| 8 |
-
{"current_steps":
|
| 9 |
-
{"current_steps":
|
| 10 |
-
{"current_steps":
|
| 11 |
-
{"current_steps":
|
| 12 |
-
{"current_steps":
|
| 13 |
-
{"current_steps":
|
| 14 |
-
{"current_steps":
|
| 15 |
-
{"current_steps":
|
| 16 |
-
{"current_steps":
|
| 17 |
-
{"current_steps":
|
| 18 |
-
{"current_steps":
|
| 19 |
-
{"current_steps":
|
| 20 |
-
{"current_steps":
|
| 21 |
-
{"current_steps":
|
| 22 |
-
{"current_steps":
|
| 23 |
-
{"current_steps":
|
| 24 |
-
{"current_steps":
|
| 25 |
-
{"current_steps":
|
| 26 |
-
{"current_steps":
|
| 27 |
-
{"current_steps":
|
| 28 |
-
{"current_steps":
|
| 29 |
-
{"current_steps":
|
| 30 |
-
{"current_steps":
|
| 31 |
-
{"current_steps":
|
| 32 |
-
{"current_steps":
|
| 33 |
-
{"current_steps":
|
| 34 |
-
{"current_steps":
|
| 35 |
-
{"current_steps":
|
| 36 |
-
{"current_steps":
|
| 37 |
-
{"current_steps":
|
| 38 |
-
{"current_steps":
|
| 39 |
-
{"current_steps":
|
| 40 |
-
{"current_steps":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 1, "total_steps": 522, "loss": 0.8871, "lr": 1.886792452830189e-07, "epoch": 0.0057361376673040155, "percentage": 0.19, "elapsed_time": "0:00:18", "remaining_time": "2:43:12"}
|
| 2 |
+
{"current_steps": 2, "total_steps": 522, "loss": 0.9169, "lr": 3.773584905660378e-07, "epoch": 0.011472275334608031, "percentage": 0.38, "elapsed_time": "0:00:32", "remaining_time": "2:22:56"}
|
| 3 |
+
{"current_steps": 3, "total_steps": 522, "loss": 0.9419, "lr": 5.660377358490567e-07, "epoch": 0.017208413001912046, "percentage": 0.57, "elapsed_time": "0:00:45", "remaining_time": "2:10:25"}
|
| 4 |
+
{"current_steps": 4, "total_steps": 522, "loss": 0.908, "lr": 7.547169811320755e-07, "epoch": 0.022944550669216062, "percentage": 0.77, "elapsed_time": "0:00:57", "remaining_time": "2:04:13"}
|
| 5 |
+
{"current_steps": 5, "total_steps": 522, "loss": 0.9057, "lr": 9.433962264150944e-07, "epoch": 0.028680688336520075, "percentage": 0.96, "elapsed_time": "0:01:10", "remaining_time": "2:02:02"}
|
| 6 |
+
{"current_steps": 6, "total_steps": 522, "loss": 0.898, "lr": 1.1320754716981133e-06, "epoch": 0.03441682600382409, "percentage": 1.15, "elapsed_time": "0:01:22", "remaining_time": "1:58:25"}
|
| 7 |
+
{"current_steps": 7, "total_steps": 522, "loss": 0.9124, "lr": 1.3207547169811322e-06, "epoch": 0.040152963671128104, "percentage": 1.34, "elapsed_time": "0:01:37", "remaining_time": "1:59:05"}
|
| 8 |
+
{"current_steps": 8, "total_steps": 522, "loss": 0.8682, "lr": 1.509433962264151e-06, "epoch": 0.045889101338432124, "percentage": 1.53, "elapsed_time": "0:01:49", "remaining_time": "1:57:34"}
|
| 9 |
+
{"current_steps": 9, "total_steps": 522, "loss": 0.8339, "lr": 1.6981132075471698e-06, "epoch": 0.05162523900573614, "percentage": 1.72, "elapsed_time": "0:02:04", "remaining_time": "1:58:05"}
|
| 10 |
+
{"current_steps": 10, "total_steps": 522, "loss": 0.8696, "lr": 1.8867924528301889e-06, "epoch": 0.05736137667304015, "percentage": 1.92, "elapsed_time": "0:02:18", "remaining_time": "1:58:04"}
|
| 11 |
+
{"current_steps": 11, "total_steps": 522, "loss": 0.8172, "lr": 2.075471698113208e-06, "epoch": 0.06309751434034416, "percentage": 2.11, "elapsed_time": "0:02:32", "remaining_time": "1:57:58"}
|
| 12 |
+
{"current_steps": 12, "total_steps": 522, "loss": 0.7592, "lr": 2.2641509433962266e-06, "epoch": 0.06883365200764818, "percentage": 2.3, "elapsed_time": "0:02:48", "remaining_time": "1:59:38"}
|
| 13 |
+
{"current_steps": 13, "total_steps": 522, "loss": 0.8284, "lr": 2.4528301886792453e-06, "epoch": 0.0745697896749522, "percentage": 2.49, "elapsed_time": "0:03:03", "remaining_time": "1:59:46"}
|
| 14 |
+
{"current_steps": 14, "total_steps": 522, "loss": 0.7991, "lr": 2.6415094339622644e-06, "epoch": 0.08030592734225621, "percentage": 2.68, "elapsed_time": "0:03:15", "remaining_time": "1:58:20"}
|
| 15 |
+
{"current_steps": 15, "total_steps": 522, "loss": 0.7871, "lr": 2.830188679245283e-06, "epoch": 0.08604206500956023, "percentage": 2.87, "elapsed_time": "0:03:29", "remaining_time": "1:57:46"}
|
| 16 |
+
{"current_steps": 16, "total_steps": 522, "loss": 0.7975, "lr": 3.018867924528302e-06, "epoch": 0.09177820267686425, "percentage": 3.07, "elapsed_time": "0:03:43", "remaining_time": "1:57:43"}
|
| 17 |
+
{"current_steps": 17, "total_steps": 522, "loss": 0.7751, "lr": 3.207547169811321e-06, "epoch": 0.09751434034416825, "percentage": 3.26, "elapsed_time": "0:03:56", "remaining_time": "1:57:06"}
|
| 18 |
+
{"current_steps": 18, "total_steps": 522, "loss": 0.7704, "lr": 3.3962264150943395e-06, "epoch": 0.10325047801147227, "percentage": 3.45, "elapsed_time": "0:04:11", "remaining_time": "1:57:11"}
|
| 19 |
+
{"current_steps": 19, "total_steps": 522, "loss": 0.7, "lr": 3.5849056603773586e-06, "epoch": 0.1089866156787763, "percentage": 3.64, "elapsed_time": "0:04:25", "remaining_time": "1:57:17"}
|
| 20 |
+
{"current_steps": 20, "total_steps": 522, "loss": 0.7275, "lr": 3.7735849056603777e-06, "epoch": 0.1147227533460803, "percentage": 3.83, "elapsed_time": "0:04:41", "remaining_time": "1:57:50"}
|
| 21 |
+
{"current_steps": 21, "total_steps": 522, "loss": 0.6948, "lr": 3.962264150943396e-06, "epoch": 0.12045889101338432, "percentage": 4.02, "elapsed_time": "0:04:57", "remaining_time": "1:58:10"}
|
| 22 |
+
{"current_steps": 22, "total_steps": 522, "loss": 0.6899, "lr": 4.150943396226416e-06, "epoch": 0.12619502868068833, "percentage": 4.21, "elapsed_time": "0:05:05", "remaining_time": "1:55:54"}
|
| 23 |
+
{"current_steps": 23, "total_steps": 522, "loss": 0.6527, "lr": 4.339622641509435e-06, "epoch": 0.13193116634799235, "percentage": 4.41, "elapsed_time": "0:05:20", "remaining_time": "1:55:52"}
|
| 24 |
+
{"current_steps": 24, "total_steps": 522, "loss": 0.6843, "lr": 4.528301886792453e-06, "epoch": 0.13766730401529637, "percentage": 4.6, "elapsed_time": "0:05:35", "remaining_time": "1:55:51"}
|
| 25 |
+
{"current_steps": 25, "total_steps": 522, "loss": 0.6668, "lr": 4.716981132075472e-06, "epoch": 0.14340344168260039, "percentage": 4.79, "elapsed_time": "0:05:51", "remaining_time": "1:56:20"}
|
| 26 |
+
{"current_steps": 26, "total_steps": 522, "loss": 0.643, "lr": 4.905660377358491e-06, "epoch": 0.1491395793499044, "percentage": 4.98, "elapsed_time": "0:06:05", "remaining_time": "1:56:15"}
|
| 27 |
+
{"current_steps": 27, "total_steps": 522, "loss": 0.6828, "lr": 5.09433962264151e-06, "epoch": 0.15487571701720843, "percentage": 5.17, "elapsed_time": "0:06:22", "remaining_time": "1:56:58"}
|
| 28 |
+
{"current_steps": 28, "total_steps": 522, "loss": 0.6592, "lr": 5.283018867924529e-06, "epoch": 0.16061185468451242, "percentage": 5.36, "elapsed_time": "0:06:36", "remaining_time": "1:56:42"}
|
| 29 |
+
{"current_steps": 29, "total_steps": 522, "loss": 0.6377, "lr": 5.4716981132075475e-06, "epoch": 0.16634799235181644, "percentage": 5.56, "elapsed_time": "0:06:49", "remaining_time": "1:56:00"}
|
| 30 |
+
{"current_steps": 30, "total_steps": 522, "loss": 0.6354, "lr": 5.660377358490566e-06, "epoch": 0.17208413001912046, "percentage": 5.75, "elapsed_time": "0:07:04", "remaining_time": "1:56:00"}
|
| 31 |
+
{"current_steps": 31, "total_steps": 522, "loss": 0.6025, "lr": 5.849056603773585e-06, "epoch": 0.17782026768642448, "percentage": 5.94, "elapsed_time": "0:07:19", "remaining_time": "1:56:04"}
|
| 32 |
+
