..
Browse files- README.md +5 -0
- adapter_config.json +30 -0
- adapter_model.safetensors +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +43 -0
- trainer_log.jsonl +318 -0
- trainer_state.json +2121 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: gotzmann/uni
|
| 4 |
+
---
|
| 5 |
+
|
adapter_config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "gotzmann/uni",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 16,
|
| 13 |
+
"lora_dropout": 0.0,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 64,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"q_proj",
|
| 23 |
+
"k_proj",
|
| 24 |
+
"v_proj",
|
| 25 |
+
"o_proj"
|
| 26 |
+
],
|
| 27 |
+
"task_type": "CAUSAL_LM",
|
| 28 |
+
"use_dora": false,
|
| 29 |
+
"use_rslora": false
|
| 30 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:627fc4c4e1729828c40e1e55d30eb2526e3fe8b9e52aa4d5d2896a8116485076
|
| 3 |
+
size 524376008
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"bos_token": "<s>",
|
| 31 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<s>' + system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '\\n\\n## User:\\n\\n ' + content + '\\n\\n## Assistant:\\n\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
|
| 32 |
+
"clean_up_tokenization_spaces": false,
|
| 33 |
+
"eos_token": "</s>",
|
| 34 |
+
"legacy": false,
|
| 35 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 36 |
+
"pad_token": "</s>",
|
| 37 |
+
"padding_side": "right",
|
| 38 |
+
"sp_model_kwargs": {},
|
| 39 |
+
"split_special_tokens": false,
|
| 40 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 41 |
+
"unk_token": "<unk>",
|
| 42 |
+
"use_default_system_prompt": false
|
| 43 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,318 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 1, "total_steps": 480, "loss": 1.3728, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.0, "percentage": 0.21, "elapsed_time": "0:01:05", "remaining_time": "8:45:46"}
|
| 2 |
+
{"current_steps": 2, "total_steps": 480, "loss": 1.3427, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.01, "percentage": 0.42, "elapsed_time": "0:02:10", "remaining_time": "8:39:18"}
|
| 3 |
+
{"current_steps": 3, "total_steps": 480, "loss": 1.3983, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.01, "percentage": 0.62, "elapsed_time": "0:03:15", "remaining_time": "8:38:12"}
|
| 4 |
+
{"current_steps": 4, "total_steps": 480, "loss": 1.4146, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.02, "percentage": 0.83, "elapsed_time": "0:04:20", "remaining_time": "8:36:46"}
|
| 5 |
+
{"current_steps": 5, "total_steps": 480, "loss": 1.3665, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.02, "percentage": 1.04, "elapsed_time": "0:05:24", "remaining_time": "8:34:17"}
|
| 6 |
+
{"current_steps": 6, "total_steps": 480, "loss": 1.3865, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.02, "percentage": 1.25, "elapsed_time": "0:06:29", "remaining_time": "8:33:02"}
|
| 7 |
+
{"current_steps": 7, "total_steps": 480, "loss": 1.315, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.03, "percentage": 1.46, "elapsed_time": "0:07:34", "remaining_time": "8:31:50"}
|
| 8 |
+
{"current_steps": 8, "total_steps": 480, "loss": 1.3531, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.03, "percentage": 1.67, "elapsed_time": "0:08:39", "remaining_time": "8:30:56"}
|
| 9 |
+
{"current_steps": 9, "total_steps": 480, "loss": 1.3722, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.04, "percentage": 1.88, "elapsed_time": "0:09:43", "remaining_time": "8:29:03"}
|
| 10 |
+
{"current_steps": 10, "total_steps": 480, "loss": 1.3179, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.04, "percentage": 2.08, "elapsed_time": "0:10:49", "remaining_time": "8:28:25"}
|
| 11 |
+
{"current_steps": 11, "total_steps": 480, "loss": 1.3595, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.05, "percentage": 2.29, "elapsed_time": "0:11:55", "remaining_time": "8:28:30"}
|
| 12 |
+
{"current_steps": 12, "total_steps": 480, "loss": 1.3904, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.05, "percentage": 2.5, "elapsed_time": "0:13:01", "remaining_time": "8:28:12"}
|
| 13 |
+
{"current_steps": 13, "total_steps": 480, "loss": 1.4069, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.05, "percentage": 2.71, "elapsed_time": "0:14:07", "remaining_time": "8:27:10"}
|
| 14 |
+
{"current_steps": 14, "total_steps": 480, "loss": 1.4516, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.06, "percentage": 2.92, "elapsed_time": "0:15:12", "remaining_time": "8:25:59"}
|
| 15 |
+
{"current_steps": 15, "total_steps": 480, "loss": 1.3407, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.06, "percentage": 3.12, "elapsed_time": "0:16:17", "remaining_time": "8:24:49"}
|
| 16 |
+
{"current_steps": 16, "total_steps": 480, "loss": 1.2756, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.07, "percentage": 3.33, "elapsed_time": "0:17:21", "remaining_time": "8:23:19"}
|
| 17 |
+
{"current_steps": 17, "total_steps": 480, "loss": 1.4446, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.07, "percentage": 3.54, "elapsed_time": "0:18:26", "remaining_time": "8:22:14"}
|
| 18 |
+
{"current_steps": 18, "total_steps": 480, "loss": 1.3975, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.07, "percentage": 3.75, "elapsed_time": "0:19:30", "remaining_time": "8:20:55"}
|
| 19 |
+
{"current_steps": 19, "total_steps": 480, "loss": 1.3954, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.08, "percentage": 3.96, "elapsed_time": "0:20:35", "remaining_time": "8:19:41"}
|
| 20 |
+
{"current_steps": 20, "total_steps": 480, "loss": 1.3254, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.08, "percentage": 4.17, "elapsed_time": "0:21:41", "remaining_time": "8:18:49"}
|
| 21 |
+
{"current_steps": 21, "total_steps": 480, "loss": 1.3688, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.09, "percentage": 4.38, "elapsed_time": "0:22:46", "remaining_time": "8:17:57"}
|
| 22 |
+
{"current_steps": 22, "total_steps": 480, "loss": 1.3304, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.09, "percentage": 4.58, "elapsed_time": "0:23:52", "remaining_time": "8:16:57"}
|
| 23 |
+
{"current_steps": 23, "total_steps": 480, "loss": 1.3422, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.1, "percentage": 4.79, "elapsed_time": "0:24:57", "remaining_time": "8:15:58"}
|
| 24 |
+
{"current_steps": 24, "total_steps": 480, "loss": 1.403, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.1, "percentage": 5.0, "elapsed_time": "0:26:02", "remaining_time": "8:14:44"}
|
| 25 |
+
{"current_steps": 25, "total_steps": 480, "loss": 1.3088, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.1, "percentage": 5.21, "elapsed_time": "0:27:06", "remaining_time": "8:13:16"}
|
| 26 |
+
{"current_steps": 26, "total_steps": 480, "loss": 1.3156, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.11, "percentage": 5.42, "elapsed_time": "0:28:11", "remaining_time": "8:12:08"}
|
| 27 |
+
{"current_steps": 27, "total_steps": 480, "loss": 1.3548, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.11, "percentage": 5.62, "elapsed_time": "0:29:15", "remaining_time": "8:10:56"}
|
| 28 |
+
{"current_steps": 28, "total_steps": 480, "loss": 1.323, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.12, "percentage": 5.83, "elapsed_time": "0:30:20", "remaining_time": "8:09:48"}
|
| 29 |
+
{"current_steps": 29, "total_steps": 480, "loss": 1.2991, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.12, "percentage": 6.04, "elapsed_time": "0:31:26", "remaining_time": "8:08:52"}
|
| 30 |
+
{"current_steps": 30, "total_steps": 480, "loss": 1.299, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.12, "percentage": 6.25, "elapsed_time": "0:32:31", "remaining_time": "8:07:53"}
|
| 31 |
+
{"current_steps": 31, "total_steps": 480, "loss": 1.327, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.13, "percentage": 6.46, "elapsed_time": "0:33:36", "remaining_time": "8:06:42"}
|
| 32 |
+
{"current_steps": 32, "total_steps": 480, "loss": 1.33, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.13, "percentage": 6.67, "elapsed_time": "0:34:39", "remaining_time": "8:05:19"}
|
| 33 |
+
{"current_steps": 33, "total_steps": 480, "loss": 1.3307, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.14, "percentage": 6.88, "elapsed_time": "0:35:44", "remaining_time": "8:04:14"}
|
| 34 |
+
{"current_steps": 34, "total_steps": 480, "loss": 1.3028, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.14, "percentage": 7.08, "elapsed_time": "0:36:50", "remaining_time": "8:03:11"}
|
| 35 |
+
{"current_steps": 35, "total_steps": 480, "loss": 1.2963, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.15, "percentage": 7.29, "elapsed_time": "0:37:55", "remaining_time": "8:02:11"}
|
| 36 |
+
{"current_steps": 36, "total_steps": 480, "loss": 1.2444, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.15, "percentage": 7.5, "elapsed_time": "0:39:00", "remaining_time": "8:01:07"}
|
| 37 |
+
{"current_steps": 37, "total_steps": 480, "loss": 1.26, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.15, "percentage": 7.71, "elapsed_time": "0:40:05", "remaining_time": "8:00:03"}
|
| 38 |
+
{"current_steps": 38, "total_steps": 480, "loss": 1.3438, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.16, "percentage": 7.92, "elapsed_time": "0:41:10", "remaining_time": "7:58:58"}
|
| 39 |
+
{"current_steps": 39, "total_steps": 480, "loss": 1.3285, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.16, "percentage": 8.12, "elapsed_time": "0:42:16", "remaining_time": "7:57:58"}
|
| 40 |
+
{"current_steps": 40, "total_steps": 480, "loss": 1.3221, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.17, "percentage": 8.33, "elapsed_time": "0:43:20", "remaining_time": "7:56:50"}
|
| 41 |
+
{"current_steps": 41, "total_steps": 480, "loss": 1.2861, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.17, "percentage": 8.54, "elapsed_time": "0:44:26", "remaining_time": "7:55:47"}
|
| 42 |
+
{"current_steps": 42, "total_steps": 480, "loss": 1.3068, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.17, "percentage": 8.75, "elapsed_time": "0:45:31", "remaining_time": "7:54:42"}
|
| 43 |
+
{"current_steps": 43, "total_steps": 480, "loss": 1.3156, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.18, "percentage": 8.96, "elapsed_time": "0:46:35", "remaining_time": "7:53:34"}
|
| 44 |
+
{"current_steps": 44, "total_steps": 480, "loss": 1.3088, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.18, "percentage": 9.17, "elapsed_time": "0:47:40", "remaining_time": "7:52:28"}
|
| 45 |
+
{"current_steps": 45, "total_steps": 480, "loss": 1.3316, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.19, "percentage": 9.38, "elapsed_time": "0:48:46", "remaining_time": "7:51:24"}
|
| 46 |
+
{"current_steps": 46, "total_steps": 480, "loss": 1.3352, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.19, "percentage": 9.58, "elapsed_time": "0:49:51", "remaining_time": "7:50:20"}
|
| 47 |
+
{"current_steps": 47, "total_steps": 480, "loss": 1.3144, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.2, "percentage": 9.79, "elapsed_time": "0:50:55", "remaining_time": "7:49:10"}
|
| 48 |
+
{"current_steps": 48, "total_steps": 480, "loss": 1.3204, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.2, "percentage": 10.0, "elapsed_time": "0:51:59", "remaining_time": "7:47:58"}
|
| 49 |
+
{"current_steps": 49, "total_steps": 480, "loss": 1.2887, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.2, "percentage": 10.21, "elapsed_time": "0:53:04", "remaining_time": "7:46:53"}
|
| 50 |
+
{"current_steps": 50, "total_steps": 480, "loss": 1.3332, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.21, "percentage": 10.42, "elapsed_time": "0:54:09", "remaining_time": "7:45:43"}
|
| 51 |
+
{"current_steps": 51, "total_steps": 480, "loss": 1.3553, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.21, "percentage": 10.62, "elapsed_time": "0:56:02", "remaining_time": "7:51:23"}
|
| 52 |
+
{"current_steps": 52, "total_steps": 480, "loss": 1.3671, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.22, "percentage": 10.83, "elapsed_time": "0:57:06", "remaining_time": "7:50:06"}
|
| 53 |
+
{"current_steps": 53, "total_steps": 480, "loss": 1.2771, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.22, "percentage": 11.04, "elapsed_time": "0:58:11", "remaining_time": "7:48:51"}
|
| 54 |
+
{"current_steps": 54, "total_steps": 480, "loss": 1.2277, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.22, "percentage": 11.25, "elapsed_time": "0:59:16", "remaining_time": "7:47:37"}
|
| 55 |
+
{"current_steps": 55, "total_steps": 480, "loss": 1.323, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.23, "percentage": 11.46, "elapsed_time": "1:00:21", "remaining_time": "7:46:23"}
|
| 56 |
+
{"current_steps": 56, "total_steps": 480, "loss": 1.2949, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.23, "percentage": 11.67, "elapsed_time": "1:01:26", "remaining_time": "7:45:09"}
|
| 57 |
+
