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 +252 -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 sha256:72807accc4cd0080664bc22824a2462d0767a5db275f25e4859be6d58a9fc2f0
|
| 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 +1,252 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 1, "total_steps": 2320, "loss": 2.3852, "lr": 0.0, "epoch": 0.004299226139294927, "percentage": 0.04, "elapsed_time": "0:00:29", "remaining_time": "18:43:06"}
|
| 2 |
+
{"current_steps": 2, "total_steps": 2320, "loss": 2.3566, "lr": 2e-08, "epoch": 0.008598452278589854, "percentage": 0.09, "elapsed_time": "0:00:46", "remaining_time": "15:01:04"}
|
| 3 |
+
{"current_steps": 3, "total_steps": 2320, "loss": 2.3729, "lr": 4e-08, "epoch": 0.012897678417884782, "percentage": 0.13, "elapsed_time": "0:01:04", "remaining_time": "13:49:55"}
|
| 4 |
+
{"current_steps": 4, "total_steps": 2320, "loss": 2.3796, "lr": 6e-08, "epoch": 0.017196904557179708, "percentage": 0.17, "elapsed_time": "0:01:22", "remaining_time": "13:13:36"}
|
| 5 |
+
{"current_steps": 5, "total_steps": 2320, "loss": 2.3903, "lr": 8e-08, "epoch": 0.021496130696474634, "percentage": 0.22, "elapsed_time": "0:01:39", "remaining_time": "12:51:24"}
|
| 6 |
+
{"current_steps": 6, "total_steps": 2320, "loss": 2.4095, "lr": 1e-07, "epoch": 0.025795356835769563, "percentage": 0.26, "elapsed_time": "0:01:57", "remaining_time": "12:36:40"}
|
| 7 |
+
{"current_steps": 7, "total_steps": 2320, "loss": 2.3907, "lr": 1.2e-07, "epoch": 0.03009458297506449, "percentage": 0.3, "elapsed_time": "0:02:15", "remaining_time": "12:26:04"}
|
| 8 |
+
{"current_steps": 8, "total_steps": 2320, "loss": 2.3775, "lr": 1.4e-07, "epoch": 0.034393809114359415, "percentage": 0.34, "elapsed_time": "0:02:33", "remaining_time": "12:18:07"}
|
| 9 |
+
{"current_steps": 9, "total_steps": 2320, "loss": 2.3562, "lr": 1.6e-07, "epoch": 0.03869303525365434, "percentage": 0.39, "elapsed_time": "0:02:51", "remaining_time": "12:11:52"}
|
| 10 |
+
{"current_steps": 10, "total_steps": 2320, "loss": 2.3554, "lr": 1.8e-07, "epoch": 0.04299226139294927, "percentage": 0.43, "elapsed_time": "0:03:08", "remaining_time": "12:06:47"}
|
| 11 |
+
{"current_steps": 11, "total_steps": 2320, "loss": 2.3779, "lr": 2e-07, "epoch": 0.04729148753224419, "percentage": 0.47, "elapsed_time": "0:03:26", "remaining_time": "12:02:29"}
|
| 12 |
+
{"current_steps": 12, "total_steps": 2320, "loss": 2.384, "lr": 2.1999999999999998e-07, "epoch": 0.051590713671539126, "percentage": 0.52, "elapsed_time": "0:03:44", "remaining_time": "11:58:47"}
|
| 13 |
+
{"current_steps": 13, "total_steps": 2320, "loss": 2.3948, "lr": 2.4e-07, "epoch": 0.05588993981083405, "percentage": 0.56, "elapsed_time": "0:04:01", "remaining_time": "11:55:39"}
|
| 14 |
+
{"current_steps": 14, "total_steps": 2320, "loss": 2.3868, "lr": 2.6e-07, "epoch": 0.06018916595012898, "percentage": 0.6, "elapsed_time": "0:04:19", "remaining_time": "11:52:56"}
|
| 15 |
+
{"current_steps": 15, "total_steps": 2320, "loss": 2.3797, "lr": 2.8e-07, "epoch": 0.0644883920894239, "percentage": 0.65, "elapsed_time": "0:04:37", "remaining_time": "11:50:31"}
|
| 16 |
+
{"current_steps": 16, "total_steps": 2320, "loss": 2.3763, "lr": 3e-07, "epoch": 0.06878761822871883, "percentage": 0.69, "elapsed_time": "0:04:55", "remaining_time": "11:48:24"}
|
| 17 |
+
{"current_steps": 17, "total_steps": 2320, "loss": 2.3719, "lr": 3.2e-07, "epoch": 0.07308684436801376, "percentage": 0.73, "elapsed_time": "0:05:12", "remaining_time": "11:46:34"}
|
| 18 |
+
{"current_steps": 18, "total_steps": 2320, "loss": 2.3708, "lr": 3.4000000000000003e-07, "epoch": 0.07738607050730868, "percentage": 0.78, "elapsed_time": "0:05:30", "remaining_time": "11:44:52"}
|
| 19 |
+
{"current_steps": 19, "total_steps": 2320, "loss": 2.4066, "lr": 3.6e-07, "epoch": 0.08168529664660361, "percentage": 0.82, "elapsed_time": "0:05:48", "remaining_time": "11:43:18"}
|
| 20 |
+
{"current_steps": 20, "total_steps": 2320, "loss": 2.405, "lr": 3.7999999999999996e-07, "epoch": 0.08598452278589853, "percentage": 0.86, "elapsed_time": "0:06:06", "remaining_time": "11:41:52"}
|
| 21 |
+
{"current_steps": 21, "total_steps": 2320, "loss": 2.3833, "lr": 4e-07, "epoch": 0.09028374892519346, "percentage": 0.91, "elapsed_time": "0:06:23", "remaining_time": "11:40:34"}
|
| 22 |
+
{"current_steps": 22, "total_steps": 2320, "loss": 2.3673, "lr": 4.1999999999999995e-07, "epoch": 0.09458297506448839, "percentage": 0.95, "elapsed_time": "0:06:41", "remaining_time": "11:39:18"}
|
| 23 |
+
{"current_steps": 23, "total_steps": 2320, "loss": 2.3853, "lr": 4.3999999999999997e-07, "epoch": 0.09888220120378331, "percentage": 0.99, "elapsed_time": "0:06:59", "remaining_time": "11:38:10"}
|
| 24 |
+
{"current_steps": 24, "total_steps": 2320, "loss": 2.3595, "lr": 4.6e-07, "epoch": 0.10318142734307825, "percentage": 1.03, "elapsed_time": "0:07:17", "remaining_time": "11:37:05"}
|
| 25 |
+
{"current_steps": 25, "total_steps": 2320, "loss": 2.3929, "lr": 4.8e-07, "epoch": 0.10748065348237318, "percentage": 1.08, "elapsed_time": "0:07:34", "remaining_time": "11:36:03"}
|
| 26 |
+
{"current_steps": 26, "total_steps": 2320, "loss": 2.3639, "lr": 5e-07, "epoch": 0.1117798796216681, "percentage": 1.12, "elapsed_time": "0:07:52", "remaining_time": "11:35:04"}
|
| 27 |
+
{"current_steps": 27, "total_steps": 2320, "loss": 2.3962, "lr": 5.2e-07, "epoch": 0.11607910576096303, "percentage": 1.16, "elapsed_time": "0:08:10", "remaining_time": "11:34:10"}
|
| 28 |
+
{"current_steps": 28, "total_steps": 2320, "loss": 2.3876, "lr": 5.4e-07, "epoch": 0.12037833190025796, "percentage": 1.21, "elapsed_time": "0:08:28", "remaining_time": "11:33:18"}
|
| 29 |
+
{"current_steps": 29, "total_steps": 2320, "loss": 2.3993, "lr": 5.6e-07, "epoch": 0.12467755803955288, "percentage": 1.25, "elapsed_time": "0:08:45", "remaining_time": "11:32:27"}
|
| 30 |
+
{"current_steps": 30, "total_steps": 2320, "loss": 2.3765, "lr": 5.8e-07, "epoch": 0.1289767841788478, "percentage": 1.29, "elapsed_time": "0:09:03", "remaining_time": "11:31:40"}
|
| 31 |
+
{"current_steps": 31, "total_steps": 2320, "loss": 2.3554, "lr": 6e-07, "epoch": 0.13327601031814273, "percentage": 1.34, "elapsed_time": "0:09:21", "remaining_time": "11:30:55"}
|
| 32 |
+
{"current_steps": 32, "total_steps": 2320, "loss": 2.3721, "lr": 6.2e-07, "epoch": 0.13757523645743766, "percentage": 1.38, "elapsed_time": "0:09:39", "remaining_time": "11:30:11"}
|
| 33 |
+