{"current_steps": 32, "total_steps": 522, "loss": 0.588, "lr": 6.037735849056604e-06, "epoch": 0.1835564053537285, "percentage": 6.13, "elapsed_time": "0:07:31", "remaining_time": "1:55:09"}
|
| 33 |
+
{"current_steps": 33, "total_steps": 522, "loss": 0.6162, "lr": 6.226415094339623e-06, "epoch": 0.18929254302103252, "percentage": 6.32, "elapsed_time": "0:07:46", "remaining_time": "1:55:09"}
|
| 34 |
+
{"current_steps": 34, "total_steps": 522, "loss": 0.641, "lr": 6.415094339622642e-06, "epoch": 0.1950286806883365, "percentage": 6.51, "elapsed_time": "0:07:58", "remaining_time": "1:54:21"}
|
| 35 |
+
{"current_steps": 35, "total_steps": 522, "loss": 0.6102, "lr": 6.60377358490566e-06, "epoch": 0.20076481835564053, "percentage": 6.7, "elapsed_time": "0:08:13", "remaining_time": "1:54:29"}
|
| 36 |
+
{"current_steps": 36, "total_steps": 522, "loss": 0.5989, "lr": 6.792452830188679e-06, "epoch": 0.20650095602294455, "percentage": 6.9, "elapsed_time": "0:08:30", "remaining_time": "1:54:45"}
|
| 37 |
+
{"current_steps": 37, "total_steps": 522, "loss": 0.5974, "lr": 6.981132075471699e-06, "epoch": 0.21223709369024857, "percentage": 7.09, "elapsed_time": "0:08:47", "remaining_time": "1:55:09"}
|
| 38 |
+
{"current_steps": 38, "total_steps": 522, "loss": 0.6138, "lr": 7.169811320754717e-06, "epoch": 0.2179732313575526, "percentage": 7.28, "elapsed_time": "0:09:03", "remaining_time": "1:55:28"}
|
| 39 |
+
{"current_steps": 39, "total_steps": 522, "loss": 0.6164, "lr": 7.358490566037736e-06, "epoch": 0.2237093690248566, "percentage": 7.47, "elapsed_time": "0:09:18", "remaining_time": "1:55:22"}
|
| 40 |
+
{"current_steps": 40, "total_steps": 522, "loss": 0.5681, "lr": 7.5471698113207555e-06, "epoch": 0.2294455066921606, "percentage": 7.66, "elapsed_time": "0:09:33", "remaining_time": "1:55:14"}
|
| 41 |
+
{"current_steps": 41, "total_steps": 522, "loss": 0.6223, "lr": 7.735849056603775e-06, "epoch": 0.23518164435946462, "percentage": 7.85, "elapsed_time": "0:09:47", "remaining_time": "1:54:52"}
|
| 42 |
+
{"current_steps": 42, "total_steps": 522, "loss": 0.5543, "lr": 7.924528301886793e-06, "epoch": 0.24091778202676864, "percentage": 8.05, "elapsed_time": "0:10:04", "remaining_time": "1:55:13"}
|
| 43 |
+
{"current_steps": 43, "total_steps": 522, "loss": 0.611, "lr": 8.113207547169812e-06, "epoch": 0.24665391969407266, "percentage": 8.24, "elapsed_time": "0:10:21", "remaining_time": "1:55:18"}
|
| 44 |
+
{"current_steps": 44, "total_steps": 522, "loss": 0.6055, "lr": 8.301886792452832e-06, "epoch": 0.25239005736137665, "percentage": 8.43, "elapsed_time": "0:10:36", "remaining_time": "1:55:12"}
|
| 45 |
+
{"current_steps": 45, "total_steps": 522, "loss": 0.589, "lr": 8.49056603773585e-06, "epoch": 0.25812619502868067, "percentage": 8.62, "elapsed_time": "0:10:49", "remaining_time": "1:54:44"}
|
| 46 |
+
{"current_steps": 46, "total_steps": 522, "loss": 0.5477, "lr": 8.67924528301887e-06, "epoch": 0.2638623326959847, "percentage": 8.81, "elapsed_time": "0:11:07", "remaining_time": "1:55:03"}
|
| 47 |
+
{"current_steps": 47, "total_steps": 522, "loss": 0.5881, "lr": 8.867924528301887e-06, "epoch": 0.2695984703632887, "percentage": 9.0, "elapsed_time": "0:11:20", "remaining_time": "1:54:40"}
|
| 48 |
+
{"current_steps": 48, "total_steps": 522, "loss": 0.5718, "lr": 9.056603773584907e-06, "epoch": 0.27533460803059273, "percentage": 9.2, "elapsed_time": "0:11:35", "remaining_time": "1:54:25"}
|
| 49 |
+
{"current_steps": 49, "total_steps": 522, "loss": 0.5965, "lr": 9.245283018867926e-06, "epoch": 0.28107074569789675, "percentage": 9.39, "elapsed_time": "0:11:51", "remaining_time": "1:54:31"}
|
| 50 |
+
{"current_steps": 50, "total_steps": 522, "loss": 0.552, "lr": 9.433962264150944e-06, "epoch": 0.28680688336520077, "percentage": 9.58, "elapsed_time": "0:12:07", "remaining_time": "1:54:25"}
|
| 51 |
+
{"current_steps": 51, "total_steps": 522, "loss": 0.5408, "lr": 9.622641509433963e-06, "epoch": 0.2925430210325048, "percentage": 9.77, "elapsed_time": "0:12:23", "remaining_time": "1:54:24"}
|
| 52 |
+
{"current_steps": 52, "total_steps": 522, "loss": 0.5792, "lr": 9.811320754716981e-06, "epoch": 0.2982791586998088, "percentage": 9.96, "elapsed_time": "0:12:37", "remaining_time": "1:54:09"}
|
| 53 |
+
{"current_steps": 53, "total_steps": 522, "loss": 0.5689, "lr": 1e-05, "epoch": 0.30401529636711283, "percentage": 10.15, "elapsed_time": "0:12:48", "remaining_time": "1:53:19"}
|
| 54 |
+
{"current_steps": 54, "total_steps": 522, "loss": 0.537, "lr": 9.999887825938495e-06, "epoch": 0.30975143403441685, "percentage": 10.34, "elapsed_time": "0:13:04", "remaining_time": "1:53:17"}
|
| 55 |
+
{"current_steps": 55, "total_steps": 522, "loss": 0.5519, "lr": 9.999551308787183e-06, "epoch": 0.3154875717017208, "percentage": 10.54, "elapsed_time": "0:13:17", "remaining_time": "1:52:54"}
|
| 56 |
+
{"current_steps": 56, "total_steps": 522, "loss": 0.5595, "lr": 9.998990463645464e-06, "epoch": 0.32122370936902483, "percentage": 10.73, "elapsed_time": "0:13:31", "remaining_time": "1:52:35"}
|
| 57 |
+
{"current_steps": 57, "total_steps": 522, "loss": 0.5632, "lr": 9.998205315678248e-06, "epoch": 0.32695984703632885, "percentage": 10.92, "elapsed_time": "0:13:47", "remaining_time": "1:52:32"}
|
| 58 |
+
{"current_steps": 58, "total_steps": 522, "loss": 0.5605, "lr": 9.997195900114833e-06, "epoch": 0.3326959847036329, "percentage": 11.11, "elapsed_time": "0:14:03", "remaining_time": "1:52:24"}
|
| 59 |
+
{"current_steps": 59, "total_steps": 522, "loss": 0.5474, "lr": 9.995962262247314e-06, "epoch": 0.3384321223709369, "percentage": 11.3, "elapsed_time": "0:14:16", "remaining_time": "1:52:03"}
|
| 60 |
+
{"current_steps": 60, "total_steps": 522, "loss": 0.5331, "lr": 9.994504457428557e-06, "epoch": 0.3441682600382409, "percentage": 11.49, "elapsed_time": "0:14:30", "remaining_time": "1:51:46"}
|
| 61 |
+
{"current_steps": 61, "total_steps": 522, "loss": 0.5594, "lr": 9.99282255106972e-06, "epoch": 0.34990439770554493, "percentage": 11.69, "elapsed_time": "0:14:48", "remaining_time": "1:51:52"}
|
| 62 |
+
{"current_steps": 62, "total_steps": 522, "loss": 0.558, "lr": 9.99091661863731e-06, "epoch": 0.35564053537284895, "percentage": 11.88, "elapsed_time": "0:15:03", "remaining_time": "1:51:40"}
|
| 63 |
+
{"current_steps": 63, "total_steps": 522, "loss": 0.5569, "lr": 9.988786745649798e-06, "epoch": 0.361376673040153, "percentage": 12.07, "elapsed_time": "0:15:18", "remaining_time": "1:51:32"}
|
| 64 |
+
{"current_steps": 64, "total_steps": 522, "loss": 0.5383, "lr": 9.986433027673786e-06, "epoch": 0.367112810707457, "percentage": 12.26, "elapsed_time": "0:15:35", "remaining_time": "1:51:32"}
|
| 65 |
+
{"current_steps": 65, "total_steps": 522, "loss": 0.5489, "lr": 9.983855570319716e-06, "epoch": 0.372848948374761, "percentage": 12.45, "elapsed_time": "0:15:47", "remaining_time": "1:50:59"}
|
| 66 |
+
{"current_steps": 66, "total_steps": 522, "loss": 0.5542, "lr": 9.981054489237132e-06, "epoch": 0.37858508604206503, "percentage": 12.64, "elapsed_time": "0:16:00", "remaining_time": "1:50:35"}
|
| 67 |
+
{"current_steps": 67, "total_steps": 522, "loss": 0.5259, "lr": 9.978029910109491e-06, "epoch": 0.384321223709369, "percentage": 12.84, "elapsed_time": "0:16:11", "remaining_time": "1:49:58"}
|
| 68 |
+
{"current_steps": 68, "total_steps": 522, "loss": 0.5373, "lr": 9.974781968648523e-06, "epoch": 0.390057361376673, "percentage": 13.03, "elapsed_time": "0:16:26", "remaining_time": "1:49:43"}