{"current_steps": 57, "total_steps": 480, "loss": 1.3098, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.24, "percentage": 11.88, "elapsed_time": "1:02:30", "remaining_time": "7:43:55"}
|
| 58 |
+
{"current_steps": 58, "total_steps": 480, "loss": 1.3918, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.24, "percentage": 12.08, "elapsed_time": "1:03:36", "remaining_time": "7:42:47"}
|
| 59 |
+
{"current_steps": 59, "total_steps": 480, "loss": 1.2861, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.25, "percentage": 12.29, "elapsed_time": "1:04:41", "remaining_time": "7:41:38"}
|
| 60 |
+
{"current_steps": 60, "total_steps": 480, "loss": 1.316, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.25, "percentage": 12.5, "elapsed_time": "1:05:46", "remaining_time": "7:40:27"}
|
| 61 |
+
{"current_steps": 61, "total_steps": 480, "loss": 1.2717, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.25, "percentage": 12.71, "elapsed_time": "1:06:52", "remaining_time": "7:39:19"}
|
| 62 |
+
{"current_steps": 62, "total_steps": 480, "loss": 1.3252, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.26, "percentage": 12.92, "elapsed_time": "1:07:57", "remaining_time": "7:38:13"}
|
| 63 |
+
{"current_steps": 63, "total_steps": 480, "loss": 1.3211, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.26, "percentage": 13.12, "elapsed_time": "1:09:02", "remaining_time": "7:37:01"}
|
| 64 |
+
{"current_steps": 64, "total_steps": 480, "loss": 1.2757, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.27, "percentage": 13.33, "elapsed_time": "1:10:07", "remaining_time": "7:35:46"}
|
| 65 |
+
{"current_steps": 65, "total_steps": 480, "loss": 1.2457, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.27, "percentage": 13.54, "elapsed_time": "1:11:17", "remaining_time": "7:35:10"}
|
| 66 |
+
{"current_steps": 66, "total_steps": 480, "loss": 1.3159, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.27, "percentage": 13.75, "elapsed_time": "1:12:22", "remaining_time": "7:33:56"}
|
| 67 |
+
{"current_steps": 67, "total_steps": 480, "loss": 1.2628, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.28, "percentage": 13.96, "elapsed_time": "1:13:27", "remaining_time": "7:32:47"}
|
| 68 |
+
{"current_steps": 68, "total_steps": 480, "loss": 1.2901, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.28, "percentage": 14.17, "elapsed_time": "1:14:32", "remaining_time": "7:31:41"}
|
| 69 |
+
{"current_steps": 69, "total_steps": 480, "loss": 1.2749, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.29, "percentage": 14.37, "elapsed_time": "1:15:38", "remaining_time": "7:30:31"}
|
| 70 |
+
{"current_steps": 70, "total_steps": 480, "loss": 1.33, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.29, "percentage": 14.58, "elapsed_time": "1:16:44", "remaining_time": "7:29:26"}
|
| 71 |
+
{"current_steps": 71, "total_steps": 480, "loss": 1.3084, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.29, "percentage": 14.79, "elapsed_time": "1:17:48", "remaining_time": "7:28:11"}
|
| 72 |
+
{"current_steps": 72, "total_steps": 480, "loss": 1.277, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.3, "percentage": 15.0, "elapsed_time": "1:18:52", "remaining_time": "7:26:58"}
|
| 73 |
+
{"current_steps": 73, "total_steps": 480, "loss": 1.3586, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.3, "percentage": 15.21, "elapsed_time": "1:19:57", "remaining_time": "7:25:49"}
|
| 74 |
+
{"current_steps": 74, "total_steps": 480, "loss": 1.2959, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.31, "percentage": 15.42, "elapsed_time": "1:21:03", "remaining_time": "7:24:43"}
|
| 75 |
+
{"current_steps": 75, "total_steps": 480, "loss": 1.2957, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.31, "percentage": 15.62, "elapsed_time": "1:22:08", "remaining_time": "7:23:31"}
|
| 76 |
+
{"current_steps": 76, "total_steps": 480, "loss": 1.3278, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.32, "percentage": 15.83, "elapsed_time": "1:23:12", "remaining_time": "7:22:18"}
|
| 77 |
+
{"current_steps": 77, "total_steps": 480, "loss": 1.2633, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.32, "percentage": 16.04, "elapsed_time": "1:24:16", "remaining_time": "7:21:03"}
|
| 78 |
+
{"current_steps": 78, "total_steps": 480, "loss": 1.2808, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.32, "percentage": 16.25, "elapsed_time": "1:25:21", "remaining_time": "7:19:55"}
|
| 79 |
+
{"current_steps": 79, "total_steps": 480, "loss": 1.2664, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.33, "percentage": 16.46, "elapsed_time": "1:26:26", "remaining_time": "7:18:47"}
|
| 80 |
+
{"current_steps": 80, "total_steps": 480, "loss": 1.2969, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.33, "percentage": 16.67, "elapsed_time": "1:27:32", "remaining_time": "7:17:42"}
|
| 81 |
+
{"current_steps": 81, "total_steps": 480, "loss": 1.2982, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.34, "percentage": 16.88, "elapsed_time": "1:28:36", "remaining_time": "7:16:29"}
|
| 82 |
+
{"current_steps": 82, "total_steps": 480, "loss": 1.2784, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.34, "percentage": 17.08, "elapsed_time": "1:29:41", "remaining_time": "7:15:18"}
|
| 83 |
+
{"current_steps": 83, "total_steps": 480, "loss": 1.2819, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.34, "percentage": 17.29, "elapsed_time": "1:30:45", "remaining_time": "7:14:07"}
|
| 84 |
+
{"current_steps": 84, "total_steps": 480, "loss": 1.311, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.35, "percentage": 17.5, "elapsed_time": "1:31:51", "remaining_time": "7:13:03"}
|
| 85 |
+
{"current_steps": 85, "total_steps": 480, "loss": 1.2561, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.35, "percentage": 17.71, "elapsed_time": "1:32:56", "remaining_time": "7:11:54"}
|
| 86 |
+
{"current_steps": 86, "total_steps": 480, "loss": 1.2731, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.36, "percentage": 17.92, "elapsed_time": "1:34:00", "remaining_time": "7:10:41"}
|
| 87 |
+
{"current_steps": 87, "total_steps": 480, "loss": 1.2822, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.36, "percentage": 18.12, "elapsed_time": "1:35:05", "remaining_time": "7:09:35"}
|
| 88 |
+
{"current_steps": 88, "total_steps": 480, "loss": 1.2447, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.37, "percentage": 18.33, "elapsed_time": "1:36:10", "remaining_time": "7:08:25"}
|
| 89 |
+
{"current_steps": 89, "total_steps": 480, "loss": 1.2786, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.37, "percentage": 18.54, "elapsed_time": "1:37:14", "remaining_time": "7:07:14"}
|
| 90 |
+
{"current_steps": 90, "total_steps": 480, "loss": 1.3479, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.37, "percentage": 18.75, "elapsed_time": "1:38:19", "remaining_time": "7:06:02"}
|
| 91 |
+
{"current_steps": 91, "total_steps": 480, "loss": 1.2794, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.38, "percentage": 18.96, "elapsed_time": "1:39:24", "remaining_time": "7:04:58"}
|
| 92 |
+
{"current_steps": 92, "total_steps": 480, "loss": 1.3131, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.38, "percentage": 19.17, "elapsed_time": "1:40:29", "remaining_time": "7:03:49"}
|
| 93 |
+
{"current_steps": 93, "total_steps": 480, "loss": 1.2458, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.39, "percentage": 19.38, "elapsed_time": "1:41:35", "remaining_time": "7:02:45"}
|
| 94 |
+
{"current_steps": 94, "total_steps": 480, "loss": 1.2614, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.39, "percentage": 19.58, "elapsed_time": "1:42:40", "remaining_time": "7:01:37"}
|
| 95 |
+
{"current_steps": 95, "total_steps": 480, "loss": 1.2399, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.39, "percentage": 19.79, "elapsed_time": "1:43:45", "remaining_time": "7:00:30"}
|
| 96 |
+
{"current_steps": 96, "total_steps": 480, "loss": 1.3144, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.4, "percentage": 20.0, "elapsed_time": "1:44:49", "remaining_time": "6:59:17"}
|
| 97 |
+
{"current_steps": 97, "total_steps": 480, "loss": 1.2324, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.4, "percentage": 20.21, "elapsed_time": "1:45:54", "remaining_time": "6:58:09"}
|
| 98 |
+
{"current_steps": 98, "total_steps": 480, "loss": 1.2719, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.41, "percentage": 20.42, "elapsed_time": "1:46:59", "remaining_time": "6:57:04"}
|
| 99 |
+
{"current_steps": 99, "total_steps": 480, "loss": 1.2622, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.41, "percentage": 20.62, "elapsed_time": "1:48:05", "remaining_time": "6:56:00"}
|
| 100 |
+
{"current_steps": 100, "total_steps": 480, "loss": 1.2776, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.42, "percentage": 20.83, "elapsed_time": "1:49:11", "remaining_time": "6:54:55"}
|
| 101 |
+
{"current_steps": 101, "total_steps": 480, "loss": 1.2808, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.42, "percentage": 21.04, "elapsed_time": "1:51:09", "remaining_time": "6:57:07"}
|
| 102 |
+
{"current_steps": 102, "total_steps": 480, "loss": 1.3073, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.42, "percentage": 21.25, "elapsed_time": "1:52:14", "remaining_time": "6:55:57"}
|
| 103 |
+
{"current_steps": 103, "total_steps": 480, "loss": 1.2182, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.43, "percentage": 21.46, "elapsed_time": "1:53:19", "remaining_time": "6:54:47"}
|
| 104 |
+
{"current_steps": 104, "total_steps": 480, "loss": 1.3265, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.43, "percentage": 21.67, "elapsed_time": "1:54:23", "remaining_time": "6:53:35"}
|
| 105 |
+
{"current_steps": 105, "total_steps": 480, "loss": 1.2228, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.44, "percentage": 21.88, "elapsed_time": "1:55:29", "remaining_time": "6:52:27"}
|
| 106 |
+
{"current_steps": 106, "total_steps": 480, "loss": 1.2843, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.44, "percentage": 22.08, "elapsed_time": "1:56:34", "remaining_time": "6:51:18"}
|
| 107 |
+
{"current_steps": 107, "total_steps": 480, "loss": 1.2789, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.44, "percentage": 22.29, "elapsed_time": "1:57:39", "remaining_time": "6:50:08"}
|
| 108 |
+
{"current_steps": 108, "total_steps": 480, "loss": 1.2407, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.45, "percentage": 22.5, "elapsed_time": "1:58:44", "remaining_time": "6:48:58"}
|
| 109 |
+
{"current_steps": 109, "total_steps": 480, "loss": 1.3537, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.45, "percentage": 22.71, "elapsed_time": "1:59:49", "remaining_time": "6:47:51"}
|
| 110 |
+
{"current_steps": 110, "total_steps": 480, "loss": 1.299, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.46, "percentage": 22.92, "elapsed_time": "2:00:54", "remaining_time": "6:46:41"}
|
| 111 |
+
{"current_steps": 111, "total_steps": 480, "loss": 1.3407, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.46, "percentage": 23.12, "elapsed_time": "2:01:59", "remaining_time": "6:45:33"}
|
| 112 |
+
{"current_steps": 112, "total_steps": 480, "loss": 1.2837, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.47, "percentage": 23.33, "elapsed_time": "2:03:05", "remaining_time": "6:44:25"}
|
| 113 |
+
{"current_steps": 113, "total_steps": 480, "loss": 1.2408, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.47, "percentage": 23.54, "elapsed_time": "2:04:10", "remaining_time": "6:43:18"}
|
| 114 |
+
{"current_steps": 114, "total_steps": 480, "loss": 1.2552, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.47, "percentage": 23.75, "elapsed_time": "2:05:15", "remaining_time": "6:42:09"}
|
| 115 |
+
{"current_steps": 115, "total_steps": 480, "loss": 1.3157, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.48, "percentage": 23.96, "elapsed_time": "2:06:20", "remaining_time": "6:40:59"}
|
| 116 |
+
{"current_steps": 116, "total_steps": 480, "loss": 1.3123, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.48, "percentage": 24.17, "elapsed_time": "2:07:24", "remaining_time": "6:39:48"}
|
| 117 |
+
{"current_steps": 117, "total_steps": 480, "loss": 1.2701, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.49, "percentage": 24.38, "elapsed_time": "2:08:30", "remaining_time": "6:38:40"}
|
| 118 |
+
{"current_steps": 118, "total_steps": 480, "loss": 1.2983, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.49, "percentage": 24.58, "elapsed_time": "2:09:34", "remaining_time": "6:37:31"}
|
| 119 |
+
{"current_steps": 119, "total_steps": 480, "loss": 1.3216, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.49, "percentage": 24.79, "elapsed_time": "2:10:39", "remaining_time": "6:36:23"}
|
| 120 |
+
{"current_steps": 120, "total_steps": 480, "loss": 1.3005, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.5, "percentage": 25.0, "elapsed_time": "2:11:44", "remaining_time": "6:35:14"}
|
| 121 |
+
{"current_steps": 121, "total_steps": 480, "loss": 1.3233, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.5, "percentage": 25.21, "elapsed_time": "2:12:49", "remaining_time": "6:34:05"}