{"current_steps": 33, "total_steps": 2320, "loss": 2.3609, "lr": 6.4e-07, "epoch": 0.1418744625967326, "percentage": 1.42, "elapsed_time": "0:09:56", "remaining_time": "11:29:30"}
|
| 34 |
+
{"current_steps": 34, "total_steps": 2320, "loss": 2.3855, "lr": 6.6e-07, "epoch": 0.1461736887360275, "percentage": 1.47, "elapsed_time": "0:10:14", "remaining_time": "11:28:49"}
|
| 35 |
+
{"current_steps": 35, "total_steps": 2320, "loss": 2.3816, "lr": 6.800000000000001e-07, "epoch": 0.15047291487532244, "percentage": 1.51, "elapsed_time": "0:10:32", "remaining_time": "11:28:09"}
|
| 36 |
+
{"current_steps": 36, "total_steps": 2320, "loss": 2.3775, "lr": 7e-07, "epoch": 0.15477214101461736, "percentage": 1.55, "elapsed_time": "0:10:50", "remaining_time": "11:27:30"}
|
| 37 |
+
{"current_steps": 37, "total_steps": 2320, "loss": 2.3823, "lr": 7.2e-07, "epoch": 0.1590713671539123, "percentage": 1.59, "elapsed_time": "0:11:07", "remaining_time": "11:26:52"}
|
| 38 |
+
{"current_steps": 38, "total_steps": 2320, "loss": 2.3476, "lr": 7.4e-07, "epoch": 0.16337059329320722, "percentage": 1.64, "elapsed_time": "0:11:25", "remaining_time": "11:26:15"}
|
| 39 |
+
{"current_steps": 39, "total_steps": 2320, "loss": 2.3732, "lr": 7.599999999999999e-07, "epoch": 0.16766981943250214, "percentage": 1.68, "elapsed_time": "0:11:43", "remaining_time": "11:25:40"}
|
| 40 |
+
{"current_steps": 40, "total_steps": 2320, "loss": 2.3637, "lr": 7.799999999999999e-07, "epoch": 0.17196904557179707, "percentage": 1.72, "elapsed_time": "0:12:01", "remaining_time": "11:25:06"}
|
| 41 |
+
{"current_steps": 41, "total_steps": 2320, "loss": 2.3552, "lr": 8e-07, "epoch": 0.176268271711092, "percentage": 1.77, "elapsed_time": "0:12:18", "remaining_time": "11:24:32"}
|
| 42 |
+
{"current_steps": 42, "total_steps": 2320, "loss": 2.3457, "lr": 8.199999999999999e-07, "epoch": 0.18056749785038692, "percentage": 1.81, "elapsed_time": "0:12:36", "remaining_time": "11:23:59"}
|
| 43 |
+
{"current_steps": 43, "total_steps": 2320, "loss": 2.3556, "lr": 8.399999999999999e-07, "epoch": 0.18486672398968185, "percentage": 1.85, "elapsed_time": "0:12:54", "remaining_time": "11:23:26"}
|
| 44 |
+
{"current_steps": 44, "total_steps": 2320, "loss": 2.3747, "lr": 8.599999999999999e-07, "epoch": 0.18916595012897677, "percentage": 1.9, "elapsed_time": "0:13:12", "remaining_time": "11:22:54"}
|
| 45 |
+
{"current_steps": 45, "total_steps": 2320, "loss": 2.3809, "lr": 8.799999999999999e-07, "epoch": 0.1934651762682717, "percentage": 1.94, "elapsed_time": "0:13:29", "remaining_time": "11:22:23"}
|
| 46 |
+
{"current_steps": 46, "total_steps": 2320, "loss": 2.37, "lr": 9e-07, "epoch": 0.19776440240756663, "percentage": 1.98, "elapsed_time": "0:13:47", "remaining_time": "11:21:54"}
|
| 47 |
+
{"current_steps": 47, "total_steps": 2320, "loss": 2.3246, "lr": 9.2e-07, "epoch": 0.20206362854686155, "percentage": 2.03, "elapsed_time": "0:14:05", "remaining_time": "11:21:23"}
|
| 48 |
+
{"current_steps": 48, "total_steps": 2320, "loss": 2.3537, "lr": 9.399999999999999e-07, "epoch": 0.2063628546861565, "percentage": 2.07, "elapsed_time": "0:14:23", "remaining_time": "11:20:54"}
|
| 49 |
+
{"current_steps": 49, "total_steps": 2320, "loss": 2.3405, "lr": 9.6e-07, "epoch": 0.21066208082545143, "percentage": 2.11, "elapsed_time": "0:14:40", "remaining_time": "11:20:24"}
|
| 50 |
+
{"current_steps": 50, "total_steps": 2320, "loss": 2.3524, "lr": 9.8e-07, "epoch": 0.21496130696474636, "percentage": 2.16, "elapsed_time": "0:14:58", "remaining_time": "11:19:56"}
|
| 51 |
+
{"current_steps": 51, "total_steps": 2320, "loss": 2.3268, "lr": 1e-06, "epoch": 0.21926053310404128, "percentage": 2.2, "elapsed_time": "0:15:16", "remaining_time": "11:19:28"}
|
| 52 |
+
{"current_steps": 52, "total_steps": 2320, "loss": 2.3441, "lr": 9.995594713656387e-07, "epoch": 0.2235597592433362, "percentage": 2.24, "elapsed_time": "0:15:34", "remaining_time": "11:19:02"}
|
| 53 |
+
{"current_steps": 53, "total_steps": 2320, "loss": 2.3518, "lr": 9.991189427312774e-07, "epoch": 0.22785898538263114, "percentage": 2.28, "elapsed_time": "0:15:51", "remaining_time": "11:18:34"}
|
| 54 |
+
{"current_steps": 54, "total_steps": 2320, "loss": 2.3581, "lr": 9.986784140969161e-07, "epoch": 0.23215821152192606, "percentage": 2.33, "elapsed_time": "0:16:09", "remaining_time": "11:18:07"}
|
| 55 |
+
{"current_steps": 55, "total_steps": 2320, "loss": 2.3432, "lr": 9.98237885462555e-07, "epoch": 0.236457437661221, "percentage": 2.37, "elapsed_time": "0:16:27", "remaining_time": "11:17:40"}
|
| 56 |
+
{"current_steps": 56, "total_steps": 2320, "loss": 2.3419, "lr": 9.977973568281938e-07, "epoch": 0.2407566638005159, "percentage": 2.41, "elapsed_time": "0:16:45", "remaining_time": "11:17:13"}
|
| 57 |
+
{"current_steps": 57, "total_steps": 2320, "loss": 2.3484, "lr": 9.973568281938325e-07, "epoch": 0.24505588993981084, "percentage": 2.46, "elapsed_time": "0:17:02", "remaining_time": "11:16:48"}
|
| 58 |
+
{"current_steps": 58, "total_steps": 2320, "loss": 2.3416, "lr": 9.969162995594713e-07, "epoch": 0.24935511607910577, "percentage": 2.5, "elapsed_time": "0:17:20", "remaining_time": "11:16:22"}
|
| 59 |
+
{"current_steps": 59, "total_steps": 2320, "loss": 2.3187, "lr": 9.9647577092511e-07, "epoch": 0.25365434221840066, "percentage": 2.54, "elapsed_time": "0:17:38", "remaining_time": "11:15:56"}
|
| 60 |
+
{"current_steps": 60, "total_steps": 2320, "loss": 2.3231, "lr": 9.96035242290749e-07, "epoch": 0.2579535683576956, "percentage": 2.59, "elapsed_time": "0:17:56", "remaining_time": "11:15:31"}
|
| 61 |
+
{"current_steps": 61, "total_steps": 2320, "loss": 2.3263, "lr": 9.955947136563877e-07, "epoch": 0.2622527944969905, "percentage": 2.63, "elapsed_time": "0:18:13", "remaining_time": "11:15:06"}
|
| 62 |
+
{"current_steps": 62, "total_steps": 2320, "loss": 2.3401, "lr": 9.951541850220264e-07, "epoch": 0.26655202063628547, "percentage": 2.67, "elapsed_time": "0:18:31", "remaining_time": "11:14:42"}
|
| 63 |
+
{"current_steps": 63, "total_steps": 2320, "loss": 2.287, "lr": 9.947136563876651e-07, "epoch": 0.2708512467755804, "percentage": 2.72, "elapsed_time": "0:18:49", "remaining_time": "11:14:18"}
|
| 64 |
+
{"current_steps": 64, "total_steps": 2320, "loss": 2.3352, "lr": 9.942731277533039e-07, "epoch": 0.2751504729148753, "percentage": 2.76, "elapsed_time": "0:19:07", "remaining_time": "11:13:53"}
|
| 65 |
+