|
| 69 |
+
{"current_steps": 69, "total_steps": 522, "loss": 0.544, "lr": 9.971310810588141e-06, "epoch": 0.39579349904397704, "percentage": 13.22, "elapsed_time": "0:16:44", "remaining_time": "1:49:53"}
|
| 70 |
+
{"current_steps": 70, "total_steps": 522, "loss": 0.4899, "lr": 9.967616591677906e-06, "epoch": 0.40152963671128106, "percentage": 13.41, "elapsed_time": "0:16:58", "remaining_time": "1:49:37"}
|
| 71 |
+
{"current_steps": 71, "total_steps": 522, "loss": 0.5448, "lr": 9.963699477676031e-06, "epoch": 0.4072657743785851, "percentage": 13.6, "elapsed_time": "0:17:08", "remaining_time": "1:48:52"}
|
| 72 |
+
{"current_steps": 72, "total_steps": 522, "loss": 0.5087, "lr": 9.959559644341954e-06, "epoch": 0.4130019120458891, "percentage": 13.79, "elapsed_time": "0:17:22", "remaining_time": "1:48:34"}
|
| 73 |
+
{"current_steps": 73, "total_steps": 522, "loss": 0.5434, "lr": 9.95519727742844e-06, "epoch": 0.4187380497131931, "percentage": 13.98, "elapsed_time": "0:17:38", "remaining_time": "1:48:30"}
|
| 74 |
+
{"current_steps": 74, "total_steps": 522, "loss": 0.5399, "lr": 9.950612572673255e-06, "epoch": 0.42447418738049714, "percentage": 14.18, "elapsed_time": "0:17:52", "remaining_time": "1:48:10"}
|
| 75 |
+
{"current_steps": 75, "total_steps": 522, "loss": 0.5574, "lr": 9.945805735790383e-06, "epoch": 0.43021032504780116, "percentage": 14.37, "elapsed_time": "0:18:07", "remaining_time": "1:48:04"}
|
| 76 |
+
{"current_steps": 76, "total_steps": 522, "loss": 0.5386, "lr": 9.940776982460787e-06, "epoch": 0.4359464627151052, "percentage": 14.56, "elapsed_time": "0:18:24", "remaining_time": "1:48:01"}
|
| 77 |
+
{"current_steps": 77, "total_steps": 522, "loss": 0.5512, "lr": 9.935526538322744e-06, "epoch": 0.4416826003824092, "percentage": 14.75, "elapsed_time": "0:18:41", "remaining_time": "1:48:03"}
|
| 78 |
+
{"current_steps": 78, "total_steps": 522, "loss": 0.5389, "lr": 9.930054638961709e-06, "epoch": 0.4474187380497132, "percentage": 14.94, "elapsed_time": "0:18:57", "remaining_time": "1:47:56"}
|
| 79 |
+
{"current_steps": 79, "total_steps": 522, "loss": 0.5485, "lr": 9.924361529899754e-06, "epoch": 0.45315487571701724, "percentage": 15.13, "elapsed_time": "0:19:15", "remaining_time": "1:48:00"}
|
| 80 |
+
{"current_steps": 80, "total_steps": 522, "loss": 0.5311, "lr": 9.918447466584545e-06, "epoch": 0.4588910133843212, "percentage": 15.33, "elapsed_time": "0:19:32", "remaining_time": "1:48:00"}
|
| 81 |
+
{"current_steps": 81, "total_steps": 522, "loss": 0.5337, "lr": 9.91231271437788e-06, "epoch": 0.4646271510516252, "percentage": 15.52, "elapsed_time": "0:19:47", "remaining_time": "1:47:42"}
|
| 82 |
+
{"current_steps": 82, "total_steps": 522, "loss": 0.5584, "lr": 9.905957548543794e-06, "epoch": 0.47036328871892924, "percentage": 15.71, "elapsed_time": "0:20:02", "remaining_time": "1:47:33"}
|
| 83 |
+
{"current_steps": 83, "total_steps": 522, "loss": 0.5309, "lr": 9.899382254236186e-06, "epoch": 0.47609942638623326, "percentage": 15.9, "elapsed_time": "0:20:16", "remaining_time": "1:47:14"}
|
| 84 |
+
{"current_steps": 84, "total_steps": 522, "loss": 0.5439, "lr": 9.892587126486046e-06, "epoch": 0.4818355640535373, "percentage": 16.09, "elapsed_time": "0:20:28", "remaining_time": "1:46:48"}
|
| 85 |
+
{"current_steps": 85, "total_steps": 522, "loss": 0.5282, "lr": 9.885572470188207e-06, "epoch": 0.4875717017208413, "percentage": 16.28, "elapsed_time": "0:20:44", "remaining_time": "1:46:36"}
|
| 86 |
+
{"current_steps": 86, "total_steps": 522, "loss": 0.5337, "lr": 9.878338600087658e-06, "epoch": 0.4933078393881453, "percentage": 16.48, "elapsed_time": "0:20:59", "remaining_time": "1:46:24"}
|
| 87 |
+
{"current_steps": 87, "total_steps": 522, "loss": 0.5559, "lr": 9.87088584076544e-06, "epoch": 0.49904397705544934, "percentage": 16.67, "elapsed_time": "0:21:14", "remaining_time": "1:46:10"}
|
| 88 |
+
{"current_steps": 88, "total_steps": 522, "loss": 0.5363, "lr": 9.863214526624065e-06, "epoch": 0.5047801147227533, "percentage": 16.86, "elapsed_time": "0:21:31", "remaining_time": "1:46:08"}
|
| 89 |
+
{"current_steps": 89, "total_steps": 522, "loss": 0.5445, "lr": 9.85532500187252e-06, "epoch": 0.5105162523900574, "percentage": 17.05, "elapsed_time": "0:21:45", "remaining_time": "1:45:52"}
|
| 90 |
+
{"current_steps": 90, "total_steps": 522, "loss": 0.5503, "lr": 9.847217620510815e-06, "epoch": 0.5162523900573613, "percentage": 17.24, "elapsed_time": "0:21:59", "remaining_time": "1:45:35"}
|
| 91 |
+
{"current_steps": 91, "total_steps": 522, "loss": 0.5029, "lr": 9.83889274631411e-06, "epoch": 0.5219885277246654, "percentage": 17.43, "elapsed_time": "0:22:14", "remaining_time": "1:45:21"}
|
| 92 |
+
{"current_steps": 92, "total_steps": 522, "loss": 0.5211, "lr": 9.830350752816386e-06, "epoch": 0.5277246653919694, "percentage": 17.62, "elapsed_time": "0:22:31", "remaining_time": "1:45:15"}
|
| 93 |
+
{"current_steps": 93, "total_steps": 522, "loss": 0.531, "lr": 9.821592023293686e-06, "epoch": 0.5334608030592735, "percentage": 17.82, "elapsed_time": "0:22:46", "remaining_time": "1:45:01"}
|
| 94 |
+
{"current_steps": 94, "total_steps": 522, "loss": 0.5281, "lr": 9.81261695074691e-06, "epoch": 0.5391969407265774, "percentage": 18.01, "elapsed_time": "0:22:58", "remaining_time": "1:44:37"}
|
| 95 |
+
{"current_steps": 95, "total_steps": 522, "loss": 0.5408, "lr": 9.803425937884202e-06, "epoch": 0.5449330783938815, "percentage": 18.2, "elapsed_time": "0:23:14", "remaining_time": "1:44:27"}
|
| 96 |
+
{"current_steps": 96, "total_steps": 522, "loss": 0.54, "lr": 9.794019397102852e-06, "epoch": 0.5506692160611855, "percentage": 18.39, "elapsed_time": "0:23:27", "remaining_time": "1:44:07"}
|
| 97 |
+
{"current_steps": 97, "total_steps": 522, "loss": 0.5088, "lr": 9.784397750470818e-06, "epoch": 0.5564053537284895, "percentage": 18.58, "elapsed_time": "0:23:41", "remaining_time": "1:43:49"}
|
| 98 |
+
{"current_steps": 98, "total_steps": 522, "loss": 0.5648, "lr": 9.774561429707769e-06, "epoch": 0.5621414913957935, "percentage": 18.77, "elapsed_time": "0:23:56", "remaining_time": "1:43:36"}
|
| 99 |
+
{"current_steps": 99, "total_steps": 522, "loss": 0.5251, "lr": 9.764510876165727e-06, "epoch": 0.5678776290630975, "percentage": 18.97, "elapsed_time": "0:24:08", "remaining_time": "1:43:07"}
|
| 100 |
+
{"current_steps": 100, "total_steps": 522, "loss": 0.5171, "lr": 9.754246540809257e-06, "epoch": 0.5736137667304015, "percentage": 19.16, "elapsed_time": "0:24:19", "remaining_time": "1:42:40"}
|
| 101 |
+
{"current_steps": 101, "total_steps": 522, "loss": 0.5477, "lr": 9.743768884195233e-06, "epoch": 0.5793499043977055, "percentage": 19.35, "elapsed_time": "0:24:35", "remaining_time": "1:42:29"}
|
| 102 |
+
{"current_steps": 102, "total_steps": 522, "loss": 0.5422, "lr": 9.733078376452172e-06, "epoch": 0.5850860420650096, "percentage": 19.54, "elapsed_time": "0:24:51", "remaining_time": "1:42:20"}
|
| 103 |
+
{"current_steps": 103, "total_steps": 522, "loss": 0.5329, "lr": 9.722175497259145e-06, "epoch": 0.5908221797323135, "percentage": 19.73, "elapsed_time": "0:25:03", "remaining_time": "1:41:56"}
|
| 104 |
+
{"current_steps": 104, "total_steps": 522, "loss": 0.524, "lr": 9.71106073582425e-06, "epoch": 0.5965583173996176, "percentage": 19.92, "elapsed_time": "0:25:20", "remaining_time": "1:41:50"}