|
| 122 |
+
{"current_steps": 122, "total_steps": 480, "loss": 1.3054, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.51, "percentage": 25.42, "elapsed_time": "2:13:55", "remaining_time": "6:32:58"}
|
| 123 |
+
{"current_steps": 123, "total_steps": 480, "loss": 1.2471, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.51, "percentage": 25.62, "elapsed_time": "2:15:02", "remaining_time": "6:31:56"}
|
| 124 |
+
{"current_steps": 124, "total_steps": 480, "loss": 1.3104, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.52, "percentage": 25.83, "elapsed_time": "2:16:07", "remaining_time": "6:30:48"}
|
| 125 |
+
{"current_steps": 125, "total_steps": 480, "loss": 1.2492, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.52, "percentage": 26.04, "elapsed_time": "2:17:12", "remaining_time": "6:29:41"}
|
| 126 |
+
{"current_steps": 126, "total_steps": 480, "loss": 1.2466, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.52, "percentage": 26.25, "elapsed_time": "2:18:17", "remaining_time": "6:28:31"}
|
| 127 |
+
{"current_steps": 127, "total_steps": 480, "loss": 1.3047, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.53, "percentage": 26.46, "elapsed_time": "2:19:22", "remaining_time": "6:27:23"}
|
| 128 |
+
{"current_steps": 128, "total_steps": 480, "loss": 1.2054, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.53, "percentage": 26.67, "elapsed_time": "2:20:27", "remaining_time": "6:26:16"}
|
| 129 |
+
{"current_steps": 129, "total_steps": 480, "loss": 1.2655, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.54, "percentage": 26.88, "elapsed_time": "2:21:32", "remaining_time": "6:25:08"}
|
| 130 |
+
{"current_steps": 130, "total_steps": 480, "loss": 1.2382, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.54, "percentage": 27.08, "elapsed_time": "2:22:37", "remaining_time": "6:23:58"}
|
| 131 |
+
{"current_steps": 131, "total_steps": 480, "loss": 1.3278, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.54, "percentage": 27.29, "elapsed_time": "2:23:42", "remaining_time": "6:22:52"}
|
| 132 |
+
{"current_steps": 132, "total_steps": 480, "loss": 1.3138, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.55, "percentage": 27.5, "elapsed_time": "2:24:47", "remaining_time": "6:21:44"}
|
| 133 |
+
{"current_steps": 133, "total_steps": 480, "loss": 1.3109, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.55, "percentage": 27.71, "elapsed_time": "2:25:52", "remaining_time": "6:20:35"}
|
| 134 |
+
{"current_steps": 134, "total_steps": 480, "loss": 1.2985, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.56, "percentage": 27.92, "elapsed_time": "2:26:57", "remaining_time": "6:19:26"}
|
| 135 |
+
{"current_steps": 135, "total_steps": 480, "loss": 1.2468, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.56, "percentage": 28.12, "elapsed_time": "2:28:02", "remaining_time": "6:18:18"}
|
| 136 |
+
{"current_steps": 136, "total_steps": 480, "loss": 1.3445, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.56, "percentage": 28.33, "elapsed_time": "2:29:06", "remaining_time": "6:17:10"}
|
| 137 |
+
{"current_steps": 137, "total_steps": 480, "loss": 1.2921, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.57, "percentage": 28.54, "elapsed_time": "2:30:11", "remaining_time": "6:16:01"}
|
| 138 |
+
{"current_steps": 138, "total_steps": 480, "loss": 1.3327, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.57, "percentage": 28.75, "elapsed_time": "2:31:16", "remaining_time": "6:14:52"}
|
| 139 |
+
{"current_steps": 139, "total_steps": 480, "loss": 1.3017, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.58, "percentage": 28.96, "elapsed_time": "2:32:21", "remaining_time": "6:13:46"}
|
| 140 |
+
{"current_steps": 140, "total_steps": 480, "loss": 1.3248, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.58, "percentage": 29.17, "elapsed_time": "2:33:26", "remaining_time": "6:12:38"}
|
| 141 |
+
{"current_steps": 141, "total_steps": 480, "loss": 1.3478, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.59, "percentage": 29.38, "elapsed_time": "2:34:31", "remaining_time": "6:11:31"}
|
| 142 |
+
{"current_steps": 142, "total_steps": 480, "loss": 1.2547, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.59, "percentage": 29.58, "elapsed_time": "2:35:37", "remaining_time": "6:10:25"}
|
| 143 |
+
{"current_steps": 143, "total_steps": 480, "loss": 1.2809, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.59, "percentage": 29.79, "elapsed_time": "2:36:42", "remaining_time": "6:09:19"}
|
| 144 |
+
{"current_steps": 144, "total_steps": 480, "loss": 1.2585, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.6, "percentage": 30.0, "elapsed_time": "2:37:47", "remaining_time": "6:08:11"}
|
| 145 |
+
{"current_steps": 145, "total_steps": 480, "loss": 1.316, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.6, "percentage": 30.21, "elapsed_time": "2:38:53", "remaining_time": "6:07:04"}
|
| 146 |
+
{"current_steps": 146, "total_steps": 480, "loss": 1.3576, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.61, "percentage": 30.42, "elapsed_time": "2:39:58", "remaining_time": "6:05:59"}
|
| 147 |
+
{"current_steps": 147, "total_steps": 480, "loss": 1.2939, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.61, "percentage": 30.63, "elapsed_time": "2:41:03", "remaining_time": "6:04:51"}
|
| 148 |
+
{"current_steps": 148, "total_steps": 480, "loss": 1.3307, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.61, "percentage": 30.83, "elapsed_time": "2:42:08", "remaining_time": "6:03:42"}
|
| 149 |
+
{"current_steps": 149, "total_steps": 480, "loss": 1.3118, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.62, "percentage": 31.04, "elapsed_time": "2:43:12", "remaining_time": "6:02:33"}
|
| 150 |
+
{"current_steps": 150, "total_steps": 480, "loss": 1.2836, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.62, "percentage": 31.25, "elapsed_time": "2:44:16", "remaining_time": "6:01:24"}
|
| 151 |
+
{"current_steps": 151, "total_steps": 480, "loss": 1.274, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.63, "percentage": 31.46, "elapsed_time": "2:46:10", "remaining_time": "6:02:02"}
|
| 152 |
+
{"current_steps": 152, "total_steps": 480, "loss": 1.2447, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.63, "percentage": 31.67, "elapsed_time": "2:47:14", "remaining_time": "6:00:54"}
|
| 153 |
+
{"current_steps": 153, "total_steps": 480, "loss": 1.2743, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.64, "percentage": 31.87, "elapsed_time": "2:48:19", "remaining_time": "5:59:45"}
|
| 154 |
+
{"current_steps": 154, "total_steps": 480, "loss": 1.2351, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.64, "percentage": 32.08, "elapsed_time": "2:49:30", "remaining_time": "5:58:49"}
|
| 155 |
+
{"current_steps": 155, "total_steps": 480, "loss": 1.2584, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.64, "percentage": 32.29, "elapsed_time": "2:50:34", "remaining_time": "5:57:40"}
|
| 156 |
+
{"current_steps": 156, "total_steps": 480, "loss": 1.2281, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.65, "percentage": 32.5, "elapsed_time": "2:51:39", "remaining_time": "5:56:30"}
|
| 157 |
+
{"current_steps": 157, "total_steps": 480, "loss": 1.2922, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.65, "percentage": 32.71, "elapsed_time": "2:52:43", "remaining_time": "5:55:21"}
|
| 158 |
+
{"current_steps": 158, "total_steps": 480, "loss": 1.2589, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.66, "percentage": 32.92, "elapsed_time": "2:53:48", "remaining_time": "5:54:12"}
|
| 159 |
+
{"current_steps": 159, "total_steps": 480, "loss": 1.3146, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.66, "percentage": 33.12, "elapsed_time": "2:54:52", "remaining_time": "5:53:03"}
|
| 160 |
+
{"current_steps": 160, "total_steps": 480, "loss": 1.2896, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.66, "percentage": 33.33, "elapsed_time": "2:55:57", "remaining_time": "5:51:54"}
|
| 161 |
+
{"current_steps": 161, "total_steps": 480, "loss": 1.2661, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.67, "percentage": 33.54, "elapsed_time": "2:57:02", "remaining_time": "5:50:46"}
|
| 162 |
+
{"current_steps": 162, "total_steps": 480, "loss": 1.2296, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.67, "percentage": 33.75, "elapsed_time": "2:58:07", "remaining_time": "5:49:38"}
|
| 163 |
+
{"current_steps": 163, "total_steps": 480, "loss": 1.3146, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.68, "percentage": 33.96, "elapsed_time": "2:59:11", "remaining_time": "5:48:29"}
|
| 164 |
+
{"current_steps": 164, "total_steps": 480, "loss": 1.2445, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.68, "percentage": 34.17, "elapsed_time": "3:00:15", "remaining_time": "5:47:20"}
|
| 165 |
+
{"current_steps": 165, "total_steps": 480, "loss": 1.2828, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.69, "percentage": 34.38, "elapsed_time": "3:01:20", "remaining_time": "5:46:12"}
|
| 166 |
+
{"current_steps": 166, "total_steps": 480, "loss": 1.2226, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.69, "percentage": 34.58, "elapsed_time": "3:02:26", "remaining_time": "5:45:05"}
|
| 167 |
+
{"current_steps": 167, "total_steps": 480, "loss": 1.3279, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.69, "percentage": 34.79, "elapsed_time": "3:03:31", "remaining_time": "5:43:59"}
|
| 168 |
+
{"current_steps": 168, "total_steps": 480, "loss": 1.3052, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.7, "percentage": 35.0, "elapsed_time": "3:04:36", "remaining_time": "5:42:51"}
|
| 169 |
+
{"current_steps": 169, "total_steps": 480, "loss": 1.2751, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.7, "percentage": 35.21, "elapsed_time": "3:05:40", "remaining_time": "5:41:42"}
|
| 170 |
+
{"current_steps": 170, "total_steps": 480, "loss": 1.2712, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.71, "percentage": 35.42, "elapsed_time": "3:06:45", "remaining_time": "5:40:33"}
|
| 171 |
+
{"current_steps": 171, "total_steps": 480, "loss": 1.2478, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.71, "percentage": 35.62, "elapsed_time": "3:07:50", "remaining_time": "5:39:26"}
|
| 172 |
+
{"current_steps": 172, "total_steps": 480, "loss": 1.2832, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.71, "percentage": 35.83, "elapsed_time": "3:08:55", "remaining_time": "5:38:19"}
|
| 173 |
+
{"current_steps": 173, "total_steps": 480, "loss": 1.3105, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.72, "percentage": 36.04, "elapsed_time": "3:10:01", "remaining_time": "5:37:11"}
|
| 174 |
+
{"current_steps": 174, "total_steps": 480, "loss": 1.2882, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.72, "percentage": 36.25, "elapsed_time": "3:11:05", "remaining_time": "5:36:03"}
|
| 175 |
+
{"current_steps": 175, "total_steps": 480, "loss": 1.3134, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.73, "percentage": 36.46, "elapsed_time": "3:12:09", "remaining_time": "5:34:53"}
|
| 176 |
+
{"current_steps": 176, "total_steps": 480, "loss": 1.3416, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.73, "percentage": 36.67, "elapsed_time": "3:13:14", "remaining_time": "5:33:46"}
|
| 177 |
+
{"current_steps": 177, "total_steps": 480, "loss": 1.2528, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.74, "percentage": 36.88, "elapsed_time": "3:14:18", "remaining_time": "5:32:37"}
|
| 178 |
+
{"current_steps": 178, "total_steps": 480, "loss": 1.2146, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.74, "percentage": 37.08, "elapsed_time": "3:15:23", "remaining_time": "5:31:30"}
|
| 179 |
+
{"current_steps": 179, "total_steps": 480, "loss": 1.2165, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.74, "percentage": 37.29, "elapsed_time": "3:16:28", "remaining_time": "5:30:23"}
|
| 180 |
+
{"current_steps": 180, "total_steps": 480, "loss": 1.3034, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.75, "percentage": 37.5, "elapsed_time": "3:17:33", "remaining_time": "5:29:16"}
|
| 181 |
+
{"current_steps": 181, "total_steps": 480, "loss": 1.2462, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.75, "percentage": 37.71, "elapsed_time": "3:18:39", "remaining_time": "5:28:09"}
|
| 182 |
+
{"current_steps": 182, "total_steps": 480, "loss": 1.2508, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.76, "percentage": 37.92, "elapsed_time": "3:19:43", "remaining_time": "5:27:01"}
|
| 183 |
+
{"current_steps": 183, "total_steps": 480, "loss": 1.2617, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.76, "percentage": 38.12, "elapsed_time": "3:20:48", "remaining_time": "5:25:54"}
|
| 184 |
+
{"current_steps": 184, "total_steps": 480, "loss": 1.2694, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.76, "percentage": 38.33, "elapsed_time": "3:21:54", "remaining_time": "5:24:47"}
|
| 185 |
+
{"current_steps": 185, "total_steps": 480, "loss": 1.2521, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.77, "percentage": 38.54, "elapsed_time": "3:22:58", "remaining_time": "5:23:39"}
|
| 186 |
+