{"current_steps": 65, "total_steps": 2320, "loss": 2.3317, "lr": 9.938325991189426e-07, "epoch": 0.2794496990541703, "percentage": 2.8, "elapsed_time": "0:19:24", "remaining_time": "11:13:27"}
|
| 66 |
+
{"current_steps": 66, "total_steps": 2320, "loss": 2.3367, "lr": 9.933920704845813e-07, "epoch": 0.2837489251934652, "percentage": 2.84, "elapsed_time": "0:19:42", "remaining_time": "11:13:03"}
|
| 67 |
+
{"current_steps": 67, "total_steps": 2320, "loss": 2.2921, "lr": 9.929515418502203e-07, "epoch": 0.2880481513327601, "percentage": 2.89, "elapsed_time": "0:20:00", "remaining_time": "11:12:40"}
|
| 68 |
+
{"current_steps": 68, "total_steps": 2320, "loss": 2.3141, "lr": 9.92511013215859e-07, "epoch": 0.292347377472055, "percentage": 2.93, "elapsed_time": "0:20:17", "remaining_time": "11:12:16"}
|
| 69 |
+
{"current_steps": 69, "total_steps": 2320, "loss": 2.3336, "lr": 9.920704845814977e-07, "epoch": 0.29664660361135, "percentage": 2.97, "elapsed_time": "0:20:35", "remaining_time": "11:11:52"}
|
| 70 |
+
{"current_steps": 70, "total_steps": 2320, "loss": 2.3218, "lr": 9.916299559471365e-07, "epoch": 0.3009458297506449, "percentage": 3.02, "elapsed_time": "0:20:53", "remaining_time": "11:11:29"}
|
| 71 |
+
{"current_steps": 71, "total_steps": 2320, "loss": 2.3369, "lr": 9.911894273127754e-07, "epoch": 0.30524505588993983, "percentage": 3.06, "elapsed_time": "0:21:11", "remaining_time": "11:11:06"}
|
| 72 |
+
{"current_steps": 72, "total_steps": 2320, "loss": 2.2987, "lr": 9.907488986784141e-07, "epoch": 0.30954428202923473, "percentage": 3.1, "elapsed_time": "0:21:28", "remaining_time": "11:10:43"}
|
| 73 |
+
{"current_steps": 73, "total_steps": 2320, "loss": 2.3212, "lr": 9.903083700440529e-07, "epoch": 0.3138435081685297, "percentage": 3.15, "elapsed_time": "0:21:46", "remaining_time": "11:10:20"}
|
| 74 |
+
{"current_steps": 74, "total_steps": 2320, "loss": 2.3155, "lr": 9.898678414096916e-07, "epoch": 0.3181427343078246, "percentage": 3.19, "elapsed_time": "0:22:04", "remaining_time": "11:09:57"}
|
| 75 |
+
{"current_steps": 75, "total_steps": 2320, "loss": 2.2984, "lr": 9.894273127753303e-07, "epoch": 0.32244196044711954, "percentage": 3.23, "elapsed_time": "0:22:22", "remaining_time": "11:09:35"}
|
| 76 |
+
{"current_steps": 76, "total_steps": 2320, "loss": 2.2807, "lr": 9.88986784140969e-07, "epoch": 0.32674118658641443, "percentage": 3.28, "elapsed_time": "0:22:39", "remaining_time": "11:09:13"}
|
| 77 |
+
{"current_steps": 77, "total_steps": 2320, "loss": 2.3219, "lr": 9.885462555066078e-07, "epoch": 0.3310404127257094, "percentage": 3.32, "elapsed_time": "0:22:57", "remaining_time": "11:08:50"}
|
| 78 |
+
{"current_steps": 78, "total_steps": 2320, "loss": 2.28, "lr": 9.881057268722467e-07, "epoch": 0.3353396388650043, "percentage": 3.36, "elapsed_time": "0:23:15", "remaining_time": "11:08:28"}
|
| 79 |
+
{"current_steps": 79, "total_steps": 2320, "loss": 2.3314, "lr": 9.876651982378854e-07, "epoch": 0.33963886500429924, "percentage": 3.41, "elapsed_time": "0:23:33", "remaining_time": "11:08:06"}
|
| 80 |
+
{"current_steps": 80, "total_steps": 2320, "loss": 2.2938, "lr": 9.872246696035242e-07, "epoch": 0.34393809114359414, "percentage": 3.45, "elapsed_time": "0:23:50", "remaining_time": "11:07:44"}
|
| 81 |
+
{"current_steps": 81, "total_steps": 2320, "loss": 2.2906, "lr": 9.86784140969163e-07, "epoch": 0.3482373172828891, "percentage": 3.49, "elapsed_time": "0:24:08", "remaining_time": "11:07:22"}
|
| 82 |
+
{"current_steps": 82, "total_steps": 2320, "loss": 2.316, "lr": 9.863436123348016e-07, "epoch": 0.352536543422184, "percentage": 3.53, "elapsed_time": "0:24:26", "remaining_time": "11:07:00"}
|
| 83 |
+
{"current_steps": 83, "total_steps": 2320, "loss": 2.2868, "lr": 9.859030837004406e-07, "epoch": 0.35683576956147894, "percentage": 3.58, "elapsed_time": "0:24:44", "remaining_time": "11:06:39"}
|
| 84 |
+
{"current_steps": 84, "total_steps": 2320, "loss": 2.3027, "lr": 9.854625550660793e-07, "epoch": 0.36113499570077384, "percentage": 3.62, "elapsed_time": "0:25:01", "remaining_time": "11:06:17"}
|
| 85 |
+
{"current_steps": 85, "total_steps": 2320, "loss": 2.2801, "lr": 9.85022026431718e-07, "epoch": 0.3654342218400688, "percentage": 3.66, "elapsed_time": "0:25:19", "remaining_time": "11:05:56"}
|
| 86 |
+
{"current_steps": 86, "total_steps": 2320, "loss": 2.2679, "lr": 9.845814977973568e-07, "epoch": 0.3697334479793637, "percentage": 3.71, "elapsed_time": "0:25:37", "remaining_time": "11:05:34"}
|
| 87 |
+
{"current_steps": 87, "total_steps": 2320, "loss": 2.2975, "lr": 9.841409691629957e-07, "epoch": 0.37403267411865865, "percentage": 3.75, "elapsed_time": "0:25:55", "remaining_time": "11:05:13"}
|
| 88 |
+
{"current_steps": 88, "total_steps": 2320, "loss": 2.257, "lr": 9.837004405286342e-07, "epoch": 0.37833190025795355, "percentage": 3.79, "elapsed_time": "0:26:12", "remaining_time": "11:04:52"}
|
| 89 |
+
{"current_steps": 89, "total_steps": 2320, "loss": 2.2771, "lr": 9.83259911894273e-07, "epoch": 0.3826311263972485, "percentage": 3.84, "elapsed_time": "0:26:30", "remaining_time": "11:04:31"}
|
| 90 |
+
{"current_steps": 90, "total_steps": 2320, "loss": 2.2653, "lr": 9.82819383259912e-07, "epoch": 0.3869303525365434, "percentage": 3.88, "elapsed_time": "0:26:48", "remaining_time": "11:04:10"}
|
| 91 |
+
{"current_steps": 91, "total_steps": 2320, "loss": 2.25, "lr": 9.823788546255506e-07, "epoch": 0.39122957867583835, "percentage": 3.92, "elapsed_time": "0:27:06", "remaining_time": "11:03:50"}
|
| 92 |
+
{"current_steps": 92, "total_steps": 2320, "loss": 2.2563, "lr": 9.819383259911894e-07, "epoch": 0.39552880481513325, "percentage": 3.97, "elapsed_time": "0:27:23", "remaining_time": "11:03:29"}
|
| 93 |
+
{"current_steps": 93, "total_steps": 2320, "loss": 2.2693, "lr": 9.81497797356828e-07, "epoch": 0.3998280309544282, "percentage": 4.01, "elapsed_time": "0:27:41", "remaining_time": "11:03:08"}
|
| 94 |
+
{"current_steps": 94, "total_steps": 2320, "loss": 2.2472, "lr": 9.81057268722467e-07, "epoch": 0.4041272570937231, "percentage": 4.05, "elapsed_time": "0:27:59", "remaining_time": "11:02:47"}
|
| 95 |
+
{"current_steps": 95, "total_steps": 2320, "loss": 2.2679, "lr": 9.806167400881058e-07, "epoch": 0.40842648323301806, "percentage": 4.09, "elapsed_time": "0:28:17", "remaining_time": "11:02:26"}
|
| 96 |
+
{"current_steps": 96, "total_steps": 2320, "loss": 2.2423, "lr": 9.801762114537445e-07, "epoch": 0.412725709372313, "percentage": 4.14, "elapsed_time": "0:28:34", "remaining_time": "11:02:05"}
|
| 97 |
+