|
| 105 |
+
{"current_steps": 105, "total_steps": 522, "loss": 0.5187, "lr": 9.699734590862655e-06, "epoch": 0.6022944550669216, "percentage": 20.11, "elapsed_time": "0:25:31", "remaining_time": "1:41:22"}
|
| 106 |
+
{"current_steps": 106, "total_steps": 522, "loss": 0.5449, "lr": 9.688197570574238e-06, "epoch": 0.6080305927342257, "percentage": 20.31, "elapsed_time": "0:25:44", "remaining_time": "1:41:01"}
|
| 107 |
+
{"current_steps": 107, "total_steps": 522, "loss": 0.5302, "lr": 9.676450192620767e-06, "epoch": 0.6137667304015296, "percentage": 20.5, "elapsed_time": "0:25:58", "remaining_time": "1:40:46"}
|
| 108 |
+
{"current_steps": 108, "total_steps": 522, "loss": 0.5391, "lr": 9.66449298410268e-06, "epoch": 0.6195028680688337, "percentage": 20.69, "elapsed_time": "0:26:13", "remaining_time": "1:40:33"}
|
| 109 |
+
{"current_steps": 109, "total_steps": 522, "loss": 0.4988, "lr": 9.652326481535434e-06, "epoch": 0.6252390057361377, "percentage": 20.88, "elapsed_time": "0:26:27", "remaining_time": "1:40:15"}
|
| 110 |
+
{"current_steps": 110, "total_steps": 522, "loss": 0.543, "lr": 9.639951230825433e-06, "epoch": 0.6309751434034416, "percentage": 21.07, "elapsed_time": "0:26:42", "remaining_time": "1:40:01"}
|
| 111 |
+
{"current_steps": 111, "total_steps": 522, "loss": 0.5442, "lr": 9.62736778724553e-06, "epoch": 0.6367112810707457, "percentage": 21.26, "elapsed_time": "0:26:54", "remaining_time": "1:39:39"}
|
| 112 |
+
{"current_steps": 112, "total_steps": 522, "loss": 0.55, "lr": 9.614576715410116e-06, "epoch": 0.6424474187380497, "percentage": 21.46, "elapsed_time": "0:27:07", "remaining_time": "1:39:18"}
|
| 113 |
+
{"current_steps": 113, "total_steps": 522, "loss": 0.5111, "lr": 9.60157858924978e-06, "epoch": 0.6481835564053537, "percentage": 21.65, "elapsed_time": "0:27:19", "remaining_time": "1:38:53"}
|
| 114 |
+
{"current_steps": 114, "total_steps": 522, "loss": 0.5248, "lr": 9.588373991985566e-06, "epoch": 0.6539196940726577, "percentage": 21.84, "elapsed_time": "0:27:33", "remaining_time": "1:38:36"}
|
| 115 |
+
{"current_steps": 115, "total_steps": 522, "loss": 0.5409, "lr": 9.574963516102795e-06, "epoch": 0.6596558317399618, "percentage": 22.03, "elapsed_time": "0:27:46", "remaining_time": "1:38:18"}
|
| 116 |
+
{"current_steps": 116, "total_steps": 522, "loss": 0.501, "lr": 9.561347763324484e-06, "epoch": 0.6653919694072657, "percentage": 22.22, "elapsed_time": "0:28:00", "remaining_time": "1:38:03"}
|
| 117 |
+
{"current_steps": 117, "total_steps": 522, "loss": 0.5256, "lr": 9.547527344584353e-06, "epoch": 0.6711281070745698, "percentage": 22.41, "elapsed_time": "0:28:14", "remaining_time": "1:37:45"}
|
| 118 |
+
{"current_steps": 118, "total_steps": 522, "loss": 0.5487, "lr": 9.533502879999398e-06, "epoch": 0.6768642447418738, "percentage": 22.61, "elapsed_time": "0:28:31", "remaining_time": "1:37:40"}
|
| 119 |
+
{"current_steps": 119, "total_steps": 522, "loss": 0.5415, "lr": 9.519274998842084e-06, "epoch": 0.6826003824091779, "percentage": 22.8, "elapsed_time": "0:28:47", "remaining_time": "1:37:31"}
|
| 120 |
+
{"current_steps": 120, "total_steps": 522, "loss": 0.5105, "lr": 9.504844339512096e-06, "epoch": 0.6883365200764818, "percentage": 22.99, "elapsed_time": "0:29:02", "remaining_time": "1:37:16"}
|
| 121 |
+
{"current_steps": 121, "total_steps": 522, "loss": 0.5482, "lr": 9.490211549507701e-06, "epoch": 0.6940726577437859, "percentage": 23.18, "elapsed_time": "0:29:19", "remaining_time": "1:37:09"}
|
| 122 |
+
{"current_steps": 122, "total_steps": 522, "loss": 0.5036, "lr": 9.475377285396692e-06, "epoch": 0.6998087954110899, "percentage": 23.37, "elapsed_time": "0:29:30", "remaining_time": "1:36:46"}
|
| 123 |
+
{"current_steps": 123, "total_steps": 522, "loss": 0.5122, "lr": 9.460342212786933e-06, "epoch": 0.7055449330783938, "percentage": 23.56, "elapsed_time": "0:29:45", "remaining_time": "1:36:30"}
|
| 124 |
+
{"current_steps": 124, "total_steps": 522, "loss": 0.5531, "lr": 9.445107006296488e-06, "epoch": 0.7112810707456979, "percentage": 23.75, "elapsed_time": "0:29:59", "remaining_time": "1:36:15"}
|
| 125 |
+
{"current_steps": 125, "total_steps": 522, "loss": 0.5443, "lr": 9.42967234952335e-06, "epoch": 0.7170172084130019, "percentage": 23.95, "elapsed_time": "0:30:15", "remaining_time": "1:36:04"}
|
| 126 |
+
{"current_steps": 126, "total_steps": 522, "loss": 0.5113, "lr": 9.414038935014777e-06, "epoch": 0.722753346080306, "percentage": 24.14, "elapsed_time": "0:30:31", "remaining_time": "1:35:54"}
|
| 127 |
+
{"current_steps": 127, "total_steps": 522, "loss": 0.5115, "lr": 9.398207464236209e-06, "epoch": 0.7284894837476099, "percentage": 24.33, "elapsed_time": "0:30:48", "remaining_time": "1:35:48"}
|
| 128 |
+
{"current_steps": 128, "total_steps": 522, "loss": 0.5276, "lr": 9.382178647539794e-06, "epoch": 0.734225621414914, "percentage": 24.52, "elapsed_time": "0:31:03", "remaining_time": "1:35:35"}
|
| 129 |
+
{"current_steps": 129, "total_steps": 522, "loss": 0.5337, "lr": 9.365953204132526e-06, "epoch": 0.739961759082218, "percentage": 24.71, "elapsed_time": "0:31:16", "remaining_time": "1:35:17"}
|
| 130 |
+
{"current_steps": 130, "total_steps": 522, "loss": 0.5393, "lr": 9.349531862043952e-06, "epoch": 0.745697896749522, "percentage": 24.9, "elapsed_time": "0:31:29", "remaining_time": "1:34:57"}
|
| 131 |
+
{"current_steps": 131, "total_steps": 522, "loss": 0.504, "lr": 9.332915358093532e-06, "epoch": 0.751434034416826, "percentage": 25.1, "elapsed_time": "0:31:42", "remaining_time": "1:34:39"}
|
| 132 |
+
{"current_steps": 132, "total_steps": 522, "loss": 0.5112, "lr": 9.316104437857561e-06, "epoch": 0.7571701720841301, "percentage": 25.29, "elapsed_time": "0:31:57", "remaining_time": "1:34:26"}
|
| 133 |
+
{"current_steps": 133, "total_steps": 522, "loss": 0.5028, "lr": 9.299099855635716e-06, "epoch": 0.762906309751434, "percentage": 25.48, "elapsed_time": "0:32:09", "remaining_time": "1:34:02"}
|
| 134 |
+
{"current_steps": 134, "total_steps": 522, "loss": 0.5049, "lr": 9.28190237441722e-06, "epoch": 0.768642447418738, "percentage": 25.67, "elapsed_time": "0:32:22", "remaining_time": "1:33:44"}
|
| 135 |
+
{"current_steps": 135, "total_steps": 522, "loss": 0.5021, "lr": 9.2645127658466e-06, "epoch": 0.7743785850860421, "percentage": 25.86, "elapsed_time": "0:32:37", "remaining_time": "1:33:30"}
|
| 136 |
+
{"current_steps": 136, "total_steps": 522, "loss": 0.515, "lr": 9.246931810189061e-06, "epoch": 0.780114722753346, "percentage": 26.05, "elapsed_time": "0:32:54", "remaining_time": "1:33:24"}
|
| 137 |
+
{"current_steps": 137, "total_steps": 522, "loss": 0.5012, "lr": 9.229160296295488e-06, "epoch": 0.7858508604206501, "percentage": 26.25, "elapsed_time": "0:33:09", "remaining_time": "1:33:10"}
|
| 138 |
+
{"current_steps": 138, "total_steps": 522, "loss": 0.5103, "lr": 9.211199021567034e-06, "epoch": 0.7915869980879541, "percentage": 26.44, "elapsed_time": "0:33:24", "remaining_time": "1:32:59"}
|
| 139 |
+
{"current_steps": 139, "total_steps": 522, "loss": 0.5365, "lr": 9.193048791919357e-06, "epoch": 0.7973231357552581, "percentage": 26.63, "elapsed_time": "0:33:37", "remaining_time": "1:32:40"}
|
| 140 |
+