{"current_steps": 186, "total_steps": 480, "loss": 1.2583, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.77, "percentage": 38.75, "elapsed_time": "3:24:03", "remaining_time": "5:22:33"}
|
| 187 |
+
{"current_steps": 187, "total_steps": 480, "loss": 1.2689, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.78, "percentage": 38.96, "elapsed_time": "3:25:08", "remaining_time": "5:21:24"}
|
| 188 |
+
{"current_steps": 188, "total_steps": 480, "loss": 1.3264, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.78, "percentage": 39.17, "elapsed_time": "3:26:13", "remaining_time": "5:20:18"}
|
| 189 |
+
{"current_steps": 189, "total_steps": 480, "loss": 1.2509, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.79, "percentage": 39.38, "elapsed_time": "3:27:18", "remaining_time": "5:19:11"}
|
| 190 |
+
{"current_steps": 190, "total_steps": 480, "loss": 1.2791, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.79, "percentage": 39.58, "elapsed_time": "3:28:24", "remaining_time": "5:18:05"}
|
| 191 |
+
{"current_steps": 191, "total_steps": 480, "loss": 1.3058, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.79, "percentage": 39.79, "elapsed_time": "3:29:28", "remaining_time": "5:16:57"}
|
| 192 |
+
{"current_steps": 192, "total_steps": 480, "loss": 1.298, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.8, "percentage": 40.0, "elapsed_time": "3:30:33", "remaining_time": "5:15:49"}
|
| 193 |
+
{"current_steps": 193, "total_steps": 480, "loss": 1.2822, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.8, "percentage": 40.21, "elapsed_time": "3:31:38", "remaining_time": "5:14:43"}
|
| 194 |
+
{"current_steps": 194, "total_steps": 480, "loss": 1.2952, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.81, "percentage": 40.42, "elapsed_time": "3:32:43", "remaining_time": "5:13:36"}
|
| 195 |
+
{"current_steps": 195, "total_steps": 480, "loss": 1.2916, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.81, "percentage": 40.62, "elapsed_time": "3:33:49", "remaining_time": "5:12:30"}
|
| 196 |
+
{"current_steps": 196, "total_steps": 480, "loss": 1.286, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.81, "percentage": 40.83, "elapsed_time": "3:34:54", "remaining_time": "5:11:23"}
|
| 197 |
+
{"current_steps": 197, "total_steps": 480, "loss": 1.3168, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.82, "percentage": 41.04, "elapsed_time": "3:35:59", "remaining_time": "5:10:16"}
|
| 198 |
+
{"current_steps": 198, "total_steps": 480, "loss": 1.222, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.82, "percentage": 41.25, "elapsed_time": "3:37:04", "remaining_time": "5:09:09"}
|
| 199 |
+
{"current_steps": 199, "total_steps": 480, "loss": 1.2868, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.83, "percentage": 41.46, "elapsed_time": "3:38:09", "remaining_time": "5:08:02"}
|
| 200 |
+
{"current_steps": 200, "total_steps": 480, "loss": 1.2546, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.83, "percentage": 41.67, "elapsed_time": "3:39:13", "remaining_time": "5:06:55"}
|
| 201 |
+
{"current_steps": 201, "total_steps": 480, "loss": 1.3313, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.83, "percentage": 41.88, "elapsed_time": "3:41:12", "remaining_time": "5:07:02"}
|
| 202 |
+
{"current_steps": 202, "total_steps": 480, "loss": 1.2183, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.84, "percentage": 42.08, "elapsed_time": "3:42:16", "remaining_time": "5:05:54"}
|
| 203 |
+
{"current_steps": 203, "total_steps": 480, "loss": 1.2943, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.84, "percentage": 42.29, "elapsed_time": "3:43:21", "remaining_time": "5:04:46"}
|
| 204 |
+
{"current_steps": 204, "total_steps": 480, "loss": 1.2398, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.85, "percentage": 42.5, "elapsed_time": "3:44:26", "remaining_time": "5:03:38"}
|
| 205 |
+
{"current_steps": 205, "total_steps": 480, "loss": 1.2804, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.85, "percentage": 42.71, "elapsed_time": "3:45:30", "remaining_time": "5:02:31"}
|
| 206 |
+
{"current_steps": 206, "total_steps": 480, "loss": 1.3344, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.86, "percentage": 42.92, "elapsed_time": "3:46:35", "remaining_time": "5:01:23"}
|
| 207 |
+
{"current_steps": 207, "total_steps": 480, "loss": 1.2351, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.86, "percentage": 43.12, "elapsed_time": "3:47:41", "remaining_time": "5:00:16"}
|
| 208 |
+
{"current_steps": 208, "total_steps": 480, "loss": 1.2385, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.86, "percentage": 43.33, "elapsed_time": "3:48:46", "remaining_time": "4:59:09"}
|
| 209 |
+
{"current_steps": 209, "total_steps": 480, "loss": 1.2263, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.87, "percentage": 43.54, "elapsed_time": "3:49:50", "remaining_time": "4:58:01"}
|
| 210 |
+
{"current_steps": 210, "total_steps": 480, "loss": 1.2931, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.87, "percentage": 43.75, "elapsed_time": "3:50:55", "remaining_time": "4:56:53"}
|
| 211 |
+
{"current_steps": 211, "total_steps": 480, "loss": 1.3084, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.88, "percentage": 43.96, "elapsed_time": "3:51:59", "remaining_time": "4:55:46"}
|
| 212 |
+
{"current_steps": 212, "total_steps": 480, "loss": 1.3348, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.88, "percentage": 44.17, "elapsed_time": "3:53:04", "remaining_time": "4:54:38"}
|
| 213 |
+
{"current_steps": 213, "total_steps": 480, "loss": 1.2726, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.88, "percentage": 44.38, "elapsed_time": "3:54:09", "remaining_time": "4:53:31"}
|
| 214 |
+
{"current_steps": 214, "total_steps": 480, "loss": 1.266, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.89, "percentage": 44.58, "elapsed_time": "3:55:14", "remaining_time": "4:52:24"}
|
| 215 |
+
{"current_steps": 215, "total_steps": 480, "loss": 1.2275, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.89, "percentage": 44.79, "elapsed_time": "3:56:19", "remaining_time": "4:51:16"}
|
| 216 |
+
{"current_steps": 216, "total_steps": 480, "loss": 1.166, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.9, "percentage": 45.0, "elapsed_time": "3:57:24", "remaining_time": "4:50:09"}
|
| 217 |
+
{"current_steps": 217, "total_steps": 480, "loss": 1.3315, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.9, "percentage": 45.21, "elapsed_time": "3:58:29", "remaining_time": "4:49:02"}
|
| 218 |
+
{"current_steps": 218, "total_steps": 480, "loss": 1.2339, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.91, "percentage": 45.42, "elapsed_time": "3:59:36", "remaining_time": "4:47:57"}
|
| 219 |
+
{"current_steps": 219, "total_steps": 480, "loss": 1.2884, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.91, "percentage": 45.62, "elapsed_time": "4:00:40", "remaining_time": "4:46:50"}
|
| 220 |
+
{"current_steps": 220, "total_steps": 480, "loss": 1.1792, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.91, "percentage": 45.83, "elapsed_time": "4:01:46", "remaining_time": "4:45:43"}
|
| 221 |
+
{"current_steps": 221, "total_steps": 480, "loss": 1.2511, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.92, "percentage": 46.04, "elapsed_time": "4:02:51", "remaining_time": "4:44:36"}
|
| 222 |
+
{"current_steps": 222, "total_steps": 480, "loss": 1.2653, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.92, "percentage": 46.25, "elapsed_time": "4:03:56", "remaining_time": "4:43:30"}
|
| 223 |
+
{"current_steps": 223, "total_steps": 480, "loss": 1.3067, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.93, "percentage": 46.46, "elapsed_time": "4:05:01", "remaining_time": "4:42:22"}
|
| 224 |
+
{"current_steps": 224, "total_steps": 480, "loss": 1.1765, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.93, "percentage": 46.67, "elapsed_time": "4:06:06", "remaining_time": "4:41:15"}
|
| 225 |
+
{"current_steps": 225, "total_steps": 480, "loss": 1.2627, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.93, "percentage": 46.88, "elapsed_time": "4:07:11", "remaining_time": "4:40:08"}
|
| 226 |
+
{"current_steps": 226, "total_steps": 480, "loss": 1.2726, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.94, "percentage": 47.08, "elapsed_time": "4:08:15", "remaining_time": "4:39:00"}
|
| 227 |
+
{"current_steps": 227, "total_steps": 480, "loss": 1.2062, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.94, "percentage": 47.29, "elapsed_time": "4:09:20", "remaining_time": "4:37:54"}
|
| 228 |
+
{"current_steps": 228, "total_steps": 480, "loss": 1.2472, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.95, "percentage": 47.5, "elapsed_time": "4:10:24", "remaining_time": "4:36:46"}
|
| 229 |
+
{"current_steps": 229, "total_steps": 480, "loss": 1.2648, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.95, "percentage": 47.71, "elapsed_time": "4:11:29", "remaining_time": "4:35:39"}
|
| 230 |
+
{"current_steps": 230, "total_steps": 480, "loss": 1.3097, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.96, "percentage": 47.92, "elapsed_time": "4:12:34", "remaining_time": "4:34:32"}
|
| 231 |
+
{"current_steps": 231, "total_steps": 480, "loss": 1.2462, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.96, "percentage": 48.12, "elapsed_time": "4:13:39", "remaining_time": "4:33:25"}
|
| 232 |
+
{"current_steps": 232, "total_steps": 480, "loss": 1.2852, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.96, "percentage": 48.33, "elapsed_time": "4:14:44", "remaining_time": "4:32:18"}
|
| 233 |
+
{"current_steps": 233, "total_steps": 480, "loss": 1.2879, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.97, "percentage": 48.54, "elapsed_time": "4:15:49", "remaining_time": "4:31:11"}
|
| 234 |
+
{"current_steps": 234, "total_steps": 480, "loss": 1.2475, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.97, "percentage": 48.75, "elapsed_time": "4:16:54", "remaining_time": "4:30:05"}
|
| 235 |
+
{"current_steps": 235, "total_steps": 480, "loss": 1.3275, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.98, "percentage": 48.96, "elapsed_time": "4:17:59", "remaining_time": "4:28:58"}
|
| 236 |
+
{"current_steps": 236, "total_steps": 480, "loss": 1.2307, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.98, "percentage": 49.17, "elapsed_time": "4:19:04", "remaining_time": "4:27:51"}
|
| 237 |
+
{"current_steps": 237, "total_steps": 480, "loss": 1.2575, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.98, "percentage": 49.38, "elapsed_time": "4:20:09", "remaining_time": "4:26:44"}
|
| 238 |
+
{"current_steps": 238, "total_steps": 480, "loss": 1.2906, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.99, "percentage": 49.58, "elapsed_time": "4:21:15", "remaining_time": "4:25:38"}
|
| 239 |
+
{"current_steps": 239, "total_steps": 480, "loss": 1.2758, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.99, "percentage": 49.79, "elapsed_time": "4:22:20", "remaining_time": "4:24:32"}
|
| 240 |
+
{"current_steps": 240, "total_steps": 480, "loss": 1.2972, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "4:23:25", "remaining_time": "4:23:25"}
|
| 241 |
+
{"current_steps": 241, "total_steps": 480, "loss": 1.23, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.0, "percentage": 50.21, "elapsed_time": "4:24:31", "remaining_time": "4:22:19"}
|
| 242 |
+
{"current_steps": 242, "total_steps": 480, "loss": 1.2082, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.01, "percentage": 50.42, "elapsed_time": "4:25:36", "remaining_time": "4:21:13"}
|
| 243 |
+
{"current_steps": 243, "total_steps": 480, "loss": 1.2185, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.01, "percentage": 50.62, "elapsed_time": "4:26:41", "remaining_time": "4:20:06"}
|
| 244 |
+
{"current_steps": 244, "total_steps": 480, "loss": 1.3149, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.01, "percentage": 50.83, "elapsed_time": "4:27:46", "remaining_time": "4:18:59"}
|
| 245 |
+
{"current_steps": 245, "total_steps": 480, "loss": 1.2845, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.02, "percentage": 51.04, "elapsed_time": "4:28:51", "remaining_time": "4:17:53"}
|
| 246 |
+
{"current_steps": 246, "total_steps": 480, "loss": 1.2585, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.02, "percentage": 51.25, "elapsed_time": "4:29:56", "remaining_time": "4:16:46"}
|
| 247 |
+
{"current_steps": 247, "total_steps": 480, "loss": 1.2693, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.03, "percentage": 51.46, "elapsed_time": "4:31:01", "remaining_time": "4:15:40"}
|
| 248 |
+
{"current_steps": 248, "total_steps": 480, "loss": 1.2811, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.03, "percentage": 51.67, "elapsed_time": "4:32:06", "remaining_time": "4:14:33"}
|
| 249 |
+
{"current_steps": 249, "total_steps": 480, "loss": 1.3358, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.03, "percentage": 51.88, "elapsed_time": "4:33:11", "remaining_time": "4:13:26"}
|
| 250 |
+