{"current_steps": 97, "total_steps": 2320, "loss": 2.258, "lr": 9.797356828193832e-07, "epoch": 0.4170249355116079, "percentage": 4.18, "elapsed_time": "0:28:52", "remaining_time": "11:01:45"}
|
| 98 |
+
{"current_steps": 98, "total_steps": 2320, "loss": 2.2547, "lr": 9.79295154185022e-07, "epoch": 0.42132416165090286, "percentage": 4.22, "elapsed_time": "0:29:10", "remaining_time": "11:01:24"}
|
| 99 |
+
{"current_steps": 99, "total_steps": 2320, "loss": 2.2816, "lr": 9.788546255506609e-07, "epoch": 0.42562338779019776, "percentage": 4.27, "elapsed_time": "0:29:28", "remaining_time": "11:01:04"}
|
| 100 |
+
{"current_steps": 100, "total_steps": 2320, "loss": 2.2625, "lr": 9.784140969162994e-07, "epoch": 0.4299226139294927, "percentage": 4.31, "elapsed_time": "0:29:45", "remaining_time": "11:00:44"}
|
| 101 |
+
{"current_steps": 101, "total_steps": 2320, "loss": 2.266, "lr": 9.779735682819383e-07, "epoch": 0.4342218400687876, "percentage": 4.35, "elapsed_time": "0:30:03", "remaining_time": "11:00:24"}
|
| 102 |
+
{"current_steps": 102, "total_steps": 2320, "loss": 2.2777, "lr": 9.77533039647577e-07, "epoch": 0.43852106620808257, "percentage": 4.4, "elapsed_time": "0:30:21", "remaining_time": "11:00:04"}
|
| 103 |
+
{"current_steps": 103, "total_steps": 2320, "loss": 2.2355, "lr": 9.770925110132158e-07, "epoch": 0.44282029234737746, "percentage": 4.44, "elapsed_time": "0:30:39", "remaining_time": "10:59:44"}
|
| 104 |
+
{"current_steps": 104, "total_steps": 2320, "loss": 2.2828, "lr": 9.766519823788545e-07, "epoch": 0.4471195184866724, "percentage": 4.48, "elapsed_time": "0:30:56", "remaining_time": "10:59:24"}
|
| 105 |
+
{"current_steps": 105, "total_steps": 2320, "loss": 2.2619, "lr": 9.762114537444933e-07, "epoch": 0.4514187446259673, "percentage": 4.53, "elapsed_time": "0:31:14", "remaining_time": "10:59:04"}
|
| 106 |
+
{"current_steps": 106, "total_steps": 2320, "loss": 2.2554, "lr": 9.757709251101322e-07, "epoch": 0.45571797076526227, "percentage": 4.57, "elapsed_time": "0:31:32", "remaining_time": "10:58:44"}
|
| 107 |
+
{"current_steps": 107, "total_steps": 2320, "loss": 2.2696, "lr": 9.75330396475771e-07, "epoch": 0.46001719690455717, "percentage": 4.61, "elapsed_time": "0:31:50", "remaining_time": "10:58:25"}
|
| 108 |
+
{"current_steps": 108, "total_steps": 2320, "loss": 2.2255, "lr": 9.748898678414097e-07, "epoch": 0.4643164230438521, "percentage": 4.66, "elapsed_time": "0:32:07", "remaining_time": "10:58:05"}
|
| 109 |
+
{"current_steps": 109, "total_steps": 2320, "loss": 2.199, "lr": 9.744493392070484e-07, "epoch": 0.468615649183147, "percentage": 4.7, "elapsed_time": "0:32:25", "remaining_time": "10:57:45"}
|
| 110 |
+
{"current_steps": 110, "total_steps": 2320, "loss": 2.26, "lr": 9.740088105726871e-07, "epoch": 0.472914875322442, "percentage": 4.74, "elapsed_time": "0:32:43", "remaining_time": "10:57:25"}
|
| 111 |
+
{"current_steps": 111, "total_steps": 2320, "loss": 2.2742, "lr": 9.73568281938326e-07, "epoch": 0.4772141014617369, "percentage": 4.78, "elapsed_time": "0:33:01", "remaining_time": "10:57:05"}
|
| 112 |
+
{"current_steps": 112, "total_steps": 2320, "loss": 2.257, "lr": 9.731277533039646e-07, "epoch": 0.4815133276010318, "percentage": 4.83, "elapsed_time": "0:33:18", "remaining_time": "10:56:46"}
|
| 113 |
+
{"current_steps": 113, "total_steps": 2320, "loss": 2.2456, "lr": 9.726872246696035e-07, "epoch": 0.4858125537403267, "percentage": 4.87, "elapsed_time": "0:33:36", "remaining_time": "10:56:26"}
|
| 114 |
+
{"current_steps": 114, "total_steps": 2320, "loss": 2.2419, "lr": 9.722466960352423e-07, "epoch": 0.4901117798796217, "percentage": 4.91, "elapsed_time": "0:33:54", "remaining_time": "10:56:06"}
|
| 115 |
+
{"current_steps": 115, "total_steps": 2320, "loss": 2.2414, "lr": 9.71806167400881e-07, "epoch": 0.4944110060189166, "percentage": 4.96, "elapsed_time": "0:34:12", "remaining_time": "10:55:47"}
|
| 116 |
+
{"current_steps": 116, "total_steps": 2320, "loss": 2.2453, "lr": 9.713656387665197e-07, "epoch": 0.49871023215821153, "percentage": 5.0, "elapsed_time": "0:34:29", "remaining_time": "10:55:27"}
|
| 117 |
+
{"current_steps": 117, "total_steps": 2320, "loss": 2.217, "lr": 9.709251101321584e-07, "epoch": 0.5030094582975064, "percentage": 5.04, "elapsed_time": "0:34:47", "remaining_time": "10:55:07"}
|
| 118 |
+
{"current_steps": 118, "total_steps": 2320, "loss": 2.2157, "lr": 9.704845814977974e-07, "epoch": 0.5073086844368013, "percentage": 5.09, "elapsed_time": "0:35:05", "remaining_time": "10:54:48"}
|
| 119 |
+
{"current_steps": 119, "total_steps": 2320, "loss": 2.2334, "lr": 9.700440528634361e-07, "epoch": 0.5116079105760963, "percentage": 5.13, "elapsed_time": "0:35:23", "remaining_time": "10:54:28"}
|
| 120 |
+
{"current_steps": 120, "total_steps": 2320, "loss": 2.2227, "lr": 9.696035242290748e-07, "epoch": 0.5159071367153912, "percentage": 5.17, "elapsed_time": "0:35:40", "remaining_time": "10:54:09"}
|
| 121 |
+
{"current_steps": 121, "total_steps": 2320, "loss": 2.2613, "lr": 9.691629955947136e-07, "epoch": 0.5202063628546861, "percentage": 5.22, "elapsed_time": "0:35:58", "remaining_time": "10:53:49"}
|
| 122 |
+
{"current_steps": 122, "total_steps": 2320, "loss": 2.2316, "lr": 9.687224669603525e-07, "epoch": 0.524505588993981, "percentage": 5.26, "elapsed_time": "0:36:16", "remaining_time": "10:53:30"}
|
| 123 |
+
{"current_steps": 123, "total_steps": 2320, "loss": 2.2252, "lr": 9.682819383259912e-07, "epoch": 0.528804815133276, "percentage": 5.3, "elapsed_time": "0:36:34", "remaining_time": "10:53:11"}
|
| 124 |
+
{"current_steps": 124, "total_steps": 2320, "loss": 2.2375, "lr": 9.678414096916298e-07, "epoch": 0.5331040412725709, "percentage": 5.34, "elapsed_time": "0:36:51", "remaining_time": "10:52:52"}
|
| 125 |
+
{"current_steps": 125, "total_steps": 2320, "loss": 2.2638, "lr": 9.674008810572687e-07, "epoch": 0.5374032674118658, "percentage": 5.39, "elapsed_time": "0:37:09", "remaining_time": "10:52:32"}
|
| 126 |
+
{"current_steps": 126, "total_steps": 2320, "loss": 2.2207, "lr": 9.669603524229074e-07, "epoch": 0.5417024935511608, "percentage": 5.43, "elapsed_time": "0:37:27", "remaining_time": "10:52:13"}
|
| 127 |
+
{"current_steps": 127, "total_steps": 2320, "loss": 2.2081, "lr": 9.665198237885462e-07, "epoch": 0.5460017196904557, "percentage": 5.47, "elapsed_time": "0:37:45", "remaining_time": "10:51:53"}
|
| 128 |
+