{"current_steps": 140, "total_steps": 522, "loss": 0.5613, "lr": 9.174710421746445e-06, "epoch": 0.8030592734225621, "percentage": 26.82, "elapsed_time": "0:33:53", "remaining_time": "1:32:28"}
|
| 141 |
+
{"current_steps": 141, "total_steps": 522, "loss": 0.5106, "lr": 9.156184733884084e-06, "epoch": 0.8087954110898662, "percentage": 27.01, "elapsed_time": "0:34:07", "remaining_time": "1:32:11"}
|
| 142 |
+
{"current_steps": 142, "total_steps": 522, "loss": 0.5409, "lr": 9.137472559572935e-06, "epoch": 0.8145315487571702, "percentage": 27.2, "elapsed_time": "0:34:24", "remaining_time": "1:32:05"}
|
| 143 |
+
{"current_steps": 143, "total_steps": 522, "loss": 0.5087, "lr": 9.118574738421236e-06, "epoch": 0.8202676864244742, "percentage": 27.39, "elapsed_time": "0:34:40", "remaining_time": "1:31:53"}
|
| 144 |
+
{"current_steps": 144, "total_steps": 522, "loss": 0.5335, "lr": 9.099492118367123e-06, "epoch": 0.8260038240917782, "percentage": 27.59, "elapsed_time": "0:34:53", "remaining_time": "1:31:34"}
|
| 145 |
+
{"current_steps": 145, "total_steps": 522, "loss": 0.5172, "lr": 9.080225555640601e-06, "epoch": 0.8317399617590823, "percentage": 27.78, "elapsed_time": "0:35:09", "remaining_time": "1:31:23"}
|
| 146 |
+
{"current_steps": 146, "total_steps": 522, "loss": 0.524, "lr": 9.0607759147251e-06, "epoch": 0.8374760994263862, "percentage": 27.97, "elapsed_time": "0:35:26", "remaining_time": "1:31:15"}
|
| 147 |
+
{"current_steps": 147, "total_steps": 522, "loss": 0.5082, "lr": 9.04114406831871e-06, "epoch": 0.8432122370936902, "percentage": 28.16, "elapsed_time": "0:35:40", "remaining_time": "1:30:59"}
|
| 148 |
+
{"current_steps": 148, "total_steps": 522, "loss": 0.5111, "lr": 9.021330897295011e-06, "epoch": 0.8489483747609943, "percentage": 28.35, "elapsed_time": "0:35:55", "remaining_time": "1:30:46"}
|
| 149 |
+
{"current_steps": 149, "total_steps": 522, "loss": 0.4957, "lr": 9.001337290663548e-06, "epoch": 0.8546845124282982, "percentage": 28.54, "elapsed_time": "0:36:11", "remaining_time": "1:30:34"}
|
| 150 |
+
{"current_steps": 150, "total_steps": 522, "loss": 0.5162, "lr": 8.981164145529943e-06, "epoch": 0.8604206500956023, "percentage": 28.74, "elapsed_time": "0:36:22", "remaining_time": "1:30:13"}
|
| 151 |
+
{"current_steps": 151, "total_steps": 522, "loss": 0.5277, "lr": 8.960812367055646e-06, "epoch": 0.8661567877629063, "percentage": 28.93, "elapsed_time": "0:36:38", "remaining_time": "1:30:01"}
|
| 152 |
+
{"current_steps": 152, "total_steps": 522, "loss": 0.4739, "lr": 8.940282868417321e-06, "epoch": 0.8718929254302104, "percentage": 29.12, "elapsed_time": "0:36:52", "remaining_time": "1:29:46"}
|
| 153 |
+
{"current_steps": 153, "total_steps": 522, "loss": 0.5318, "lr": 8.91957657076586e-06, "epoch": 0.8776290630975143, "percentage": 29.31, "elapsed_time": "0:37:06", "remaining_time": "1:29:29"}
|
| 154 |
+
{"current_steps": 154, "total_steps": 522, "loss": 0.4987, "lr": 8.898694403185066e-06, "epoch": 0.8833652007648184, "percentage": 29.5, "elapsed_time": "0:37:21", "remaining_time": "1:29:15"}
|
| 155 |
+
{"current_steps": 155, "total_steps": 522, "loss": 0.5174, "lr": 8.877637302649962e-06, "epoch": 0.8891013384321224, "percentage": 29.69, "elapsed_time": "0:37:36", "remaining_time": "1:29:03"}
|
| 156 |
+
{"current_steps": 156, "total_steps": 522, "loss": 0.5236, "lr": 8.856406213984743e-06, "epoch": 0.8948374760994264, "percentage": 29.89, "elapsed_time": "0:37:50", "remaining_time": "1:28:46"}
|
| 157 |
+
{"current_steps": 157, "total_steps": 522, "loss": 0.5021, "lr": 8.835002089820387e-06, "epoch": 0.9005736137667304, "percentage": 30.08, "elapsed_time": "0:38:03", "remaining_time": "1:28:29"}
|
| 158 |
+
{"current_steps": 158, "total_steps": 522, "loss": 0.5354, "lr": 8.81342589055191e-06, "epoch": 0.9063097514340345, "percentage": 30.27, "elapsed_time": "0:38:19", "remaining_time": "1:28:18"}
|
| 159 |
+
{"current_steps": 159, "total_steps": 522, "loss": 0.5014, "lr": 8.791678584295276e-06, "epoch": 0.9120458891013384, "percentage": 30.46, "elapsed_time": "0:38:33", "remaining_time": "1:28:02"}
|
| 160 |
+
{"current_steps": 160, "total_steps": 522, "loss": 0.509, "lr": 8.76976114684395e-06, "epoch": 0.9177820267686424, "percentage": 30.65, "elapsed_time": "0:38:46", "remaining_time": "1:27:42"}
|
| 161 |
+
{"current_steps": 161, "total_steps": 522, "loss": 0.5261, "lr": 8.747674561625121e-06, "epoch": 0.9235181644359465, "percentage": 30.84, "elapsed_time": "0:38:59", "remaining_time": "1:27:26"}
|
| 162 |
+
{"current_steps": 162, "total_steps": 522, "loss": 0.4732, "lr": 8.725419819655582e-06, "epoch": 0.9292543021032504, "percentage": 31.03, "elapsed_time": "0:39:11", "remaining_time": "1:27:05"}
|
| 163 |
+
{"current_steps": 163, "total_steps": 522, "loss": 0.5246, "lr": 8.702997919497247e-06, "epoch": 0.9349904397705545, "percentage": 31.23, "elapsed_time": "0:39:26", "remaining_time": "1:26:51"}
|
| 164 |
+
{"current_steps": 164, "total_steps": 522, "loss": 0.5243, "lr": 8.680409867212359e-06, "epoch": 0.9407265774378585, "percentage": 31.42, "elapsed_time": "0:39:40", "remaining_time": "1:26:36"}
|
| 165 |
+
{"current_steps": 165, "total_steps": 522, "loss": 0.5284, "lr": 8.657656676318346e-06, "epoch": 0.9464627151051626, "percentage": 31.61, "elapsed_time": "0:39:54", "remaining_time": "1:26:20"}
|
| 166 |
+
{"current_steps": 166, "total_steps": 522, "loss": 0.4909, "lr": 8.634739367742341e-06, "epoch": 0.9521988527724665, "percentage": 31.8, "elapsed_time": "0:40:09", "remaining_time": "1:26:06"}
|
| 167 |
+
{"current_steps": 167, "total_steps": 522, "loss": 0.4942, "lr": 8.611658969775378e-06, "epoch": 0.9579349904397706, "percentage": 31.99, "elapsed_time": "0:40:21", "remaining_time": "1:25:48"}
|
| 168 |
+
{"current_steps": 168, "total_steps": 522, "loss": 0.489, "lr": 8.588416518026248e-06, "epoch": 0.9636711281070746, "percentage": 32.18, "elapsed_time": "0:40:37", "remaining_time": "1:25:35"}
|
| 169 |
+
{"current_steps": 169, "total_steps": 522, "loss": 0.5132, "lr": 8.565013055375035e-06, "epoch": 0.9694072657743786, "percentage": 32.38, "elapsed_time": "0:40:49", "remaining_time": "1:25:17"}
|
| 170 |
+
{"current_steps": 170, "total_steps": 522, "loss": 0.5051, "lr": 8.541449631926325e-06, "epoch": 0.9751434034416826, "percentage": 32.57, "elapsed_time": "0:41:06", "remaining_time": "1:25:06"}
|
| 171 |
+
{"current_steps": 171, "total_steps": 522, "loss": 0.5501, "lr": 8.51772730496208e-06, "epoch": 0.9808795411089866, "percentage": 32.76, "elapsed_time": "0:41:22", "remaining_time": "1:24:55"}
|
| 172 |
+
{"current_steps": 172, "total_steps": 522, "loss": 0.5028, "lr": 8.49384713889421e-06, "epoch": 0.9866156787762906, "percentage": 32.95, "elapsed_time": "0:41:34", "remaining_time": "1:24:36"}
|
| 173 |
+
{"current_steps": 173, "total_steps": 522, "loss": 0.5344, "lr": 8.469810205216795e-06, "epoch": 0.9923518164435946, "percentage": 33.14, "elapsed_time": "0:41:49", "remaining_time": "1:24:22"}
|
| 174 |
+
{"current_steps": 174, "total_steps": 522, "loss": 0.5249, "lr": 8.445617582458033e-06, "epoch": 0.9980879541108987, "percentage": 33.33, "elapsed_time": "0:42:05", "remaining_time": "1:24:11"}
|
| 175 |
+
{"current_steps": 175, "total_steps": 522, "loss": 0.7484, "lr": 8.42127035613182e-06, "epoch": 1.0038240917782026, "percentage": 33.52, "elapsed_time": "0:43:42", "remaining_time": "1:26:40"}
|
| 176 |
+