{"current_steps": 250, "total_steps": 480, "loss": 1.2107, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.04, "percentage": 52.08, "elapsed_time": "4:34:17", "remaining_time": "4:12:21"}
|
| 251 |
+
{"current_steps": 251, "total_steps": 480, "loss": 1.2893, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.04, "percentage": 52.29, "elapsed_time": "4:36:16", "remaining_time": "4:12:03"}
|
| 252 |
+
{"current_steps": 252, "total_steps": 480, "loss": 1.2611, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.05, "percentage": 52.5, "elapsed_time": "4:37:20", "remaining_time": "4:10:55"}
|
| 253 |
+
{"current_steps": 253, "total_steps": 480, "loss": 1.2711, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.05, "percentage": 52.71, "elapsed_time": "4:38:24", "remaining_time": "4:09:48"}
|
| 254 |
+
{"current_steps": 254, "total_steps": 480, "loss": 1.2482, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.06, "percentage": 52.92, "elapsed_time": "4:39:29", "remaining_time": "4:08:40"}
|
| 255 |
+
{"current_steps": 255, "total_steps": 480, "loss": 1.2687, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.06, "percentage": 53.12, "elapsed_time": "4:40:34", "remaining_time": "4:07:34"}
|
| 256 |
+
{"current_steps": 256, "total_steps": 480, "loss": 1.2904, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.06, "percentage": 53.33, "elapsed_time": "4:41:40", "remaining_time": "4:06:27"}
|
| 257 |
+
{"current_steps": 257, "total_steps": 480, "loss": 1.2441, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.07, "percentage": 53.54, "elapsed_time": "4:42:45", "remaining_time": "4:05:20"}
|
| 258 |
+
{"current_steps": 258, "total_steps": 480, "loss": 1.2617, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.07, "percentage": 53.75, "elapsed_time": "4:43:50", "remaining_time": "4:04:14"}
|
| 259 |
+
{"current_steps": 259, "total_steps": 480, "loss": 1.2161, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.08, "percentage": 53.96, "elapsed_time": "4:44:55", "remaining_time": "4:03:06"}
|
| 260 |
+
{"current_steps": 260, "total_steps": 480, "loss": 1.2901, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.08, "percentage": 54.17, "elapsed_time": "4:45:59", "remaining_time": "4:01:59"}
|
| 261 |
+
{"current_steps": 261, "total_steps": 480, "loss": 1.2874, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.08, "percentage": 54.37, "elapsed_time": "4:47:05", "remaining_time": "4:00:53"}
|
| 262 |
+
{"current_steps": 262, "total_steps": 480, "loss": 1.2356, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.09, "percentage": 54.58, "elapsed_time": "4:48:10", "remaining_time": "3:59:46"}
|
| 263 |
+
{"current_steps": 263, "total_steps": 480, "loss": 1.236, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.09, "percentage": 54.79, "elapsed_time": "4:49:14", "remaining_time": "3:58:39"}
|
| 264 |
+
{"current_steps": 264, "total_steps": 480, "loss": 1.2421, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.1, "percentage": 55.0, "elapsed_time": "4:50:19", "remaining_time": "3:57:32"}
|
| 265 |
+
{"current_steps": 265, "total_steps": 480, "loss": 1.247, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.1, "percentage": 55.21, "elapsed_time": "4:51:23", "remaining_time": "3:56:24"}
|
| 266 |
+
{"current_steps": 266, "total_steps": 480, "loss": 1.2485, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.1, "percentage": 55.42, "elapsed_time": "4:52:28", "remaining_time": "3:55:18"}
|
| 267 |
+
{"current_steps": 267, "total_steps": 480, "loss": 1.3521, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.11, "percentage": 55.62, "elapsed_time": "4:53:33", "remaining_time": "3:54:11"}
|
| 268 |
+
{"current_steps": 268, "total_steps": 480, "loss": 1.3147, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.11, "percentage": 55.83, "elapsed_time": "4:54:38", "remaining_time": "3:53:04"}
|
| 269 |
+
{"current_steps": 269, "total_steps": 480, "loss": 1.2557, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.12, "percentage": 56.04, "elapsed_time": "4:55:44", "remaining_time": "3:51:58"}
|
| 270 |
+
{"current_steps": 270, "total_steps": 480, "loss": 1.217, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.12, "percentage": 56.25, "elapsed_time": "4:56:49", "remaining_time": "3:50:52"}
|
| 271 |
+
{"current_steps": 271, "total_steps": 480, "loss": 1.2644, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.13, "percentage": 56.46, "elapsed_time": "4:57:55", "remaining_time": "3:49:45"}
|
| 272 |
+
{"current_steps": 272, "total_steps": 480, "loss": 1.3565, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.13, "percentage": 56.67, "elapsed_time": "4:58:59", "remaining_time": "3:48:38"}
|
| 273 |
+
{"current_steps": 273, "total_steps": 480, "loss": 1.2218, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.13, "percentage": 56.88, "elapsed_time": "5:00:03", "remaining_time": "3:47:31"}
|
| 274 |
+
{"current_steps": 274, "total_steps": 480, "loss": 1.3112, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.14, "percentage": 57.08, "elapsed_time": "5:01:08", "remaining_time": "3:46:24"}
|
| 275 |
+
{"current_steps": 275, "total_steps": 480, "loss": 1.253, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.14, "percentage": 57.29, "elapsed_time": "5:02:13", "remaining_time": "3:45:17"}
|
| 276 |
+
{"current_steps": 276, "total_steps": 480, "loss": 1.3009, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.15, "percentage": 57.5, "elapsed_time": "5:03:18", "remaining_time": "3:44:11"}
|
| 277 |
+
{"current_steps": 277, "total_steps": 480, "loss": 1.2592, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.15, "percentage": 57.71, "elapsed_time": "5:04:23", "remaining_time": "3:43:04"}
|
| 278 |
+
{"current_steps": 278, "total_steps": 480, "loss": 1.2774, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.15, "percentage": 57.92, "elapsed_time": "5:05:28", "remaining_time": "3:41:57"}
|
| 279 |
+
{"current_steps": 279, "total_steps": 480, "loss": 1.1952, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.16, "percentage": 58.13, "elapsed_time": "5:06:33", "remaining_time": "3:40:51"}
|
| 280 |
+
{"current_steps": 280, "total_steps": 480, "loss": 1.2365, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.16, "percentage": 58.33, "elapsed_time": "5:07:38", "remaining_time": "3:39:44"}
|
| 281 |
+
{"current_steps": 281, "total_steps": 480, "loss": 1.2847, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.17, "percentage": 58.54, "elapsed_time": "5:08:43", "remaining_time": "3:38:37"}
|
| 282 |
+
{"current_steps": 282, "total_steps": 480, "loss": 1.3455, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.17, "percentage": 58.75, "elapsed_time": "5:09:47", "remaining_time": "3:37:30"}
|
| 283 |
+
{"current_steps": 283, "total_steps": 480, "loss": 1.2748, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.18, "percentage": 58.96, "elapsed_time": "5:10:52", "remaining_time": "3:36:24"}
|
| 284 |
+
{"current_steps": 284, "total_steps": 480, "loss": 1.2911, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.18, "percentage": 59.17, "elapsed_time": "5:11:58", "remaining_time": "3:35:18"}
|
| 285 |
+
{"current_steps": 285, "total_steps": 480, "loss": 1.2784, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.18, "percentage": 59.38, "elapsed_time": "5:13:03", "remaining_time": "3:34:11"}
|
| 286 |
+
{"current_steps": 286, "total_steps": 480, "loss": 1.2659, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.19, "percentage": 59.58, "elapsed_time": "5:14:08", "remaining_time": "3:33:05"}
|
| 287 |
+
{"current_steps": 287, "total_steps": 480, "loss": 1.2668, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.19, "percentage": 59.79, "elapsed_time": "5:15:13", "remaining_time": "3:31:58"}
|
| 288 |
+
{"current_steps": 288, "total_steps": 480, "loss": 1.3022, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.2, "percentage": 60.0, "elapsed_time": "5:16:17", "remaining_time": "3:30:51"}
|
| 289 |
+
{"current_steps": 289, "total_steps": 480, "loss": 1.2033, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.2, "percentage": 60.21, "elapsed_time": "5:17:22", "remaining_time": "3:29:45"}
|
| 290 |
+
{"current_steps": 290, "total_steps": 480, "loss": 1.251, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.2, "percentage": 60.42, "elapsed_time": "5:18:28", "remaining_time": "3:28:39"}
|
| 291 |
+
{"current_steps": 291, "total_steps": 480, "loss": 1.3053, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.21, "percentage": 60.62, "elapsed_time": "5:19:32", "remaining_time": "3:27:32"}
|
| 292 |
+
{"current_steps": 292, "total_steps": 480, "loss": 1.2226, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.21, "percentage": 60.83, "elapsed_time": "5:20:36", "remaining_time": "3:26:25"}
|
| 293 |
+
{"current_steps": 293, "total_steps": 480, "loss": 1.2478, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.22, "percentage": 61.04, "elapsed_time": "5:21:41", "remaining_time": "3:25:18"}
|
| 294 |
+
{"current_steps": 294, "total_steps": 480, "loss": 1.2803, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.22, "percentage": 61.25, "elapsed_time": "5:22:46", "remaining_time": "3:24:12"}
|
| 295 |
+
{"current_steps": 295, "total_steps": 480, "loss": 1.3025, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.23, "percentage": 61.46, "elapsed_time": "5:23:51", "remaining_time": "3:23:05"}
|
| 296 |
+
{"current_steps": 296, "total_steps": 480, "loss": 1.297, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.23, "percentage": 61.67, "elapsed_time": "5:24:57", "remaining_time": "3:21:59"}
|
| 297 |
+
{"current_steps": 297, "total_steps": 480, "loss": 1.2958, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.23, "percentage": 61.88, "elapsed_time": "5:26:03", "remaining_time": "3:20:54"}
|
| 298 |
+
{"current_steps": 298, "total_steps": 480, "loss": 1.2675, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.24, "percentage": 62.08, "elapsed_time": "5:27:07", "remaining_time": "3:19:47"}
|
| 299 |
+
{"current_steps": 299, "total_steps": 480, "loss": 1.2631, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.24, "percentage": 62.29, "elapsed_time": "5:28:12", "remaining_time": "3:18:41"}
|
| 300 |
+
{"current_steps": 300, "total_steps": 480, "loss": 1.2664, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.25, "percentage": 62.5, "elapsed_time": "5:29:18", "remaining_time": "3:17:34"}
|
| 301 |
+
{"current_steps": 301, "total_steps": 480, "loss": 1.2316, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.25, "percentage": 62.71, "elapsed_time": "5:31:16", "remaining_time": "3:17:00"}
|
| 302 |
+
{"current_steps": 302, "total_steps": 480, "loss": 1.2485, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.25, "percentage": 62.92, "elapsed_time": "5:32:21", "remaining_time": "3:15:53"}
|
| 303 |
+
{"current_steps": 303, "total_steps": 480, "loss": 1.2762, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.26, "percentage": 63.12, "elapsed_time": "5:33:26", "remaining_time": "3:14:47"}
|
| 304 |
+
{"current_steps": 304, "total_steps": 480, "loss": 1.2404, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.26, "percentage": 63.33, "elapsed_time": "5:34:30", "remaining_time": "3:13:40"}
|
| 305 |
+
{"current_steps": 305, "total_steps": 480, "loss": 1.3051, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.27, "percentage": 63.54, "elapsed_time": "5:35:36", "remaining_time": "3:12:33"}
|
| 306 |
+
{"current_steps": 306, "total_steps": 480, "loss": 1.2, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.27, "percentage": 63.75, "elapsed_time": "5:36:40", "remaining_time": "3:11:26"}
|
| 307 |
+
{"current_steps": 307, "total_steps": 480, "loss": 1.2801, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.28, "percentage": 63.96, "elapsed_time": "5:37:45", "remaining_time": "3:10:20"}
|
| 308 |
+
{"current_steps": 308, "total_steps": 480, "loss": 1.3106, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.28, "percentage": 64.17, "elapsed_time": "5:38:51", "remaining_time": "3:09:13"}
|
| 309 |
+
{"current_steps": 309, "total_steps": 480, "loss": 1.2159, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.28, "percentage": 64.38, "elapsed_time": "5:39:57", "remaining_time": "3:08:07"}
|
| 310 |
+
{"current_steps": 310, "total_steps": 480, "loss": 1.2904, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.29, "percentage": 64.58, "elapsed_time": "5:41:02", "remaining_time": "3:07:01"}
|
| 311 |
+
{"current_steps": 311, "total_steps": 480, "loss": 1.1714, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.29, "percentage": 64.79, "elapsed_time": "5:42:06", "remaining_time": "3:05:54"}
|
| 312 |
+
{"current_steps": 312, "total_steps": 480, "loss": 1.2112, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.3, "percentage": 65.0, "elapsed_time": "5:43:12", "remaining_time": "3:04:48"}
|
| 313 |
+
{"current_steps": 313, "total_steps": 480, "loss": 1.1997, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.3, "percentage": 65.21, "elapsed_time": "5:44:17", "remaining_time": "3:03:41"}
|
| 314 |
+
{"current_steps": 314, "total_steps": 480, "loss": 1.2958, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.3, "percentage": 65.42, "elapsed_time": "5:45:22", "remaining_time": "3:02:35"}