{"current_steps": 128, "total_steps": 2320, "loss": 2.2282, "lr": 9.660792951541849e-07, "epoch": 0.5503009458297506, "percentage": 5.52, "elapsed_time": "0:38:02", "remaining_time": "10:51:34"}
|
| 129 |
+
{"current_steps": 129, "total_steps": 2320, "loss": 2.24, "lr": 9.656387665198238e-07, "epoch": 0.5546001719690455, "percentage": 5.56, "elapsed_time": "0:38:20", "remaining_time": "10:51:15"}
|
| 130 |
+
{"current_steps": 130, "total_steps": 2320, "loss": 2.2144, "lr": 9.651982378854626e-07, "epoch": 0.5588993981083406, "percentage": 5.6, "elapsed_time": "0:38:38", "remaining_time": "10:50:56"}
|
| 131 |
+
{"current_steps": 131, "total_steps": 2320, "loss": 2.259, "lr": 9.647577092511013e-07, "epoch": 0.5631986242476354, "percentage": 5.65, "elapsed_time": "0:38:56", "remaining_time": "10:50:37"}
|
| 132 |
+
{"current_steps": 132, "total_steps": 2320, "loss": 2.2118, "lr": 9.6431718061674e-07, "epoch": 0.5674978503869303, "percentage": 5.69, "elapsed_time": "0:39:13", "remaining_time": "10:50:18"}
|
| 133 |
+
{"current_steps": 133, "total_steps": 2320, "loss": 2.2543, "lr": 9.638766519823788e-07, "epoch": 0.5717970765262252, "percentage": 5.73, "elapsed_time": "0:39:31", "remaining_time": "10:49:59"}
|
| 134 |
+
{"current_steps": 134, "total_steps": 2320, "loss": 2.2005, "lr": 9.634361233480177e-07, "epoch": 0.5760963026655203, "percentage": 5.78, "elapsed_time": "0:39:49", "remaining_time": "10:49:40"}
|
| 135 |
+
{"current_steps": 135, "total_steps": 2320, "loss": 2.2162, "lr": 9.629955947136564e-07, "epoch": 0.5803955288048152, "percentage": 5.82, "elapsed_time": "0:40:07", "remaining_time": "10:49:21"}
|
| 136 |
+
{"current_steps": 136, "total_steps": 2320, "loss": 2.2353, "lr": 9.625550660792952e-07, "epoch": 0.58469475494411, "percentage": 5.86, "elapsed_time": "0:40:25", "remaining_time": "10:49:03"}
|
| 137 |
+
{"current_steps": 137, "total_steps": 2320, "loss": 2.2256, "lr": 9.621145374449339e-07, "epoch": 0.588993981083405, "percentage": 5.91, "elapsed_time": "0:40:42", "remaining_time": "10:48:44"}
|
| 138 |
+
{"current_steps": 138, "total_steps": 2320, "loss": 2.2152, "lr": 9.616740088105726e-07, "epoch": 0.5932932072227, "percentage": 5.95, "elapsed_time": "0:41:00", "remaining_time": "10:48:24"}
|
| 139 |
+
{"current_steps": 139, "total_steps": 2320, "loss": 2.213, "lr": 9.612334801762113e-07, "epoch": 0.5975924333619949, "percentage": 5.99, "elapsed_time": "0:41:18", "remaining_time": "10:48:06"}
|
| 140 |
+
{"current_steps": 140, "total_steps": 2320, "loss": 2.2236, "lr": 9.6079295154185e-07, "epoch": 0.6018916595012898, "percentage": 6.03, "elapsed_time": "0:41:36", "remaining_time": "10:47:47"}
|
| 141 |
+
{"current_steps": 141, "total_steps": 2320, "loss": 2.2412, "lr": 9.60352422907489e-07, "epoch": 0.6061908856405847, "percentage": 6.08, "elapsed_time": "0:41:53", "remaining_time": "10:47:28"}
|
| 142 |
+
{"current_steps": 142, "total_steps": 2320, "loss": 2.2004, "lr": 9.599118942731277e-07, "epoch": 0.6104901117798797, "percentage": 6.12, "elapsed_time": "0:42:11", "remaining_time": "10:47:09"}
|
| 143 |
+
{"current_steps": 143, "total_steps": 2320, "loss": 2.2357, "lr": 9.594713656387665e-07, "epoch": 0.6147893379191746, "percentage": 6.16, "elapsed_time": "0:42:29", "remaining_time": "10:46:50"}
|
| 144 |
+
{"current_steps": 144, "total_steps": 2320, "loss": 2.2101, "lr": 9.590308370044052e-07, "epoch": 0.6190885640584695, "percentage": 6.21, "elapsed_time": "0:42:47", "remaining_time": "10:46:31"}
|
| 145 |
+
{"current_steps": 145, "total_steps": 2320, "loss": 2.2138, "lr": 9.58590308370044e-07, "epoch": 0.6233877901977644, "percentage": 6.25, "elapsed_time": "0:43:04", "remaining_time": "10:46:12"}
|
| 146 |
+
{"current_steps": 146, "total_steps": 2320, "loss": 2.1993, "lr": 9.581497797356829e-07, "epoch": 0.6276870163370594, "percentage": 6.29, "elapsed_time": "0:43:22", "remaining_time": "10:45:53"}
|
| 147 |
+
{"current_steps": 147, "total_steps": 2320, "loss": 2.2253, "lr": 9.577092511013216e-07, "epoch": 0.6319862424763543, "percentage": 6.34, "elapsed_time": "0:43:40", "remaining_time": "10:45:34"}
|
| 148 |
+
{"current_steps": 148, "total_steps": 2320, "loss": 2.2141, "lr": 9.572687224669603e-07, "epoch": 0.6362854686156492, "percentage": 6.38, "elapsed_time": "0:43:58", "remaining_time": "10:45:15"}
|
| 149 |
+
{"current_steps": 149, "total_steps": 2320, "loss": 2.2145, "lr": 9.56828193832599e-07, "epoch": 0.6405846947549441, "percentage": 6.42, "elapsed_time": "0:44:15", "remaining_time": "10:44:57"}
|
| 150 |
+
{"current_steps": 150, "total_steps": 2320, "loss": 2.2024, "lr": 9.563876651982378e-07, "epoch": 0.6448839208942391, "percentage": 6.47, "elapsed_time": "0:44:33", "remaining_time": "10:44:38"}
|
| 151 |
+
{"current_steps": 151, "total_steps": 2320, "loss": 2.2137, "lr": 9.559471365638765e-07, "epoch": 0.649183147033534, "percentage": 6.51, "elapsed_time": "0:44:51", "remaining_time": "10:44:18"}
|
| 152 |
+
{"current_steps": 152, "total_steps": 2320, "loss": 2.1912, "lr": 9.555066079295155e-07, "epoch": 0.6534823731728289, "percentage": 6.55, "elapsed_time": "0:45:09", "remaining_time": "10:43:59"}
|
| 153 |
+
{"current_steps": 153, "total_steps": 2320, "loss": 2.1844, "lr": 9.550660792951542e-07, "epoch": 0.6577815993121238, "percentage": 6.59, "elapsed_time": "0:45:26", "remaining_time": "10:43:40"}
|
| 154 |
+
{"current_steps": 154, "total_steps": 2320, "loss": 2.2002, "lr": 9.54625550660793e-07, "epoch": 0.6620808254514188, "percentage": 6.64, "elapsed_time": "0:45:44", "remaining_time": "10:43:22"}
|
| 155 |
+
{"current_steps": 155, "total_steps": 2320, "loss": 2.2187, "lr": 9.541850220264317e-07, "epoch": 0.6663800515907137, "percentage": 6.68, "elapsed_time": "0:46:02", "remaining_time": "10:43:03"}
|
| 156 |
+
{"current_steps": 156, "total_steps": 2320, "loss": 2.1945, "lr": 9.537444933920704e-07, "epoch": 0.6706792777300086, "percentage": 6.72, "elapsed_time": "0:46:20", "remaining_time": "10:42:45"}
|
| 157 |
+
{"current_steps": 157, "total_steps": 2320, "loss": 2.1964, "lr": 9.533039647577092e-07, "epoch": 0.6749785038693035, "percentage": 6.77, "elapsed_time": "0:46:37", "remaining_time": "10:42:26"}
|
| 158 |
+
{"current_steps": 158, "total_steps": 2320, "loss": 2.2057, "lr": 9.52863436123348e-07, "epoch": 0.6792777300085985, "percentage": 6.81, "elapsed_time": "0:46:55", "remaining_time": "10:42:07"}
|
| 159 |
+
{"current_steps": 159, "total_steps": 2320, "loss": 2.235, "lr": 9.524229074889868e-07, "epoch": 0.6835769561478934, "percentage": 6.85, "elapsed_time": "0:47:13", "remaining_time": "10:41:48"}