{"current_steps": 176, "total_steps": 522, "loss": 0.4684, "lr": 8.396769618689064e-06, "epoch": 1.0095602294455066, "percentage": 33.72, "elapsed_time": "0:43:58", "remaining_time": "1:26:26"}
|
| 177 |
+
{"current_steps": 177, "total_steps": 522, "loss": 0.5179, "lr": 8.372116469468654e-06, "epoch": 1.0152963671128108, "percentage": 33.91, "elapsed_time": "0:44:15", "remaining_time": "1:26:15"}
|
| 178 |
+
{"current_steps": 178, "total_steps": 522, "loss": 0.4496, "lr": 8.347312014648144e-06, "epoch": 1.0210325047801148, "percentage": 34.1, "elapsed_time": "0:44:28", "remaining_time": "1:25:56"}
|
| 179 |
+
{"current_steps": 179, "total_steps": 522, "loss": 0.4475, "lr": 8.32235736719411e-06, "epoch": 1.0267686424474187, "percentage": 34.29, "elapsed_time": "0:44:42", "remaining_time": "1:25:39"}
|
| 180 |
+
{"current_steps": 180, "total_steps": 522, "loss": 0.4795, "lr": 8.297253646812213e-06, "epoch": 1.0325047801147227, "percentage": 34.48, "elapsed_time": "0:44:56", "remaining_time": "1:25:22"}
|
| 181 |
+
{"current_steps": 181, "total_steps": 522, "loss": 0.3987, "lr": 8.272001979896962e-06, "epoch": 1.0382409177820269, "percentage": 34.67, "elapsed_time": "0:45:11", "remaining_time": "1:25:08"}
|
| 182 |
+
{"current_steps": 182, "total_steps": 522, "loss": 0.4851, "lr": 8.246603499481177e-06, "epoch": 1.0439770554493308, "percentage": 34.87, "elapsed_time": "0:45:25", "remaining_time": "1:24:51"}
|
| 183 |
+
{"current_steps": 183, "total_steps": 522, "loss": 0.4891, "lr": 8.221059345185136e-06, "epoch": 1.0497131931166348, "percentage": 35.06, "elapsed_time": "0:45:38", "remaining_time": "1:24:33"}
|
| 184 |
+
{"current_steps": 184, "total_steps": 522, "loss": 0.4717, "lr": 8.195370663165455e-06, "epoch": 1.0554493307839388, "percentage": 35.25, "elapsed_time": "0:45:54", "remaining_time": "1:24:19"}
|
| 185 |
+
{"current_steps": 185, "total_steps": 522, "loss": 0.4284, "lr": 8.169538606063647e-06, "epoch": 1.0611854684512427, "percentage": 35.44, "elapsed_time": "0:46:07", "remaining_time": "1:24:01"}
|
| 186 |
+
{"current_steps": 186, "total_steps": 522, "loss": 0.5056, "lr": 8.143564332954426e-06, "epoch": 1.066921606118547, "percentage": 35.63, "elapsed_time": "0:46:19", "remaining_time": "1:23:40"}
|
| 187 |
+
{"current_steps": 187, "total_steps": 522, "loss": 0.4761, "lr": 8.117449009293668e-06, "epoch": 1.0726577437858509, "percentage": 35.82, "elapsed_time": "0:46:35", "remaining_time": "1:23:28"}
|
| 188 |
+
{"current_steps": 188, "total_steps": 522, "loss": 0.5182, "lr": 8.091193806866147e-06, "epoch": 1.0783938814531548, "percentage": 36.02, "elapsed_time": "0:46:52", "remaining_time": "1:23:17"}
|
| 189 |
+
{"current_steps": 189, "total_steps": 522, "loss": 0.3982, "lr": 8.064799903732936e-06, "epoch": 1.0841300191204588, "percentage": 36.21, "elapsed_time": "0:47:07", "remaining_time": "1:23:02"}
|
| 190 |
+
{"current_steps": 190, "total_steps": 522, "loss": 0.5303, "lr": 8.038268484178566e-06, "epoch": 1.089866156787763, "percentage": 36.4, "elapsed_time": "0:47:26", "remaining_time": "1:22:53"}
|
| 191 |
+
{"current_steps": 191, "total_steps": 522, "loss": 0.4372, "lr": 8.011600738657865e-06, "epoch": 1.095602294455067, "percentage": 36.59, "elapsed_time": "0:47:39", "remaining_time": "1:22:35"}
|
| 192 |
+
{"current_steps": 192, "total_steps": 522, "loss": 0.4337, "lr": 7.98479786374257e-06, "epoch": 1.101338432122371, "percentage": 36.78, "elapsed_time": "0:47:53", "remaining_time": "1:22:18"}
|
| 193 |
+
{"current_steps": 193, "total_steps": 522, "loss": 0.4685, "lr": 7.957861062067614e-06, "epoch": 1.107074569789675, "percentage": 36.97, "elapsed_time": "0:48:05", "remaining_time": "1:21:59"}
|
| 194 |
+
{"current_steps": 194, "total_steps": 522, "loss": 0.4743, "lr": 7.930791542277175e-06, "epoch": 1.1128107074569789, "percentage": 37.16, "elapsed_time": "0:48:20", "remaining_time": "1:21:43"}
|
| 195 |
+
{"current_steps": 195, "total_steps": 522, "loss": 0.4595, "lr": 7.903590518970445e-06, "epoch": 1.118546845124283, "percentage": 37.36, "elapsed_time": "0:48:33", "remaining_time": "1:21:25"}
|
| 196 |
+
{"current_steps": 196, "total_steps": 522, "loss": 0.4061, "lr": 7.876259212647129e-06, "epoch": 1.124282982791587, "percentage": 37.55, "elapsed_time": "0:48:44", "remaining_time": "1:21:04"}
|
| 197 |
+
{"current_steps": 197, "total_steps": 522, "loss": 0.5362, "lr": 7.848798849652684e-06, "epoch": 1.130019120458891, "percentage": 37.74, "elapsed_time": "0:49:01", "remaining_time": "1:20:51"}
|
| 198 |
+
{"current_steps": 198, "total_steps": 522, "loss": 0.47, "lr": 7.821210662123284e-06, "epoch": 1.135755258126195, "percentage": 37.93, "elapsed_time": "0:49:16", "remaining_time": "1:20:37"}
|
| 199 |
+
{"current_steps": 199, "total_steps": 522, "loss": 0.4206, "lr": 7.793495887930551e-06, "epoch": 1.1414913957934991, "percentage": 38.12, "elapsed_time": "0:49:26", "remaining_time": "1:20:15"}
|
| 200 |
+
{"current_steps": 200, "total_steps": 522, "loss": 0.4387, "lr": 7.765655770625997e-06, "epoch": 1.147227533460803, "percentage": 38.31, "elapsed_time": "0:49:37", "remaining_time": "1:19:54"}
|
| 201 |
+
{"current_steps": 201, "total_steps": 522, "loss": 0.4437, "lr": 7.737691559385237e-06, "epoch": 1.152963671128107, "percentage": 38.51, "elapsed_time": "0:49:53", "remaining_time": "1:19:41"}
|
| 202 |
+
{"current_steps": 202, "total_steps": 522, "loss": 0.5166, "lr": 7.709604508951927e-06, "epoch": 1.158699808795411, "percentage": 38.7, "elapsed_time": "0:50:05", "remaining_time": "1:19:21"}
|
| 203 |
+
{"current_steps": 203, "total_steps": 522, "loss": 0.4315, "lr": 7.68139587958148e-06, "epoch": 1.1644359464627152, "percentage": 38.89, "elapsed_time": "0:50:19", "remaining_time": "1:19:04"}
|
| 204 |
+
{"current_steps": 204, "total_steps": 522, "loss": 0.5259, "lr": 7.653066936984504e-06, "epoch": 1.1701720841300192, "percentage": 39.08, "elapsed_time": "0:50:34", "remaining_time": "1:18:50"}
|
| 205 |
+
{"current_steps": 205, "total_steps": 522, "loss": 0.4733, "lr": 7.6246189522700205e-06, "epoch": 1.1759082217973231, "percentage": 39.27, "elapsed_time": "0:50:48", "remaining_time": "1:18:34"}
|
| 206 |
+
{"current_steps": 206, "total_steps": 522, "loss": 0.4522, "lr": 7.596053201888425e-06, "epoch": 1.181644359464627, "percentage": 39.46, "elapsed_time": "0:51:02", "remaining_time": "1:18:18"}
|
| 207 |
+
{"current_steps": 207, "total_steps": 522, "loss": 0.4569, "lr": 7.56737096757421e-06, "epoch": 1.1873804971319313, "percentage": 39.66, "elapsed_time": "0:51:15", "remaining_time": "1:17:59"}
|
| 208 |
+
{"current_steps": 208, "total_steps": 522, "loss": 0.4537, "lr": 7.538573536288466e-06, "epoch": 1.1931166347992352, "percentage": 39.85, "elapsed_time": "0:51:30", "remaining_time": "1:17:45"}
|
| 209 |
+
{"current_steps": 209, "total_steps": 522, "loss": 0.4652, "lr": 7.509662200161122e-06, "epoch": 1.1988527724665392, "percentage": 40.04, "elapsed_time": "0:51:44", "remaining_time": "1:17:29"}
|
| 210 |
+
{"current_steps": 210, "total_steps": 522, "loss": 0.4539, "lr": 7.480638256432977e-06, "epoch": 1.2045889101338432, "percentage": 40.23, "elapsed_time": "0:52:00", "remaining_time": "1:17:16"}
|
| 211 |
+
{"current_steps": 211, "total_steps": 522, "loss": 0.4799, "lr": 7.4515030073974915e-06, "epoch": 1.2103250478011471, "percentage": 40.42, "elapsed_time": "0:52:15", "remaining_time": "1:17:01"}
|
| 212 |
+