|
| 315 |
+
{"current_steps": 315, "total_steps": 480, "loss": 1.2334, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.31, "percentage": 65.62, "elapsed_time": "5:46:27", "remaining_time": "3:01:28"}
|
| 316 |
+
{"current_steps": 316, "total_steps": 480, "loss": 1.287, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.31, "percentage": 65.83, "elapsed_time": "5:47:32", "remaining_time": "3:00:22"}
|
| 317 |
+
{"current_steps": 317, "total_steps": 480, "loss": 1.283, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.32, "percentage": 66.04, "elapsed_time": "5:48:36", "remaining_time": "2:59:15"}
|
| 318 |
+
{"current_steps": 318, "total_steps": 480, "loss": 1.26, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 1.32, "percentage": 66.25, "elapsed_time": "5:49:43", "remaining_time": "2:58:09"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.2461059190031152,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 300,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"grad_norm": 0.012170583144449788,
|
| 14 |
+
"learning_rate": 3e-05,
|
| 15 |
+
"loss": 1.3728,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.01,
|
| 20 |
+
"grad_norm": 0.012441205679409878,
|
| 21 |
+
"learning_rate": 3e-05,
|
| 22 |
+
"loss": 1.3427,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.01,
|
| 27 |
+
"grad_norm": 0.012336052820426525,
|
| 28 |
+
"learning_rate": 3e-05,
|
| 29 |
+
"loss": 1.3983,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.02,
|
| 34 |
+
"grad_norm": 0.013373499678550779,
|
| 35 |
+
"learning_rate": 3e-05,
|
| 36 |
+
"loss": 1.4146,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"grad_norm": 0.016376857472937493,
|
| 42 |
+
"learning_rate": 3e-05,
|
| 43 |
+
"loss": 1.3665,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.02,
|
| 48 |
+
"grad_norm": 0.01605485412905265,
|
| 49 |
+
"learning_rate": 3e-05,
|
| 50 |
+
"loss": 1.3865,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03,
|
| 55 |
+
"grad_norm": 0.01460238003538074,
|
| 56 |
+
"learning_rate": 3e-05,
|
| 57 |
+
"loss": 1.315,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.03,
|
| 62 |
+
"grad_norm": 0.015553135144585159,
|
| 63 |
+
"learning_rate": 3e-05,
|
| 64 |
+
"loss": 1.3531,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.04,
|
| 69 |
+
"grad_norm": 0.017868624998865858,
|
| 70 |
+
"learning_rate": 3e-05,
|
| 71 |
+
"loss": 1.3722,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.04,
|
| 76 |
+
"grad_norm": 0.0164281315042581,
|
| 77 |
+
"learning_rate": 3e-05,
|
| 78 |
+
"loss": 1.3179,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.05,
|
| 83 |
+
"grad_norm": 0.01913856813259346,
|
| 84 |
+
"learning_rate": 3e-05,
|
| 85 |
+
"loss": 1.3595,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.05,
|
| 90 |
+
"grad_norm": 0.0197227271190587,
|
| 91 |
+
"learning_rate": 3e-05,
|
| 92 |
+
"loss": 1.3904,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.05,
|
| 97 |
+
"grad_norm": 0.02003628325196358,
|
| 98 |
+
"learning_rate": 3e-05,
|
| 99 |
+
"loss": 1.4069,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.06,
|
| 104 |
+
"grad_norm": 0.020818781168561763,
|
| 105 |
+
"learning_rate": 3e-05,
|
| 106 |
+
"loss": 1.4516,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.06,
|
| 111 |
+
"grad_norm": 0.020893517671768724,
|
| 112 |
+
"learning_rate": 3e-05,
|
| 113 |
+
"loss": 1.3407,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.07,
|
| 118 |
+
"grad_norm": 0.02002708390520797,
|
| 119 |
+
"learning_rate": 3e-05,
|
| 120 |
+
"loss": 1.2756,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.07,
|
| 125 |
+
"grad_norm": 0.02147346418874998,
|
| 126 |
+
"learning_rate": 3e-05,
|
| 127 |
+
"loss": 1.4446,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.07,
|
| 132 |
+
"grad_norm": 0.026756951404830708,
|
| 133 |
+
"learning_rate": 3e-05,
|
| 134 |
+
"loss": 1.3975,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.08,
|
| 139 |
+
"grad_norm": 0.02147348610321771,
|
| 140 |
+
"learning_rate": 3e-05,
|
| 141 |
+
"loss": 1.3954,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.08,
|
| 146 |
+
"grad_norm": 0.02000891892461215,
|
| 147 |
+
"learning_rate": 3e-05,
|
| 148 |
+
"loss": 1.3254,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.09,
|
| 153 |
+
"grad_norm": 0.02051820688028316,
|
| 154 |
+
"learning_rate": 3e-05,
|
| 155 |
+
"loss": 1.3688,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.09,
|
| 160 |
+
"grad_norm": 0.019940598635671183,
|
| 161 |
+
"learning_rate": 3e-05,
|
| 162 |
+
"loss": 1.3304,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.1,
|
| 167 |
+
"grad_norm": 0.019387442345986872,
|
| 168 |
+
"learning_rate": 3e-05,
|
| 169 |
+
"loss": 1.3422,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.1,
|
| 174 |
+
"grad_norm": 0.024538417724117162,
|
| 175 |
+
"learning_rate": 3e-05,
|
| 176 |
+
"loss": 1.403,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.1,
|
| 181 |
+
"grad_norm": 0.0197067247131013,
|
| 182 |
+
"learning_rate": 3e-05,
|
| 183 |
+
"loss": 1.3088,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.11,
|
| 188 |
+
"grad_norm": 0.019906918553002587,
|
| 189 |
+
"learning_rate": 3e-05,
|
| 190 |
+
"loss": 1.3156,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.11,
|
| 195 |
+
"grad_norm": 0.01690103579384712,
|
| 196 |
+
"learning_rate": 3e-05,
|
| 197 |
+
"loss": 1.3548,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.12,
|
| 202 |
+
"grad_norm": 0.016146757145965005,
|
| 203 |
+
"learning_rate": 3e-05,
|
| 204 |
+
"loss": 1.323,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.12,
|
| 209 |
+
"grad_norm": 0.015853850291687382,
|
| 210 |
+
"learning_rate": 3e-05,
|
| 211 |
+
"loss": 1.2991,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.12,
|
| 216 |
+
"grad_norm": 0.014301767220445117,
|
| 217 |
+
"learning_rate": 3e-05,
|
| 218 |
+
"loss": 1.299,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.13,
|
| 223 |
+
"grad_norm": 0.01456552708533801,
|
| 224 |
+
"learning_rate": 3e-05,
|
| 225 |
+
"loss": 1.327,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.13,
|
| 230 |
+
"grad_norm": 0.014037544424116656,
|
| 231 |
+
"learning_rate": 3e-05,
|
| 232 |
+
"loss": 1.33,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.14,
|
| 237 |
+
"grad_norm": 0.014164388239542412,
|
| 238 |
+
"learning_rate": 3e-05,
|
| 239 |
+
"loss": 1.3307,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.14,
|
| 244 |
+
"grad_norm": 0.012972207094917622,
|
| 245 |
+
"learning_rate": 3e-05,
|
| 246 |
+
"loss": 1.3028,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.15,
|
| 251 |
+
"grad_norm": 0.012981889713494583,
|
| 252 |
+
"learning_rate": 3e-05,
|
| 253 |
+
"loss": 1.2963,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.15,
|
| 258 |
+
"grad_norm": 0.013445913227694615,
|
| 259 |
+
"learning_rate": 3e-05,
|
| 260 |
+
"loss": 1.2444,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.15,
|
| 265 |
+
"grad_norm": 0.012792648708552297,
|
| 266 |
+
"learning_rate": 3e-05,
|
| 267 |
+
"loss": 1.26,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.16,
|
| 272 |
+
"grad_norm": 0.012141794711979773,
|
| 273 |
+
"learning_rate": 3e-05,
|
| 274 |
+
"loss": 1.3438,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.16,
|
| 279 |
+
"grad_norm": 0.013862600605300035,
|
| 280 |
+
"learning_rate": 3e-05,
|
| 281 |
+
"loss": 1.3285,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.17,
|
| 286 |
+
"grad_norm": 0.012129096713587641,
|
| 287 |
+
"learning_rate": 3e-05,
|
| 288 |
+
"loss": 1.3221,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.17,
|
| 293 |
+
"grad_norm": 0.01871167034290605,
|
| 294 |
+
"learning_rate": 3e-05,
|
| 295 |
+
"loss": 1.2861,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.17,
|
| 300 |
+
"grad_norm": 0.012436045483287136,
|
| 301 |
+
"learning_rate": 3e-05,
|
| 302 |
+
"loss": 1.3068,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.18,
|
| 307 |
+
"grad_norm": 0.012364790923012296,
|
| 308 |
+
"learning_rate": 3e-05,
|
| 309 |
+
"loss": 1.3156,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.18,
|
| 314 |
+
"grad_norm": 0.012376437364947857,
|
| 315 |
+
"learning_rate": 3e-05,
|
| 316 |
+
"loss": 1.3088,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.19,
|
| 321 |
+
"grad_norm": 0.013969833036331685,
|
| 322 |
+
"learning_rate": 3e-05,
|
| 323 |
+
"loss": 1.3316,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.19,
|
| 328 |
+
"grad_norm": 0.012765341814671809,
|
| 329 |
+
"learning_rate": 3e-05,
|
| 330 |
+
"loss": 1.3352,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.2,
|
| 335 |
+
"grad_norm": 0.01261010445191611,
|
| 336 |
+
"learning_rate": 3e-05,
|
| 337 |
+
"loss": 1.3144,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.2,
|
| 342 |
+
"grad_norm": 0.012151618759459493,
|
| 343 |
+
"learning_rate": 3e-05,
|
| 344 |
+
"loss": 1.3204,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.2,
|
| 349 |
+
"grad_norm": 0.012998675059932196,
|
| 350 |
+
"learning_rate": 3e-05,
|
| 351 |
+
"loss": 1.2887,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.21,
|
| 356 |
+
"grad_norm": 0.012169489046924829,
|
| 357 |
+
"learning_rate": 3e-05,
|
| 358 |
+
"loss": 1.3332,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.21,
|
| 363 |
+
"grad_norm": 0.011920646653506707,
|
| 364 |
+
"learning_rate": 3e-05,
|
| 365 |
+
"loss": 1.3553,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.22,
|
| 370 |
+
"grad_norm": 0.011751923105885437,
|
| 371 |
+
"learning_rate": 3e-05,
|
| 372 |
+
"loss": 1.3671,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.22,
|
| 377 |
+
"grad_norm": 0.011025753112968974,
|
| 378 |
+
"learning_rate": 3e-05,
|
| 379 |
+
"loss": 1.2771,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.22,
|
| 384 |
+
"grad_norm": 0.012584882940640368,
|
| 385 |
+
"learning_rate": 3e-05,
|
| 386 |
+
"loss": 1.2277,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.23,
|
| 391 |
+
"grad_norm": 0.01179619281685698,
|
| 392 |
+
"learning_rate": 3e-05,
|
| 393 |
+
"loss": 1.323,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.23,
|
| 398 |
+
"grad_norm": 0.014564873082288777,
|
| 399 |
+
"learning_rate": 3e-05,
|
| 400 |
+
"loss": 1.2949,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.24,
|
| 405 |
+
"grad_norm": 0.019435936977958635,
|
| 406 |
+
"learning_rate": 3e-05,
|
| 407 |
+
"loss": 1.3098,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.24,
|
| 412 |
+
"grad_norm": 0.012111351048084126,
|
| 413 |
+
"learning_rate": 3e-05,
|
| 414 |
+
"loss": 1.3918,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.25,
|
| 419 |
+
"grad_norm": 0.012162697288403175,
|
| 420 |
+
"learning_rate": 3e-05,
|
| 421 |
+
"loss": 1.2861,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.25,
|
| 426 |
+
"grad_norm": 0.011286641826996159,
|
| 427 |
+
"learning_rate": 3e-05,
|
| 428 |
+
"loss": 1.316,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.25,
|
| 433 |
+
"grad_norm": 0.014424400496857113,
|
| 434 |
+
"learning_rate": 3e-05,
|
| 435 |
+
"loss": 1.2717,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.26,
|
| 440 |
+
"grad_norm": 0.011730736205609419,
|
| 441 |
+
"learning_rate": 3e-05,
|
| 442 |
+
"loss": 1.3252,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.26,
|
| 447 |
+
"grad_norm": 0.011179658792604664,
|
| 448 |
+
"learning_rate": 3e-05,
|
| 449 |
+
"loss": 1.3211,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.27,
|
| 454 |
+
"grad_norm": 0.011909295790935862,
|
| 455 |
+
"learning_rate": 3e-05,
|
| 456 |
+
"loss": 1.2757,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.27,
|
| 461 |
+
"grad_norm": 0.013362118144354595,
|
| 462 |
+
"learning_rate": 3e-05,
|
| 463 |
+
"loss": 1.2457,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.27,
|
| 468 |
+
"grad_norm": 0.019726440026194825,
|
| 469 |
+
"learning_rate": 3e-05,
|
| 470 |
+
"loss": 1.3159,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.28,
|
| 475 |
+
"grad_norm": 0.01151143382587086,
|
| 476 |
+
"learning_rate": 3e-05,
|
| 477 |
+
"loss": 1.2628,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.28,
|
| 482 |
+
"grad_norm": 0.011159675986273602,
|
| 483 |
+
"learning_rate": 3e-05,
|
| 484 |
+
"loss": 1.2901,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.29,
|
| 489 |
+
"grad_norm": 0.01052362952035569,
|
| 490 |
+
"learning_rate": 3e-05,
|
| 491 |
+
"loss": 1.2749,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.29,
|
| 496 |
+
"grad_norm": 0.014028722939171852,
|
| 497 |
+
"learning_rate": 3e-05,
|
| 498 |
+
"loss": 1.33,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.29,
|
| 503 |
+
"grad_norm": 0.010897615932695505,
|
| 504 |
+
"learning_rate": 3e-05,
|
| 505 |
+
"loss": 1.3084,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.3,
|
| 510 |
+
"grad_norm": 0.011353909572748124,
|
| 511 |
+
"learning_rate": 3e-05,
|
| 512 |
+
"loss": 1.277,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.3,
|
| 517 |
+
"grad_norm": 0.011100433604844168,
|
| 518 |
+
"learning_rate": 3e-05,
|