|
| 160 |
+
{"current_steps": 160, "total_steps": 2320, "loss": 2.1906, "lr": 9.519823788546255e-07, "epoch": 0.6878761822871883, "percentage": 6.9, "elapsed_time": "0:47:31", "remaining_time": "10:41:30"}
|
| 161 |
+
{"current_steps": 161, "total_steps": 2320, "loss": 2.2196, "lr": 9.515418502202642e-07, "epoch": 0.6921754084264833, "percentage": 6.94, "elapsed_time": "0:47:48", "remaining_time": "10:41:11"}
|
| 162 |
+
{"current_steps": 162, "total_steps": 2320, "loss": 2.1967, "lr": 9.511013215859031e-07, "epoch": 0.6964746345657782, "percentage": 6.98, "elapsed_time": "0:48:06", "remaining_time": "10:40:53"}
|
| 163 |
+
{"current_steps": 163, "total_steps": 2320, "loss": 2.2079, "lr": 9.506607929515418e-07, "epoch": 0.7007738607050731, "percentage": 7.03, "elapsed_time": "0:48:24", "remaining_time": "10:40:34"}
|
| 164 |
+
{"current_steps": 164, "total_steps": 2320, "loss": 2.1818, "lr": 9.502202643171806e-07, "epoch": 0.705073086844368, "percentage": 7.07, "elapsed_time": "0:48:42", "remaining_time": "10:40:15"}
|
| 165 |
+
{"current_steps": 165, "total_steps": 2320, "loss": 2.1873, "lr": 9.497797356828194e-07, "epoch": 0.709372312983663, "percentage": 7.11, "elapsed_time": "0:48:59", "remaining_time": "10:39:57"}
|
| 166 |
+
{"current_steps": 166, "total_steps": 2320, "loss": 2.2096, "lr": 9.493392070484581e-07, "epoch": 0.7136715391229579, "percentage": 7.16, "elapsed_time": "0:49:17", "remaining_time": "10:39:39"}
|
| 167 |
+
{"current_steps": 167, "total_steps": 2320, "loss": 2.2043, "lr": 9.488986784140968e-07, "epoch": 0.7179707652622528, "percentage": 7.2, "elapsed_time": "0:49:35", "remaining_time": "10:39:20"}
|
| 168 |
+
{"current_steps": 168, "total_steps": 2320, "loss": 2.1888, "lr": 9.484581497797356e-07, "epoch": 0.7222699914015477, "percentage": 7.24, "elapsed_time": "0:49:53", "remaining_time": "10:39:02"}
|
| 169 |
+
{"current_steps": 169, "total_steps": 2320, "loss": 2.1847, "lr": 9.480176211453744e-07, "epoch": 0.7265692175408427, "percentage": 7.28, "elapsed_time": "0:50:11", "remaining_time": "10:38:44"}
|
| 170 |
+
{"current_steps": 170, "total_steps": 2320, "loss": 2.2036, "lr": 9.475770925110131e-07, "epoch": 0.7308684436801376, "percentage": 7.33, "elapsed_time": "0:50:28", "remaining_time": "10:38:25"}
|
| 171 |
+
{"current_steps": 171, "total_steps": 2320, "loss": 2.1938, "lr": 9.47136563876652e-07, "epoch": 0.7351676698194325, "percentage": 7.37, "elapsed_time": "0:50:46", "remaining_time": "10:38:07"}
|
| 172 |
+
{"current_steps": 172, "total_steps": 2320, "loss": 2.1894, "lr": 9.466960352422907e-07, "epoch": 0.7394668959587274, "percentage": 7.41, "elapsed_time": "0:51:04", "remaining_time": "10:37:48"}
|
| 173 |
+
{"current_steps": 173, "total_steps": 2320, "loss": 2.2077, "lr": 9.462555066079295e-07, "epoch": 0.7437661220980224, "percentage": 7.46, "elapsed_time": "0:51:22", "remaining_time": "10:37:30"}
|
| 174 |
+
{"current_steps": 174, "total_steps": 2320, "loss": 2.1852, "lr": 9.458149779735683e-07, "epoch": 0.7480653482373173, "percentage": 7.5, "elapsed_time": "0:51:39", "remaining_time": "10:37:11"}
|
| 175 |
+
{"current_steps": 175, "total_steps": 2320, "loss": 2.1604, "lr": 9.45374449339207e-07, "epoch": 0.7523645743766122, "percentage": 7.54, "elapsed_time": "0:51:57", "remaining_time": "10:36:53"}
|
| 176 |
+
{"current_steps": 176, "total_steps": 2320, "loss": 2.1759, "lr": 9.449339207048458e-07, "epoch": 0.7566638005159071, "percentage": 7.59, "elapsed_time": "0:52:15", "remaining_time": "10:36:34"}
|
| 177 |
+
{"current_steps": 177, "total_steps": 2320, "loss": 2.2069, "lr": 9.444933920704846e-07, "epoch": 0.7609630266552021, "percentage": 7.63, "elapsed_time": "0:52:33", "remaining_time": "10:36:16"}
|
| 178 |
+
{"current_steps": 178, "total_steps": 2320, "loss": 2.2148, "lr": 9.440528634361233e-07, "epoch": 0.765262252794497, "percentage": 7.67, "elapsed_time": "0:52:50", "remaining_time": "10:35:57"}
|
| 179 |
+
{"current_steps": 179, "total_steps": 2320, "loss": 2.1918, "lr": 9.43612334801762e-07, "epoch": 0.7695614789337919, "percentage": 7.72, "elapsed_time": "0:53:08", "remaining_time": "10:35:39"}
|
| 180 |
+
{"current_steps": 180, "total_steps": 2320, "loss": 2.1849, "lr": 9.431718061674008e-07, "epoch": 0.7738607050730868, "percentage": 7.76, "elapsed_time": "0:53:26", "remaining_time": "10:35:20"}
|
| 181 |
+
{"current_steps": 181, "total_steps": 2320, "loss": 2.1685, "lr": 9.427312775330396e-07, "epoch": 0.7781599312123818, "percentage": 7.8, "elapsed_time": "0:53:44", "remaining_time": "10:35:02"}
|
| 182 |
+
{"current_steps": 182, "total_steps": 2320, "loss": 2.2005, "lr": 9.422907488986783e-07, "epoch": 0.7824591573516767, "percentage": 7.84, "elapsed_time": "0:54:01", "remaining_time": "10:34:43"}
|
| 183 |
+
{"current_steps": 183, "total_steps": 2320, "loss": 2.1789, "lr": 9.418502202643171e-07, "epoch": 0.7867583834909716, "percentage": 7.89, "elapsed_time": "0:54:19", "remaining_time": "10:34:24"}
|
| 184 |
+
{"current_steps": 184, "total_steps": 2320, "loss": 2.1678, "lr": 9.414096916299559e-07, "epoch": 0.7910576096302665, "percentage": 7.93, "elapsed_time": "0:54:37", "remaining_time": "10:34:06"}
|
| 185 |
+
{"current_steps": 185, "total_steps": 2320, "loss": 2.1869, "lr": 9.409691629955947e-07, "epoch": 0.7953568357695615, "percentage": 7.97, "elapsed_time": "0:54:55", "remaining_time": "10:33:47"}
|
| 186 |
+
{"current_steps": 186, "total_steps": 2320, "loss": 2.1829, "lr": 9.405286343612334e-07, "epoch": 0.7996560619088564, "percentage": 8.02, "elapsed_time": "0:55:12", "remaining_time": "10:33:29"}
|
| 187 |
+
{"current_steps": 187, "total_steps": 2320, "loss": 2.2041, "lr": 9.400881057268723e-07, "epoch": 0.8039552880481513, "percentage": 8.06, "elapsed_time": "0:55:30", "remaining_time": "10:33:10"}
|
| 188 |
+
{"current_steps": 188, "total_steps": 2320, "loss": 2.1809, "lr": 9.39647577092511e-07, "epoch": 0.8082545141874462, "percentage": 8.1, "elapsed_time": "0:55:48", "remaining_time": "10:32:52"}
|
| 189 |
+
{"current_steps": 189, "total_steps": 2320, "loss": 2.1645, "lr": 9.392070484581497e-07, "epoch": 0.8125537403267412, "percentage": 8.15, "elapsed_time": "0:56:06", "remaining_time": "10:32:34"}
|
| 190 |
+
{"current_steps": 190, "total_steps": 2320, "loss": 2.192, "lr": 9.387665198237885e-07, "epoch": 0.8168529664660361, "percentage": 8.19, "elapsed_time": "0:56:23", "remaining_time": "10:32:15"}
|
| 191 |
+