{"current_steps": 212, "total_steps": 522, "loss": 0.4727, "lr": 7.422257760342351e-06, "epoch": 1.2160611854684513, "percentage": 40.61, "elapsed_time": "0:52:29", "remaining_time": "1:16:44"}
|
| 213 |
+
{"current_steps": 213, "total_steps": 522, "loss": 0.4369, "lr": 7.392903827490814e-06, "epoch": 1.2217973231357553, "percentage": 40.8, "elapsed_time": "0:52:39", "remaining_time": "1:16:23"}
|
| 214 |
+
{"current_steps": 214, "total_steps": 522, "loss": 0.4383, "lr": 7.363442525942827e-06, "epoch": 1.2275334608030593, "percentage": 41.0, "elapsed_time": "0:52:51", "remaining_time": "1:16:04"}
|
| 215 |
+
{"current_steps": 215, "total_steps": 522, "loss": 0.4882, "lr": 7.333875177615931e-06, "epoch": 1.2332695984703632, "percentage": 41.19, "elapsed_time": "0:53:06", "remaining_time": "1:15:49"}
|
| 216 |
+
{"current_steps": 216, "total_steps": 522, "loss": 0.4802, "lr": 7.304203109185947e-06, "epoch": 1.2390057361376674, "percentage": 41.38, "elapsed_time": "0:53:19", "remaining_time": "1:15:33"}
|
| 217 |
+
{"current_steps": 217, "total_steps": 522, "loss": 0.4137, "lr": 7.274427652027444e-06, "epoch": 1.2447418738049714, "percentage": 41.57, "elapsed_time": "0:53:34", "remaining_time": "1:15:18"}
|
| 218 |
+
{"current_steps": 218, "total_steps": 522, "loss": 0.4254, "lr": 7.244550142154009e-06, "epoch": 1.2504780114722753, "percentage": 41.76, "elapsed_time": "0:53:44", "remaining_time": "1:14:57"}
|
| 219 |
+
{"current_steps": 219, "total_steps": 522, "loss": 0.4954, "lr": 7.214571920158293e-06, "epoch": 1.2562141491395793, "percentage": 41.95, "elapsed_time": "0:53:57", "remaining_time": "1:14:39"}
|
| 220 |
+
{"current_steps": 220, "total_steps": 522, "loss": 0.4796, "lr": 7.1844943311518665e-06, "epoch": 1.2619502868068833, "percentage": 42.15, "elapsed_time": "0:54:13", "remaining_time": "1:14:26"}
|
| 221 |
+
{"current_steps": 221, "total_steps": 522, "loss": 0.471, "lr": 7.1543187247048525e-06, "epoch": 1.2676864244741874, "percentage": 42.34, "elapsed_time": "0:54:28", "remaining_time": "1:14:11"}
|
| 222 |
+
{"current_steps": 222, "total_steps": 522, "loss": 0.4857, "lr": 7.124046454785387e-06, "epoch": 1.2734225621414914, "percentage": 42.53, "elapsed_time": "0:54:44", "remaining_time": "1:13:58"}
|
| 223 |
+
{"current_steps": 223, "total_steps": 522, "loss": 0.5037, "lr": 7.093678879698858e-06, "epoch": 1.2791586998087954, "percentage": 42.72, "elapsed_time": "0:54:58", "remaining_time": "1:13:42"}
|
| 224 |
+
{"current_steps": 224, "total_steps": 522, "loss": 0.4692, "lr": 7.063217362026957e-06, "epoch": 1.2848948374760996, "percentage": 42.91, "elapsed_time": "0:55:12", "remaining_time": "1:13:26"}
|
| 225 |
+
{"current_steps": 225, "total_steps": 522, "loss": 0.4413, "lr": 7.032663268566547e-06, "epoch": 1.2906309751434035, "percentage": 43.1, "elapsed_time": "0:55:25", "remaining_time": "1:13:09"}
|
| 226 |
+
{"current_steps": 226, "total_steps": 522, "loss": 0.4544, "lr": 7.002017970268336e-06, "epoch": 1.2963671128107075, "percentage": 43.3, "elapsed_time": "0:55:38", "remaining_time": "1:12:51"}
|
| 227 |
+
{"current_steps": 227, "total_steps": 522, "loss": 0.4663, "lr": 6.97128284217535e-06, "epoch": 1.3021032504780115, "percentage": 43.49, "elapsed_time": "0:55:50", "remaining_time": "1:12:33"}
|
| 228 |
+
{"current_steps": 228, "total_steps": 522, "loss": 0.4933, "lr": 6.9404592633612486e-06, "epoch": 1.3078393881453154, "percentage": 43.68, "elapsed_time": "0:56:07", "remaining_time": "1:12:22"}
|
| 229 |
+
{"current_steps": 229, "total_steps": 522, "loss": 0.52, "lr": 6.909548616868444e-06, "epoch": 1.3135755258126194, "percentage": 43.87, "elapsed_time": "0:56:23", "remaining_time": "1:12:08"}
|
| 230 |
+
{"current_steps": 230, "total_steps": 522, "loss": 0.4325, "lr": 6.878552289646041e-06, "epoch": 1.3193116634799236, "percentage": 44.06, "elapsed_time": "0:56:36", "remaining_time": "1:11:52"}
|
| 231 |
+
{"current_steps": 231, "total_steps": 522, "loss": 0.4163, "lr": 6.847471672487607e-06, "epoch": 1.3250478011472275, "percentage": 44.25, "elapsed_time": "0:56:51", "remaining_time": "1:11:37"}
|
| 232 |
+
{"current_steps": 232, "total_steps": 522, "loss": 0.4871, "lr": 6.816308159968761e-06, "epoch": 1.3307839388145315, "percentage": 44.44, "elapsed_time": "0:57:08", "remaining_time": "1:11:25"}
|
| 233 |
+
{"current_steps": 233, "total_steps": 522, "loss": 0.486, "lr": 6.7850631503846165e-06, "epoch": 1.3365200764818357, "percentage": 44.64, "elapsed_time": "0:57:23", "remaining_time": "1:11:11"}
|
| 234 |
+
{"current_steps": 234, "total_steps": 522, "loss": 0.4844, "lr": 6.753738045687021e-06, "epoch": 1.3422562141491396, "percentage": 44.83, "elapsed_time": "0:57:41", "remaining_time": "1:10:59"}
|
| 235 |
+
{"current_steps": 235, "total_steps": 522, "loss": 0.4609, "lr": 6.722334251421665e-06, "epoch": 1.3479923518164436, "percentage": 45.02, "elapsed_time": "0:57:57", "remaining_time": "1:10:47"}
|
| 236 |
+
{"current_steps": 236, "total_steps": 522, "loss": 0.5086, "lr": 6.690853176665007e-06, "epoch": 1.3537284894837476, "percentage": 45.21, "elapsed_time": "0:58:14", "remaining_time": "1:10:34"}
|
| 237 |
+
{"current_steps": 237, "total_steps": 522, "loss": 0.3915, "lr": 6.659296233961055e-06, "epoch": 1.3594646271510515, "percentage": 45.4, "elapsed_time": "0:58:28", "remaining_time": "1:10:19"}
|
| 238 |
+
{"current_steps": 238, "total_steps": 522, "loss": 0.4861, "lr": 6.627664839257979e-06, "epoch": 1.3652007648183555, "percentage": 45.59, "elapsed_time": "0:58:44", "remaining_time": "1:10:06"}
|
| 239 |
+
{"current_steps": 239, "total_steps": 522, "loss": 0.4326, "lr": 6.595960411844589e-06, "epoch": 1.3709369024856597, "percentage": 45.79, "elapsed_time": "0:59:00", "remaining_time": "1:09:51"}
|
| 240 |
+
{"current_steps": 240, "total_steps": 522, "loss": 0.5214, "lr": 6.564184374286636e-06, "epoch": 1.3766730401529637, "percentage": 45.98, "elapsed_time": "0:59:13", "remaining_time": "1:09:35"}
|
| 241 |
+
{"current_steps": 241, "total_steps": 522, "loss": 0.4665, "lr": 6.532338152363001e-06, "epoch": 1.3824091778202676, "percentage": 46.17, "elapsed_time": "0:59:28", "remaining_time": "1:09:21"}
|
| 242 |
+
{"current_steps": 242, "total_steps": 522, "loss": 0.4313, "lr": 6.500423175001705e-06, "epoch": 1.3881453154875718, "percentage": 46.36, "elapsed_time": "0:59:43", "remaining_time": "1:09:06"}
|
| 243 |
+
{"current_steps": 243, "total_steps": 522, "loss": 0.4403, "lr": 6.468440874215801e-06, "epoch": 1.3938814531548758, "percentage": 46.55, "elapsed_time": "0:59:56", "remaining_time": "1:08:49"}
|
| 244 |
+
{"current_steps": 244, "total_steps": 522, "loss": 0.5141, "lr": 6.43639268503912e-06, "epoch": 1.3996175908221797, "percentage": 46.74, "elapsed_time": "1:00:12", "remaining_time": "1:08:36"}
|
| 245 |
+
{"current_steps": 245, "total_steps": 522, "loss": 0.4892, "lr": 6.40428004546188e-06, "epoch": 1.4053537284894837, "percentage": 46.93, "elapsed_time": "1:00:25", "remaining_time": "1:08:19"}
|
| 246 |
+
{"current_steps": 246, "total_steps": 522, "loss": 0.4652, "lr": 6.372104396366162e-06, "epoch": 1.4110898661567877, "percentage": 47.13, "elapsed_time": "1:00:41", "remaining_time": "1:08:06"}
|
| 247 |
+
{"current_steps": 247, "total_steps": 522, "loss": 0.4802, "lr": 6.339867181461265e-06, "epoch": 1.4168260038240919, "percentage": 47.32, "elapsed_time": "1:00:58", "remaining_time": "1:07:53"}