| 519 |
+
"loss": 1.3586,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.31,
|
| 524 |
+
"grad_norm": 0.011880796497294469,
|
| 525 |
+
"learning_rate": 3e-05,
|
| 526 |
+
"loss": 1.2959,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.31,
|
| 531 |
+
"grad_norm": 0.011759412083305202,
|
| 532 |
+
"learning_rate": 3e-05,
|
| 533 |
+
"loss": 1.2957,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.32,
|
| 538 |
+
"grad_norm": 0.011480127470140948,
|
| 539 |
+
"learning_rate": 3e-05,
|
| 540 |
+
"loss": 1.3278,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.32,
|
| 545 |
+
"grad_norm": 0.011449384427383405,
|
| 546 |
+
"learning_rate": 3e-05,
|
| 547 |
+
"loss": 1.2633,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.32,
|
| 552 |
+
"grad_norm": 0.011764058753943114,
|
| 553 |
+
"learning_rate": 3e-05,
|
| 554 |
+
"loss": 1.2808,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.33,
|
| 559 |
+
"grad_norm": 0.01124430953679315,
|
| 560 |
+
"learning_rate": 3e-05,
|
| 561 |
+
"loss": 1.2664,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.33,
|
| 566 |
+
"grad_norm": 0.01057061147022858,
|
| 567 |
+
"learning_rate": 3e-05,
|
| 568 |
+
"loss": 1.2969,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.34,
|
| 573 |
+
"grad_norm": 0.011616218617106901,
|
| 574 |
+
"learning_rate": 3e-05,
|
| 575 |
+
"loss": 1.2982,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.34,
|
| 580 |
+
"grad_norm": 0.01144732781571693,
|
| 581 |
+
"learning_rate": 3e-05,
|
| 582 |
+
"loss": 1.2784,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.34,
|
| 587 |
+
"grad_norm": 0.011077640894084905,
|
| 588 |
+
"learning_rate": 3e-05,
|
| 589 |
+
"loss": 1.2819,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.35,
|
| 594 |
+
"grad_norm": 0.01613205804007413,
|
| 595 |
+
"learning_rate": 3e-05,
|
| 596 |
+
"loss": 1.311,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.35,
|
| 601 |
+
"grad_norm": 0.013574606375148299,
|
| 602 |
+
"learning_rate": 3e-05,
|
| 603 |
+
"loss": 1.2561,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.36,
|
| 608 |
+
"grad_norm": 0.01335654343450743,
|
| 609 |
+
"learning_rate": 3e-05,
|
| 610 |
+
"loss": 1.2731,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.36,
|
| 615 |
+
"grad_norm": 0.012449392909288468,
|
| 616 |
+
"learning_rate": 3e-05,
|
| 617 |
+
"loss": 1.2822,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.37,
|
| 622 |
+
"grad_norm": 0.012435933132224748,
|
| 623 |
+
"learning_rate": 3e-05,
|
| 624 |
+
"loss": 1.2447,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.37,
|
| 629 |
+
"grad_norm": 0.011302776757667351,
|
| 630 |
+
"learning_rate": 3e-05,
|
| 631 |
+
"loss": 1.2786,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.37,
|
| 636 |
+
"grad_norm": 0.012040795209866716,
|
| 637 |
+
"learning_rate": 3e-05,
|
| 638 |
+
"loss": 1.3479,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.38,
|
| 643 |
+
"grad_norm": 0.011073079422530921,
|
| 644 |
+
"learning_rate": 3e-05,
|
| 645 |
+
"loss": 1.2794,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.38,
|
| 650 |
+
"grad_norm": 0.013030304746973722,
|
| 651 |
+
"learning_rate": 3e-05,
|
| 652 |
+
"loss": 1.3131,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.39,
|
| 657 |
+
"grad_norm": 0.012526490354635381,
|
| 658 |
+
"learning_rate": 3e-05,
|
| 659 |
+
"loss": 1.2458,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.39,
|
| 664 |
+
"grad_norm": 0.012847228081473072,
|
| 665 |
+
"learning_rate": 3e-05,
|
| 666 |
+
"loss": 1.2614,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.39,
|
| 671 |
+
"grad_norm": 0.012688536258452844,
|
| 672 |
+
"learning_rate": 3e-05,
|
| 673 |
+
"loss": 1.2399,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.4,
|
| 678 |
+
"grad_norm": 0.012208675458581508,
|
| 679 |
+
"learning_rate": 3e-05,
|
| 680 |
+
"loss": 1.3144,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.4,
|
| 685 |
+
"grad_norm": 0.010859781351210412,
|
| 686 |
+
"learning_rate": 3e-05,
|
| 687 |
+
"loss": 1.2324,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.41,
|
| 692 |
+
"grad_norm": 0.012478911974195483,
|
| 693 |
+
"learning_rate": 3e-05,
|
| 694 |
+
"loss": 1.2719,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.41,
|
| 699 |
+
"grad_norm": 0.012373249769099943,
|
| 700 |
+
"learning_rate": 3e-05,
|
| 701 |
+
"loss": 1.2622,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.42,
|
| 706 |
+
"grad_norm": 0.013463086982838338,
|
| 707 |
+
"learning_rate": 3e-05,
|
| 708 |
+
"loss": 1.2776,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.42,
|
| 713 |
+
"grad_norm": 0.016385409822984896,
|
| 714 |
+
"learning_rate": 3e-05,
|
| 715 |
+
"loss": 1.2808,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.42,
|
| 720 |
+
"grad_norm": 0.012219344462321249,
|
| 721 |
+
"learning_rate": 3e-05,
|
| 722 |
+
"loss": 1.3073,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.43,
|
| 727 |
+
"grad_norm": 0.01219020267598617,
|
| 728 |
+
"learning_rate": 3e-05,
|
| 729 |
+
"loss": 1.2182,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.43,
|
| 734 |
+
"grad_norm": 0.012387262921564371,
|
| 735 |
+
"learning_rate": 3e-05,
|
| 736 |
+
"loss": 1.3265,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.44,
|
| 741 |
+
"grad_norm": 0.01206079560473451,
|
| 742 |
+
"learning_rate": 3e-05,
|
| 743 |
+
"loss": 1.2228,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.44,
|
| 748 |
+
"grad_norm": 0.01225473000339032,
|
| 749 |
+
"learning_rate": 3e-05,
|
| 750 |
+
"loss": 1.2843,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.44,
|
| 755 |
+
"grad_norm": 0.01326596734337093,
|
| 756 |
+
"learning_rate": 3e-05,
|
| 757 |
+
"loss": 1.2789,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.45,
|
| 762 |
+
"grad_norm": 0.014527084891658,
|
| 763 |
+
"learning_rate": 3e-05,
|
| 764 |
+
"loss": 1.2407,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.45,
|
| 769 |
+
"grad_norm": 0.013506152190492582,
|
| 770 |
+
"learning_rate": 3e-05,
|
| 771 |
+
"loss": 1.3537,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.46,
|
| 776 |
+
"grad_norm": 0.012350713785703687,
|
| 777 |
+
"learning_rate": 3e-05,
|
| 778 |
+
"loss": 1.299,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.46,
|
| 783 |
+
"grad_norm": 0.013548036090856945,
|
| 784 |
+
"learning_rate": 3e-05,
|
| 785 |
+
"loss": 1.3407,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.47,
|
| 790 |
+
"grad_norm": 0.012716548388196138,
|
| 791 |
+
"learning_rate": 3e-05,
|
| 792 |
+
"loss": 1.2837,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.47,
|
| 797 |
+
"grad_norm": 0.012376449836024567,
|
| 798 |
+
"learning_rate": 3e-05,
|
| 799 |
+
"loss": 1.2408,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.47,
|
| 804 |
+
"grad_norm": 0.013149525793997427,
|
| 805 |
+
"learning_rate": 3e-05,
|
| 806 |
+
"loss": 1.2552,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.48,
|
| 811 |
+
"grad_norm": 0.012168644210731216,
|
| 812 |
+
"learning_rate": 3e-05,
|
| 813 |
+
"loss": 1.3157,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.48,
|
| 818 |
+
"grad_norm": 0.012324914288283324,
|
| 819 |
+
"learning_rate": 3e-05,
|
| 820 |
+
"loss": 1.3123,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.49,
|
| 825 |
+
"grad_norm": 0.012072754893928983,
|
| 826 |
+
"learning_rate": 3e-05,
|
| 827 |
+
"loss": 1.2701,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.49,
|
| 832 |
+
"grad_norm": 0.01264419972632402,
|
| 833 |
+
"learning_rate": 3e-05,
|
| 834 |
+
"loss": 1.2983,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.49,
|
| 839 |
+
"grad_norm": 0.042949486922442916,
|
| 840 |
+
"learning_rate": 3e-05,
|
| 841 |
+
"loss": 1.3216,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.5,
|
| 846 |
+
"grad_norm": 0.02568672309407492,
|
| 847 |
+
"learning_rate": 3e-05,
|
| 848 |
+
"loss": 1.3005,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.5,
|
| 853 |
+
"grad_norm": 0.012811282089116556,
|
| 854 |
+
"learning_rate": 3e-05,
|
| 855 |
+
"loss": 1.3233,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.51,
|
| 860 |
+
"grad_norm": 0.017868025898532574,
|
| 861 |
+
"learning_rate": 3e-05,
|
| 862 |
+
"loss": 1.3054,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.51,
|
| 867 |
+
"grad_norm": 0.012993051949728001,
|
| 868 |
+
"learning_rate": 3e-05,
|
| 869 |
+
"loss": 1.2471,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.52,
|
| 874 |
+
"grad_norm": 0.018403888249234238,
|
| 875 |
+
"learning_rate": 3e-05,
|
| 876 |
+
"loss": 1.3104,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.52,
|
| 881 |
+
"grad_norm": 0.018015251441908964,
|
| 882 |
+
"learning_rate": 3e-05,
|
| 883 |
+
"loss": 1.2492,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.52,
|
| 888 |
+
"grad_norm": 0.013906581394784246,
|
| 889 |
+
"learning_rate": 3e-05,
|
| 890 |
+
"loss": 1.2466,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.53,
|
| 895 |
+
"grad_norm": 0.014862930320357416,
|
| 896 |
+
"learning_rate": 3e-05,
|
| 897 |
+
"loss": 1.3047,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.53,
|
| 902 |
+
"grad_norm": 0.04412014629710122,
|
| 903 |
+
"learning_rate": 3e-05,
|
| 904 |
+
"loss": 1.2054,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.54,
|
| 909 |
+
"grad_norm": 0.026614261465937473,
|
| 910 |
+
"learning_rate": 3e-05,
|
| 911 |
+
"loss": 1.2655,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.54,
|
| 916 |
+
"grad_norm": 0.01376408626191131,
|
| 917 |
+
"learning_rate": 3e-05,
|
| 918 |
+
"loss": 1.2382,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.54,
|
| 923 |
+
"grad_norm": 0.015429717937867932,
|
| 924 |
+
"learning_rate": 3e-05,
|
| 925 |
+
"loss": 1.3278,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.55,
|
| 930 |
+
"grad_norm": 0.014533210702277371,
|
| 931 |
+
"learning_rate": 3e-05,
|
| 932 |
+
"loss": 1.3138,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.55,
|
| 937 |
+
"grad_norm": 0.012982144097939177,
|
| 938 |
+
"learning_rate": 3e-05,
|
| 939 |
+
"loss": 1.3109,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.56,
|
| 944 |
+
"grad_norm": 0.0182304886411741,
|
| 945 |
+
"learning_rate": 3e-05,
|
| 946 |
+
"loss": 1.2985,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.56,
|
| 951 |
+
"grad_norm": 0.017093917039141884,
|
| 952 |
+
"learning_rate": 3e-05,
|
| 953 |
+
"loss": 1.2468,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.56,
|
| 958 |
+
"grad_norm": 0.014512262916267834,
|
| 959 |
+
"learning_rate": 3e-05,
|
| 960 |
+
"loss": 1.3445,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.57,
|
| 965 |
+
"grad_norm": 0.012373216012523584,
|
| 966 |
+
"learning_rate": 3e-05,
|
| 967 |
+
"loss": 1.2921,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.57,
|
| 972 |
+
"grad_norm": 0.014913292517795098,
|
| 973 |
+
"learning_rate": 3e-05,
|
| 974 |
+
"loss": 1.3327,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.58,
|
| 979 |
+
"grad_norm": 0.01548966880954737,
|
| 980 |
+
"learning_rate": 3e-05,
|
| 981 |
+
"loss": 1.3017,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.58,
|
| 986 |
+
"grad_norm": 0.0140787411578127,
|
| 987 |
+
"learning_rate": 3e-05,
|
| 988 |
+
"loss": 1.3248,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.59,
|
| 993 |
+
"grad_norm": 0.01421362111312793,
|
| 994 |
+
"learning_rate": 3e-05,
|
| 995 |
+
"loss": 1.3478,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.59,
|
| 1000 |
+
"grad_norm": 0.012945172730785133,
|
| 1001 |
+
"learning_rate": 3e-05,
|
| 1002 |
+
"loss": 1.2547,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.59,
|
| 1007 |
+
"grad_norm": 0.013197491856509017,
|
| 1008 |
+
"learning_rate": 3e-05,
|
| 1009 |
+
"loss": 1.2809,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.6,
|
| 1014 |
+
"grad_norm": 0.014138707993779835,
|
| 1015 |
+
"learning_rate": 3e-05,
|
| 1016 |
+
"loss": 1.2585,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.6,
|
| 1021 |
+
"grad_norm": 0.013999463137089363,
|
| 1022 |
+
"learning_rate": 3e-05,
|
| 1023 |
+
"loss": 1.316,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.61,
|
| 1028 |
+
"grad_norm": 0.014733166701341028,
|
| 1029 |
+
"learning_rate": 3e-05,
|
| 1030 |
+
"loss": 1.3576,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.61,
|
| 1035 |
+
"grad_norm": 0.012930967759936974,
|
| 1036 |
+
"learning_rate": 3e-05,
|
| 1037 |
+
"loss": 1.2939,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.61,
|
| 1042 |
+
"grad_norm": 0.013560296387293834,
|
| 1043 |
+
"learning_rate": 3e-05,
|
| 1044 |
+
"loss": 1.3307,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.62,
|
| 1049 |
+
"grad_norm": 0.017730136160404638,
|
| 1050 |
+
"learning_rate": 3e-05,
|
| 1051 |
+
"loss": 1.3118,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.62,
|
| 1056 |
+
"grad_norm": 0.013975982126514604,
|
| 1057 |
+
"learning_rate": 3e-05,
|
| 1058 |
+
"loss": 1.2836,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.63,
|
| 1063 |
+
"grad_norm": 0.013166737892207972,
|
| 1064 |
+
"learning_rate": 3e-05,
|
| 1065 |
+