{"current_steps": 191, "total_steps": 2320, "loss": 2.1644, "lr": 9.383259911894272e-07, "epoch": 0.821152192605331, "percentage": 8.23, "elapsed_time": "0:56:41", "remaining_time": "10:31:57"}
|
| 192 |
+
{"current_steps": 192, "total_steps": 2320, "loss": 2.179, "lr": 9.37885462555066e-07, "epoch": 0.825451418744626, "percentage": 8.28, "elapsed_time": "0:56:59", "remaining_time": "10:31:39"}
|
| 193 |
+
{"current_steps": 193, "total_steps": 2320, "loss": 2.1699, "lr": 9.374449339207048e-07, "epoch": 0.8297506448839209, "percentage": 8.32, "elapsed_time": "0:57:17", "remaining_time": "10:31:21"}
|
| 194 |
+
{"current_steps": 194, "total_steps": 2320, "loss": 2.1859, "lr": 9.370044052863436e-07, "epoch": 0.8340498710232158, "percentage": 8.36, "elapsed_time": "0:57:35", "remaining_time": "10:31:02"}
|
| 195 |
+
{"current_steps": 195, "total_steps": 2320, "loss": 2.1809, "lr": 9.365638766519823e-07, "epoch": 0.8383490971625107, "percentage": 8.41, "elapsed_time": "0:57:52", "remaining_time": "10:30:44"}
|
| 196 |
+
{"current_steps": 196, "total_steps": 2320, "loss": 2.1875, "lr": 9.361233480176211e-07, "epoch": 0.8426483233018057, "percentage": 8.45, "elapsed_time": "0:58:10", "remaining_time": "10:30:25"}
|
| 197 |
+
{"current_steps": 197, "total_steps": 2320, "loss": 2.1924, "lr": 9.356828193832599e-07, "epoch": 0.8469475494411006, "percentage": 8.49, "elapsed_time": "0:58:28", "remaining_time": "10:30:07"}
|
| 198 |
+
{"current_steps": 198, "total_steps": 2320, "loss": 2.1895, "lr": 9.352422907488986e-07, "epoch": 0.8512467755803955, "percentage": 8.53, "elapsed_time": "0:58:46", "remaining_time": "10:29:48"}
|
| 199 |
+
{"current_steps": 199, "total_steps": 2320, "loss": 2.1861, "lr": 9.348017621145375e-07, "epoch": 0.8555460017196904, "percentage": 8.58, "elapsed_time": "0:59:03", "remaining_time": "10:29:30"}
|
| 200 |
+
{"current_steps": 200, "total_steps": 2320, "loss": 2.1736, "lr": 9.343612334801762e-07, "epoch": 0.8598452278589854, "percentage": 8.62, "elapsed_time": "0:59:21", "remaining_time": "10:29:12"}
|
| 201 |
+
{"current_steps": 201, "total_steps": 2320, "loss": 2.2004, "lr": 9.33920704845815e-07, "epoch": 0.8641444539982803, "percentage": 8.66, "elapsed_time": "0:59:39", "remaining_time": "10:28:53"}
|
| 202 |
+
{"current_steps": 202, "total_steps": 2320, "loss": 2.164, "lr": 9.334801762114536e-07, "epoch": 0.8684436801375752, "percentage": 8.71, "elapsed_time": "0:59:57", "remaining_time": "10:28:35"}
|
| 203 |
+
{"current_steps": 203, "total_steps": 2320, "loss": 2.1558, "lr": 9.330396475770924e-07, "epoch": 0.8727429062768701, "percentage": 8.75, "elapsed_time": "1:00:14", "remaining_time": "10:28:16"}
|
| 204 |
+
{"current_steps": 204, "total_steps": 2320, "loss": 2.1786, "lr": 9.325991189427312e-07, "epoch": 0.8770421324161651, "percentage": 8.79, "elapsed_time": "1:00:32", "remaining_time": "10:27:58"}
|
| 205 |
+
{"current_steps": 205, "total_steps": 2320, "loss": 2.2189, "lr": 9.321585903083699e-07, "epoch": 0.88134135855546, "percentage": 8.84, "elapsed_time": "1:00:50", "remaining_time": "10:27:40"}
|
| 206 |
+
{"current_steps": 206, "total_steps": 2320, "loss": 2.1641, "lr": 9.317180616740088e-07, "epoch": 0.8856405846947549, "percentage": 8.88, "elapsed_time": "1:01:08", "remaining_time": "10:27:22"}
|
| 207 |
+
{"current_steps": 207, "total_steps": 2320, "loss": 2.1587, "lr": 9.312775330396475e-07, "epoch": 0.8899398108340498, "percentage": 8.92, "elapsed_time": "1:01:25", "remaining_time": "10:27:03"}
|
| 208 |
+
{"current_steps": 208, "total_steps": 2320, "loss": 2.1613, "lr": 9.308370044052863e-07, "epoch": 0.8942390369733448, "percentage": 8.97, "elapsed_time": "1:01:43", "remaining_time": "10:26:45"}
|
| 209 |
+
{"current_steps": 209, "total_steps": 2320, "loss": 2.1661, "lr": 9.303964757709251e-07, "epoch": 0.8985382631126397, "percentage": 9.01, "elapsed_time": "1:02:01", "remaining_time": "10:26:26"}
|
| 210 |
+
{"current_steps": 210, "total_steps": 2320, "loss": 2.1775, "lr": 9.299559471365639e-07, "epoch": 0.9028374892519346, "percentage": 9.05, "elapsed_time": "1:02:19", "remaining_time": "10:26:09"}
|
| 211 |
+
{"current_steps": 211, "total_steps": 2320, "loss": 2.1434, "lr": 9.295154185022026e-07, "epoch": 0.9071367153912295, "percentage": 9.09, "elapsed_time": "1:02:36", "remaining_time": "10:25:50"}
|
| 212 |
+
{"current_steps": 212, "total_steps": 2320, "loss": 2.1835, "lr": 9.290748898678414e-07, "epoch": 0.9114359415305245, "percentage": 9.14, "elapsed_time": "1:02:54", "remaining_time": "10:25:32"}
|
| 213 |
+
{"current_steps": 213, "total_steps": 2320, "loss": 2.1595, "lr": 9.286343612334802e-07, "epoch": 0.9157351676698194, "percentage": 9.18, "elapsed_time": "1:03:12", "remaining_time": "10:25:14"}
|
| 214 |
+
{"current_steps": 214, "total_steps": 2320, "loss": 2.1607, "lr": 9.281938325991188e-07, "epoch": 0.9200343938091143, "percentage": 9.22, "elapsed_time": "1:03:30", "remaining_time": "10:24:55"}
|
| 215 |
+
{"current_steps": 215, "total_steps": 2320, "loss": 2.1707, "lr": 9.277533039647577e-07, "epoch": 0.9243336199484092, "percentage": 9.27, "elapsed_time": "1:03:47", "remaining_time": "10:24:37"}
|
| 216 |
+
{"current_steps": 216, "total_steps": 2320, "loss": 2.1915, "lr": 9.273127753303964e-07, "epoch": 0.9286328460877042, "percentage": 9.31, "elapsed_time": "1:04:05", "remaining_time": "10:24:18"}
|
| 217 |
+
{"current_steps": 217, "total_steps": 2320, "loss": 2.1661, "lr": 9.268722466960352e-07, "epoch": 0.9329320722269991, "percentage": 9.35, "elapsed_time": "1:04:23", "remaining_time": "10:24:00"}
|
| 218 |
+
{"current_steps": 218, "total_steps": 2320, "loss": 2.1882, "lr": 9.26431718061674e-07, "epoch": 0.937231298366294, "percentage": 9.4, "elapsed_time": "1:04:41", "remaining_time": "10:23:41"}
|
| 219 |
+
{"current_steps": 219, "total_steps": 2320, "loss": 2.1813, "lr": 9.259911894273127e-07, "epoch": 0.9415305245055889, "percentage": 9.44, "elapsed_time": "1:04:58", "remaining_time": "10:23:22"}
|
| 220 |
+
{"current_steps": 220, "total_steps": 2320, "loss": 2.1988, "lr": 9.255506607929515e-07, "epoch": 0.945829750644884, "percentage": 9.48, "elapsed_time": "1:05:16", "remaining_time": "10:23:04"}
|
| 221 |
+
{"current_steps": 221, "total_steps": 2320, "loss": 2.1628, "lr": 9.251101321585902e-07, "epoch": 0.9501289767841788, "percentage": 9.53, "elapsed_time": "1:05:34", "remaining_time": "10:22:46"}
|
| 222 |
+
{"current_steps": 222, "total_steps": 2320, "loss": 2.1794, "lr": 9.246696035242291e-07, "epoch": 0.9544282029234737, "percentage": 9.57, "elapsed_time": "1:05:51", "remaining_time": "10:22:27"}