|
| 248 |
+
{"current_steps": 248, "total_steps": 522, "loss": 0.4388, "lr": 6.307569847218917e-06, "epoch": 1.4225621414913958, "percentage": 47.51, "elapsed_time": "1:01:15", "remaining_time": "1:07:40"}
|
| 249 |
+
{"current_steps": 249, "total_steps": 522, "loss": 0.4825, "lr": 6.275213842808383e-06, "epoch": 1.4282982791586998, "percentage": 47.7, "elapsed_time": "1:01:29", "remaining_time": "1:07:25"}
|
| 250 |
+
{"current_steps": 250, "total_steps": 522, "loss": 0.4412, "lr": 6.242800620031434e-06, "epoch": 1.4340344168260037, "percentage": 47.89, "elapsed_time": "1:01:47", "remaining_time": "1:07:13"}
|
| 251 |
+
{"current_steps": 251, "total_steps": 522, "loss": 0.4808, "lr": 6.2103316332572095e-06, "epoch": 1.439770554493308, "percentage": 48.08, "elapsed_time": "1:02:03", "remaining_time": "1:07:00"}
|
| 252 |
+
{"current_steps": 252, "total_steps": 522, "loss": 0.4844, "lr": 6.177808339356954e-06, "epoch": 1.445506692160612, "percentage": 48.28, "elapsed_time": "1:02:19", "remaining_time": "1:06:46"}
|
| 253 |
+
{"current_steps": 253, "total_steps": 522, "loss": 0.4195, "lr": 6.14523219763866e-06, "epoch": 1.4512428298279159, "percentage": 48.47, "elapsed_time": "1:02:32", "remaining_time": "1:06:29"}
|
| 254 |
+
{"current_steps": 254, "total_steps": 522, "loss": 0.4678, "lr": 6.112604669781572e-06, "epoch": 1.4569789674952198, "percentage": 48.66, "elapsed_time": "1:02:46", "remaining_time": "1:06:13"}
|
| 255 |
+
{"current_steps": 255, "total_steps": 522, "loss": 0.4829, "lr": 6.079927219770623e-06, "epoch": 1.4627151051625238, "percentage": 48.85, "elapsed_time": "1:03:01", "remaining_time": "1:05:59"}
|
| 256 |
+
{"current_steps": 256, "total_steps": 522, "loss": 0.4695, "lr": 6.047201313830724e-06, "epoch": 1.468451242829828, "percentage": 49.04, "elapsed_time": "1:03:17", "remaining_time": "1:05:46"}
|
| 257 |
+
{"current_steps": 257, "total_steps": 522, "loss": 0.4975, "lr": 6.014428420360987e-06, "epoch": 1.474187380497132, "percentage": 49.23, "elapsed_time": "1:03:33", "remaining_time": "1:05:32"}
|
| 258 |
+
{"current_steps": 258, "total_steps": 522, "loss": 0.4501, "lr": 5.9816100098688456e-06, "epoch": 1.479923518164436, "percentage": 49.43, "elapsed_time": "1:03:48", "remaining_time": "1:05:17"}
|
| 259 |
+
{"current_steps": 259, "total_steps": 522, "loss": 0.4811, "lr": 5.948747554904054e-06, "epoch": 1.48565965583174, "percentage": 49.62, "elapsed_time": "1:04:03", "remaining_time": "1:05:03"}
|
| 260 |
+
{"current_steps": 260, "total_steps": 522, "loss": 0.4829, "lr": 5.915842529992632e-06, "epoch": 1.491395793499044, "percentage": 49.81, "elapsed_time": "1:04:17", "remaining_time": "1:04:46"}
|
| 261 |
+
{"current_steps": 261, "total_steps": 522, "loss": 0.4382, "lr": 5.8828964115706925e-06, "epoch": 1.497131931166348, "percentage": 50.0, "elapsed_time": "1:04:27", "remaining_time": "1:04:27"}
|
| 262 |
+
{"current_steps": 262, "total_steps": 522, "loss": 0.4417, "lr": 5.849910677918205e-06, "epoch": 1.502868068833652, "percentage": 50.19, "elapsed_time": "1:04:39", "remaining_time": "1:04:09"}
|
| 263 |
+
{"current_steps": 263, "total_steps": 522, "loss": 0.47, "lr": 5.816886809092651e-06, "epoch": 1.508604206500956, "percentage": 50.38, "elapsed_time": "1:04:52", "remaining_time": "1:03:53"}
|
| 264 |
+
{"current_steps": 264, "total_steps": 522, "loss": 0.479, "lr": 5.783826286862631e-06, "epoch": 1.51434034416826, "percentage": 50.57, "elapsed_time": "1:05:08", "remaining_time": "1:03:39"}
|
| 265 |
+
{"current_steps": 265, "total_steps": 522, "loss": 0.4284, "lr": 5.750730594641367e-06, "epoch": 1.520076481835564, "percentage": 50.77, "elapsed_time": "1:05:22", "remaining_time": "1:03:24"}
|
| 266 |
+
{"current_steps": 266, "total_steps": 522, "loss": 0.4533, "lr": 5.717601217420143e-06, "epoch": 1.525812619502868, "percentage": 50.96, "elapsed_time": "1:05:36", "remaining_time": "1:03:08"}
|
| 267 |
+
{"current_steps": 267, "total_steps": 522, "loss": 0.4587, "lr": 5.68443964170168e-06, "epoch": 1.5315487571701722, "percentage": 51.15, "elapsed_time": "1:05:52", "remaining_time": "1:02:54"}
|
| 268 |
+
{"current_steps": 268, "total_steps": 522, "loss": 0.4441, "lr": 5.6512473554334294e-06, "epoch": 1.5372848948374762, "percentage": 51.34, "elapsed_time": "1:06:06", "remaining_time": "1:02:39"}
|
| 269 |
+
{"current_steps": 269, "total_steps": 522, "loss": 0.5072, "lr": 5.618025847940817e-06, "epoch": 1.5430210325047802, "percentage": 51.53, "elapsed_time": "1:06:23", "remaining_time": "1:02:26"}
|
| 270 |
+
{"current_steps": 270, "total_steps": 522, "loss": 0.492, "lr": 5.584776609860414e-06, "epoch": 1.5487571701720841, "percentage": 51.72, "elapsed_time": "1:06:35", "remaining_time": "1:02:09"}
|
| 271 |
+
{"current_steps": 271, "total_steps": 522, "loss": 0.4789, "lr": 5.551501133073048e-06, "epoch": 1.554493307839388, "percentage": 51.92, "elapsed_time": "1:06:50", "remaining_time": "1:01:54"}
|
| 272 |
+
{"current_steps": 272, "total_steps": 522, "loss": 0.4564, "lr": 5.518200910636875e-06, "epoch": 1.560229445506692, "percentage": 52.11, "elapsed_time": "1:07:06", "remaining_time": "1:01:40"}
|
| 273 |
+
{"current_steps": 273, "total_steps": 522, "loss": 0.4769, "lr": 5.4848774367203715e-06, "epoch": 1.565965583173996, "percentage": 52.3, "elapsed_time": "1:07:21", "remaining_time": "1:01:26"}
|
| 274 |
+
{"current_steps": 274, "total_steps": 522, "loss": 0.5163, "lr": 5.451532206535306e-06, "epoch": 1.5717017208413002, "percentage": 52.49, "elapsed_time": "1:07:35", "remaining_time": "1:01:11"}
|
| 275 |
+
{"current_steps": 275, "total_steps": 522, "loss": 0.4344, "lr": 5.418166716269636e-06, "epoch": 1.5774378585086042, "percentage": 52.68, "elapsed_time": "1:07:49", "remaining_time": "1:00:55"}
|
| 276 |
+
{"current_steps": 276, "total_steps": 522, "loss": 0.4864, "lr": 5.384782463020385e-06, "epoch": 1.5831739961759084, "percentage": 52.87, "elapsed_time": "1:08:07", "remaining_time": "1:00:43"}
|
| 277 |
+
{"current_steps": 277, "total_steps": 522, "loss": 0.4715, "lr": 5.351380944726465e-06, "epoch": 1.5889101338432123, "percentage": 53.07, "elapsed_time": "1:08:23", "remaining_time": "1:00:29"}
|
| 278 |
+
{"current_steps": 278, "total_steps": 522, "loss": 0.4559, "lr": 5.317963660101464e-06, "epoch": 1.5946462715105163, "percentage": 53.26, "elapsed_time": "1:08:37", "remaining_time": "1:00:14"}
|
| 279 |
+
{"current_steps": 279, "total_steps": 522, "loss": 0.4249, "lr": 5.284532108566396e-06, "epoch": 1.6003824091778203, "percentage": 53.45, "elapsed_time": "1:08:52", "remaining_time": "0:59:59"}
|
| 280 |
+
{"current_steps": 280, "total_steps": 522, "loss": 0.4934, "lr": 5.251087790182428e-06, "epoch": 1.6061185468451242, "percentage": 53.64, "elapsed_time": "1:09:07", "remaining_time": "0:59:45"}
|
| 281 |
+
{"current_steps": 281, "total_steps": 522, "loss": 0.4493, "lr": 5.217632205583574e-06, "epoch": 1.6118546845124282, "percentage": 53.83, "elapsed_time": "1:09:21", "remaining_time": "0:59:28"}
|
| 282 |
+
{"current_steps": 282, "total_steps": 522, "loss": 0.5144, "lr": 5.184166855909355e-06, "epoch": 1.6175908221797322, "percentage": 54.02, "elapsed_time": "1:09:35", "remaining_time": "0:59:13"}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:accad4e208d07eebed76e4d21088deb153c9566559b9e9db2e0162971b2f2cc1
|
| 3 |
+
size 7224
|