|
| 223 |
+
{"current_steps": 223, "total_steps": 2320, "loss": 2.1913, "lr": 9.242290748898678e-07, "epoch": 0.9587274290627688, "percentage": 9.61, "elapsed_time": "1:06:09", "remaining_time": "10:22:09"}
|
| 224 |
+
{"current_steps": 224, "total_steps": 2320, "loss": 2.1672, "lr": 9.237885462555067e-07, "epoch": 0.9630266552020637, "percentage": 9.66, "elapsed_time": "1:06:27", "remaining_time": "10:21:50"}
|
| 225 |
+
{"current_steps": 225, "total_steps": 2320, "loss": 2.1731, "lr": 9.233480176211454e-07, "epoch": 0.9673258813413586, "percentage": 9.7, "elapsed_time": "1:06:45", "remaining_time": "10:21:32"}
|
| 226 |
+
{"current_steps": 226, "total_steps": 2320, "loss": 2.1601, "lr": 9.22907488986784e-07, "epoch": 0.9716251074806534, "percentage": 9.74, "elapsed_time": "1:07:02", "remaining_time": "10:21:14"}
|
| 227 |
+
{"current_steps": 227, "total_steps": 2320, "loss": 2.1722, "lr": 9.224669603524228e-07, "epoch": 0.9759243336199485, "percentage": 9.78, "elapsed_time": "1:07:20", "remaining_time": "10:20:56"}
|
| 228 |
+
{"current_steps": 228, "total_steps": 2320, "loss": 2.1611, "lr": 9.220264317180616e-07, "epoch": 0.9802235597592434, "percentage": 9.83, "elapsed_time": "1:07:38", "remaining_time": "10:20:37"}
|
| 229 |
+
{"current_steps": 229, "total_steps": 2320, "loss": 2.1776, "lr": 9.215859030837004e-07, "epoch": 0.9845227858985383, "percentage": 9.87, "elapsed_time": "1:07:56", "remaining_time": "10:20:19"}
|
| 230 |
+
{"current_steps": 230, "total_steps": 2320, "loss": 2.1665, "lr": 9.211453744493391e-07, "epoch": 0.9888220120378332, "percentage": 9.91, "elapsed_time": "1:08:13", "remaining_time": "10:20:01"}
|
| 231 |
+
{"current_steps": 231, "total_steps": 2320, "loss": 2.1705, "lr": 9.20704845814978e-07, "epoch": 0.9931212381771282, "percentage": 9.96, "elapsed_time": "1:08:31", "remaining_time": "10:19:43"}
|
| 232 |
+
{"current_steps": 232, "total_steps": 2320, "loss": 2.1712, "lr": 9.202643171806167e-07, "epoch": 0.9974204643164231, "percentage": 10.0, "elapsed_time": "1:08:49", "remaining_time": "10:19:25"}
|
| 233 |
+
{"current_steps": 233, "total_steps": 2320, "loss": 4.3335, "lr": 9.198237885462554e-07, "epoch": 1.004299226139295, "percentage": 10.04, "elapsed_time": "1:09:17", "remaining_time": "10:20:38"}
|
| 234 |
+
{"current_steps": 234, "total_steps": 2320, "loss": 2.159, "lr": 9.193832599118943e-07, "epoch": 1.0085984522785898, "percentage": 10.09, "elapsed_time": "1:09:35", "remaining_time": "10:20:20"}
|
| 235 |
+
{"current_steps": 235, "total_steps": 2320, "loss": 2.1685, "lr": 9.18942731277533e-07, "epoch": 1.0128976784178847, "percentage": 10.13, "elapsed_time": "1:09:52", "remaining_time": "10:20:01"}
|
| 236 |
+
{"current_steps": 236, "total_steps": 2320, "loss": 2.1657, "lr": 9.185022026431718e-07, "epoch": 1.0171969045571798, "percentage": 10.17, "elapsed_time": "1:10:10", "remaining_time": "10:19:42"}
|
| 237 |
+
{"current_steps": 237, "total_steps": 2320, "loss": 2.1789, "lr": 9.180616740088106e-07, "epoch": 1.0214961306964747, "percentage": 10.22, "elapsed_time": "1:10:28", "remaining_time": "10:19:24"}
|
| 238 |
+
{"current_steps": 238, "total_steps": 2320, "loss": 2.143, "lr": 9.176211453744494e-07, "epoch": 1.0257953568357696, "percentage": 10.26, "elapsed_time": "1:10:46", "remaining_time": "10:19:05"}
|
| 239 |
+
{"current_steps": 239, "total_steps": 2320, "loss": 2.1598, "lr": 9.17180616740088e-07, "epoch": 1.0300945829750645, "percentage": 10.3, "elapsed_time": "1:11:03", "remaining_time": "10:18:46"}
|
| 240 |
+
{"current_steps": 240, "total_steps": 2320, "loss": 2.1802, "lr": 9.167400881057267e-07, "epoch": 1.0343938091143594, "percentage": 10.34, "elapsed_time": "1:11:21", "remaining_time": "10:18:28"}
|
| 241 |
+
{"current_steps": 241, "total_steps": 2320, "loss": 2.1527, "lr": 9.162995594713656e-07, "epoch": 1.0386930352536543, "percentage": 10.39, "elapsed_time": "1:11:39", "remaining_time": "10:18:09"}
|
| 242 |
+
{"current_steps": 242, "total_steps": 2320, "loss": 2.1422, "lr": 9.158590308370043e-07, "epoch": 1.0429922613929492, "percentage": 10.43, "elapsed_time": "1:11:57", "remaining_time": "10:17:50"}
|
| 243 |
+
{"current_steps": 243, "total_steps": 2320, "loss": 2.1357, "lr": 9.154185022026431e-07, "epoch": 1.047291487532244, "percentage": 10.47, "elapsed_time": "1:12:14", "remaining_time": "10:17:32"}
|
| 244 |
+
{"current_steps": 244, "total_steps": 2320, "loss": 2.1511, "lr": 9.149779735682819e-07, "epoch": 1.0515907136715392, "percentage": 10.52, "elapsed_time": "1:12:32", "remaining_time": "10:17:13"}
|
| 245 |
+
{"current_steps": 245, "total_steps": 2320, "loss": 2.1803, "lr": 9.145374449339207e-07, "epoch": 1.0558899398108341, "percentage": 10.56, "elapsed_time": "1:12:50", "remaining_time": "10:16:54"}
|
| 246 |
+
{"current_steps": 246, "total_steps": 2320, "loss": 2.1627, "lr": 9.140969162995594e-07, "epoch": 1.060189165950129, "percentage": 10.6, "elapsed_time": "1:13:08", "remaining_time": "10:16:35"}
|
| 247 |
+
{"current_steps": 247, "total_steps": 2320, "loss": 2.1645, "lr": 9.136563876651982e-07, "epoch": 1.064488392089424, "percentage": 10.65, "elapsed_time": "1:13:25", "remaining_time": "10:16:17"}
|
| 248 |
+
{"current_steps": 248, "total_steps": 2320, "loss": 2.1522, "lr": 9.13215859030837e-07, "epoch": 1.0687876182287188, "percentage": 10.69, "elapsed_time": "1:13:43", "remaining_time": "10:15:58"}
|
| 249 |
+
{"current_steps": 249, "total_steps": 2320, "loss": 2.1812, "lr": 9.127753303964757e-07, "epoch": 1.0730868443680137, "percentage": 10.73, "elapsed_time": "1:14:01", "remaining_time": "10:15:39"}
|
| 250 |
+
{"current_steps": 250, "total_steps": 2320, "loss": 2.1705, "lr": 9.123348017621146e-07, "epoch": 1.0773860705073086, "percentage": 10.78, "elapsed_time": "1:14:19", "remaining_time": "10:15:21"}
|
| 251 |
+
{"current_steps": 251, "total_steps": 2320, "loss": 2.1518, "lr": 9.118942731277532e-07, "epoch": 1.0816852966466035, "percentage": 10.82, "elapsed_time": "1:14:43", "remaining_time": "10:15:58"}
|
| 252 |
+
{"current_steps": 252, "total_steps": 2320, "loss": 2.1441, "lr": 9.11453744493392e-07, "epoch": 1.0859845227858986, "percentage": 10.86, "elapsed_time": "1:15:01", "remaining_time": "10:15:39"}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bab3a6138806ada98ad676160349291e48887dbb1cf9f390e2364b37e9023406
|
| 3 |
+
size 7608
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|