"loss": 1.274,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.63,
|
| 1070 |
+
"grad_norm": 0.01341654728143307,
|
| 1071 |
+
"learning_rate": 3e-05,
|
| 1072 |
+
"loss": 1.2447,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.64,
|
| 1077 |
+
"grad_norm": 0.015608064826784552,
|
| 1078 |
+
"learning_rate": 3e-05,
|
| 1079 |
+
"loss": 1.2743,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.64,
|
| 1084 |
+
"grad_norm": 0.014402235915901979,
|
| 1085 |
+
"learning_rate": 3e-05,
|
| 1086 |
+
"loss": 1.2351,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.64,
|
| 1091 |
+
"grad_norm": 0.013660194729217125,
|
| 1092 |
+
"learning_rate": 3e-05,
|
| 1093 |
+
"loss": 1.2584,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.65,
|
| 1098 |
+
"grad_norm": 0.013437763813973025,
|
| 1099 |
+
"learning_rate": 3e-05,
|
| 1100 |
+
"loss": 1.2281,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.65,
|
| 1105 |
+
"grad_norm": 0.01391064432526438,
|
| 1106 |
+
"learning_rate": 3e-05,
|
| 1107 |
+
"loss": 1.2922,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.66,
|
| 1112 |
+
"grad_norm": 0.013854673514263218,
|
| 1113 |
+
"learning_rate": 3e-05,
|
| 1114 |
+
"loss": 1.2589,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.66,
|
| 1119 |
+
"grad_norm": 0.013357866419948893,
|
| 1120 |
+
"learning_rate": 3e-05,
|
| 1121 |
+
"loss": 1.3146,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.66,
|
| 1126 |
+
"grad_norm": 0.013746796253108871,
|
| 1127 |
+
"learning_rate": 3e-05,
|
| 1128 |
+
"loss": 1.2896,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.67,
|
| 1133 |
+
"grad_norm": 0.01323955577224082,
|
| 1134 |
+
"learning_rate": 3e-05,
|
| 1135 |
+
"loss": 1.2661,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.67,
|
| 1140 |
+
"grad_norm": 0.014094881922329888,
|
| 1141 |
+
"learning_rate": 3e-05,
|
| 1142 |
+
"loss": 1.2296,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.68,
|
| 1147 |
+
"grad_norm": 0.021786851768047143,
|
| 1148 |
+
"learning_rate": 3e-05,
|
| 1149 |
+
"loss": 1.3146,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.68,
|
| 1154 |
+
"grad_norm": 0.014115247163622169,
|
| 1155 |
+
"learning_rate": 3e-05,
|
| 1156 |
+
"loss": 1.2445,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.69,
|
| 1161 |
+
"grad_norm": 0.013235405572388292,
|
| 1162 |
+
"learning_rate": 3e-05,
|
| 1163 |
+
"loss": 1.2828,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.69,
|
| 1168 |
+
"grad_norm": 0.013292324416878417,
|
| 1169 |
+
"learning_rate": 3e-05,
|
| 1170 |
+
"loss": 1.2226,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.69,
|
| 1175 |
+
"grad_norm": 0.014395884061164101,
|
| 1176 |
+
"learning_rate": 3e-05,
|
| 1177 |
+
"loss": 1.3279,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.7,
|
| 1182 |
+
"grad_norm": 0.013904468976095652,
|
| 1183 |
+
"learning_rate": 3e-05,
|
| 1184 |
+
"loss": 1.3052,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.7,
|
| 1189 |
+
"grad_norm": 0.01498037832336143,
|
| 1190 |
+
"learning_rate": 3e-05,
|
| 1191 |
+
"loss": 1.2751,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.71,
|
| 1196 |
+
"grad_norm": 0.013935053913175984,
|
| 1197 |
+
"learning_rate": 3e-05,
|
| 1198 |
+
"loss": 1.2712,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.71,
|
| 1203 |
+
"grad_norm": 0.013342634505562194,
|
| 1204 |
+
"learning_rate": 3e-05,
|
| 1205 |
+
"loss": 1.2478,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.71,
|
| 1210 |
+
"grad_norm": 0.014280227334636308,
|
| 1211 |
+
"learning_rate": 3e-05,
|
| 1212 |
+
"loss": 1.2832,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.72,
|
| 1217 |
+
"grad_norm": 0.013662238228160744,
|
| 1218 |
+
"learning_rate": 3e-05,
|
| 1219 |
+
"loss": 1.3105,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.72,
|
| 1224 |
+
"grad_norm": 0.013883566745022063,
|
| 1225 |
+
"learning_rate": 3e-05,
|
| 1226 |
+
"loss": 1.2882,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.73,
|
| 1231 |
+
"grad_norm": 0.014231700687422954,
|
| 1232 |
+
"learning_rate": 3e-05,
|
| 1233 |
+
"loss": 1.3134,
|
| 1234 |
+
"step": 175
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.73,
|
| 1238 |
+
"grad_norm": 0.015856322519580097,
|
| 1239 |
+
"learning_rate": 3e-05,
|
| 1240 |
+
"loss": 1.3416,
|
| 1241 |
+
"step": 176
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.74,
|
| 1245 |
+
"grad_norm": 0.014864139947341821,
|
| 1246 |
+
"learning_rate": 3e-05,
|
| 1247 |
+
"loss": 1.2528,
|
| 1248 |
+
"step": 177
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.74,
|
| 1252 |
+
"grad_norm": 0.01384672514806748,
|
| 1253 |
+
"learning_rate": 3e-05,
|
| 1254 |
+
"loss": 1.2146,
|
| 1255 |
+
"step": 178
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.74,
|
| 1259 |
+
"grad_norm": 0.015464948934868796,
|
| 1260 |
+
"learning_rate": 3e-05,
|
| 1261 |
+
"loss": 1.2165,
|
| 1262 |
+
"step": 179
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.75,
|
| 1266 |
+
"grad_norm": 0.015385891583895897,
|
| 1267 |
+
"learning_rate": 3e-05,
|
| 1268 |
+
"loss": 1.3034,
|
| 1269 |
+
"step": 180
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.75,
|
| 1273 |
+
"grad_norm": 0.015500556463836994,
|
| 1274 |
+
"learning_rate": 3e-05,
|
| 1275 |
+
"loss": 1.2462,
|
| 1276 |
+
"step": 181
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.76,
|
| 1280 |
+
"grad_norm": 0.015360964744432567,
|
| 1281 |
+
"learning_rate": 3e-05,
|
| 1282 |
+
"loss": 1.2508,
|
| 1283 |
+
"step": 182
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.76,
|
| 1287 |
+
"grad_norm": 0.018104130847576297,
|
| 1288 |
+
"learning_rate": 3e-05,
|
| 1289 |
+
"loss": 1.2617,
|
| 1290 |
+
"step": 183
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.76,
|
| 1294 |
+
"grad_norm": 0.017297392951343114,
|
| 1295 |
+
"learning_rate": 3e-05,
|
| 1296 |
+
"loss": 1.2694,
|
| 1297 |
+
"step": 184
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.77,
|
| 1301 |
+
"grad_norm": 0.014605348589579433,
|
| 1302 |
+
"learning_rate": 3e-05,
|
| 1303 |
+
"loss": 1.2521,
|
| 1304 |
+
"step": 185
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.77,
|
| 1308 |
+
"grad_norm": 0.014287950283906567,
|
| 1309 |
+
"learning_rate": 3e-05,
|
| 1310 |
+
"loss": 1.2583,
|
| 1311 |
+
"step": 186
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.78,
|
| 1315 |
+
"grad_norm": 0.01496726177324148,
|
| 1316 |
+
"learning_rate": 3e-05,
|
| 1317 |
+
"loss": 1.2689,
|
| 1318 |
+
"step": 187
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.78,
|
| 1322 |
+
"grad_norm": 0.015097305854620989,
|
| 1323 |
+
"learning_rate": 3e-05,
|
| 1324 |
+
"loss": 1.3264,
|
| 1325 |
+
"step": 188
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.79,
|
| 1329 |
+
"grad_norm": 0.014393731181691946,
|
| 1330 |
+
"learning_rate": 3e-05,
|
| 1331 |
+
"loss": 1.2509,
|
| 1332 |
+
"step": 189
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.79,
|
| 1336 |
+
"grad_norm": 0.014329101467007178,
|
| 1337 |
+
"learning_rate": 3e-05,
|
| 1338 |
+
"loss": 1.2791,
|
| 1339 |
+
"step": 190
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.79,
|
| 1343 |
+
"grad_norm": 0.01432823143229832,
|
| 1344 |
+
"learning_rate": 3e-05,
|
| 1345 |
+
"loss": 1.3058,
|
| 1346 |
+
"step": 191
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.8,
|
| 1350 |
+
"grad_norm": 0.01409215280735208,
|
| 1351 |
+
"learning_rate": 3e-05,
|
| 1352 |
+
"loss": 1.298,
|
| 1353 |
+
"step": 192
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.8,
|
| 1357 |
+
"grad_norm": 0.014322129770126826,
|
| 1358 |
+
"learning_rate": 3e-05,
|
| 1359 |
+
"loss": 1.2822,
|
| 1360 |
+
"step": 193
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.81,
|
| 1364 |
+
"grad_norm": 0.015535730832931206,
|
| 1365 |
+
"learning_rate": 3e-05,
|
| 1366 |
+
"loss": 1.2952,
|
| 1367 |
+
"step": 194
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.81,
|
| 1371 |
+
"grad_norm": 0.014586001705999283,
|
| 1372 |
+
"learning_rate": 3e-05,
|
| 1373 |
+
"loss": 1.2916,
|
| 1374 |
+
"step": 195
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.81,
|
| 1378 |
+
"grad_norm": 0.014346450671961445,
|
| 1379 |
+
"learning_rate": 3e-05,
|
| 1380 |
+
"loss": 1.286,
|
| 1381 |
+
"step": 196
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.82,
|
| 1385 |
+
"grad_norm": 0.01465216301040808,
|
| 1386 |
+
"learning_rate": 3e-05,
|
| 1387 |
+
"loss": 1.3168,
|
| 1388 |
+
"step": 197
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.82,
|
| 1392 |
+
"grad_norm": 0.014633342656678221,
|
| 1393 |
+
"learning_rate": 3e-05,
|
| 1394 |
+
"loss": 1.222,
|
| 1395 |
+
"step": 198
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.83,
|
| 1399 |
+
"grad_norm": 0.019433028609002513,
|
| 1400 |
+
"learning_rate": 3e-05,
|
| 1401 |
+
"loss": 1.2868,
|
| 1402 |
+
"step": 199
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.83,
|
| 1406 |
+
"grad_norm": 0.015999291729556466,
|
| 1407 |
+
"learning_rate": 3e-05,
|
| 1408 |
+
"loss": 1.2546,
|
| 1409 |
+
"step": 200
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.83,
|
| 1413 |
+
"grad_norm": 0.013974319782604303,
|
| 1414 |
+
"learning_rate": 3e-05,
|
| 1415 |
+
"loss": 1.3313,
|
| 1416 |
+
"step": 201
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.84,
|
| 1420 |
+
"grad_norm": 0.019684778346554094,
|
| 1421 |
+
"learning_rate": 3e-05,
|
| 1422 |
+
"loss": 1.2183,
|
| 1423 |
+
"step": 202
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.84,
|
| 1427 |
+
"grad_norm": 0.033028122367380335,
|
| 1428 |
+
"learning_rate": 3e-05,
|
| 1429 |
+
"loss": 1.2943,
|
| 1430 |
+
"step": 203
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.85,
|
| 1434 |
+
"grad_norm": 0.015226007463866797,
|
| 1435 |
+
"learning_rate": 3e-05,
|
| 1436 |
+
"loss": 1.2398,
|
| 1437 |
+
"step": 204
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.85,
|
| 1441 |
+
"grad_norm": 0.018039902586464752,
|
| 1442 |
+
"learning_rate": 3e-05,
|
| 1443 |
+
"loss": 1.2804,
|
| 1444 |
+
"step": 205
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.86,
|
| 1448 |
+
"grad_norm": 0.01458863130389662,
|
| 1449 |
+
"learning_rate": 3e-05,
|
| 1450 |
+
"loss": 1.3344,
|
| 1451 |
+
"step": 206
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.86,
|
| 1455 |
+
"grad_norm": 0.015824538304288215,
|
| 1456 |
+
"learning_rate": 3e-05,
|
| 1457 |
+
"loss": 1.2351,
|
| 1458 |
+
"step": 207
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.86,
|
| 1462 |
+
"grad_norm": 0.014833851868165835,
|
| 1463 |
+
"learning_rate": 3e-05,
|
| 1464 |
+
"loss": 1.2385,
|
| 1465 |
+
"step": 208
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.87,
|
| 1469 |
+
"grad_norm": 0.013926386093476583,
|
| 1470 |
+
"learning_rate": 3e-05,
|
| 1471 |
+
"loss": 1.2263,
|
| 1472 |
+
"step": 209
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.87,
|
| 1476 |
+
"grad_norm": 0.015632500062928826,
|
| 1477 |
+
"learning_rate": 3e-05,
|
| 1478 |
+
"loss": 1.2931,
|
| 1479 |
+
"step": 210
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.88,
|
| 1483 |
+
"grad_norm": 0.014724285681248521,
|
| 1484 |
+
"learning_rate": 3e-05,
|
| 1485 |
+
"loss": 1.3084,
|
| 1486 |
+
"step": 211
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.88,
|
| 1490 |
+
"grad_norm": 0.014461044938261114,
|
| 1491 |
+
"learning_rate": 3e-05,
|
| 1492 |
+
"loss": 1.3348,
|
| 1493 |
+
"step": 212
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.88,
|
| 1497 |
+
"grad_norm": 0.014888010433011196,
|
| 1498 |
+
"learning_rate": 3e-05,
|
| 1499 |
+
"loss": 1.2726,
|
| 1500 |
+
"step": 213
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.89,
|
| 1504 |
+
"grad_norm": 0.015186640580123631,
|
| 1505 |
+
"learning_rate": 3e-05,
|
| 1506 |
+
"loss": 1.266,
|
| 1507 |
+
"step": 214
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.89,
|
| 1511 |
+
"grad_norm": 0.014169851274828012,
|
| 1512 |
+
"learning_rate": 3e-05,
|
| 1513 |
+
"loss": 1.2275,
|
| 1514 |
+
"step": 215
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.9,
|
| 1518 |
+
"grad_norm": 0.014597768020650003,
|
| 1519 |
+
"learning_rate": 3e-05,
|
| 1520 |
+
"loss": 1.166,
|
| 1521 |
+
"step": 216
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.9,
|
| 1525 |
+
"grad_norm": 0.016348049435478462,
|
| 1526 |
+
"learning_rate": 3e-05,
|
| 1527 |
+
"loss": 1.3315,
|
| 1528 |
+
"step": 217
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.91,
|
| 1532 |
+
"grad_norm": 0.01389791869445101,
|
| 1533 |
+
"learning_rate": 3e-05,
|
| 1534 |
+
"loss": 1.2339,
|
| 1535 |
+
"step": 218
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.91,
|
| 1539 |
+
"grad_norm": 0.014730542143538614,
|
| 1540 |
+
"learning_rate": 3e-05,
|
| 1541 |
+
"loss": 1.2884,
|
| 1542 |
+
"step": 219
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.91,
|
| 1546 |
+
"grad_norm": 0.01495965630015944,
|
| 1547 |
+
"learning_rate": 3e-05,
|
| 1548 |
+
"loss": 1.1792,
|
| 1549 |
+
"step": 220
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.92,
|
| 1553 |
+
"grad_norm": 0.016164599847288814,
|
| 1554 |
+
"learning_rate": 3e-05,
|
| 1555 |
+
"loss": 1.2511,
|
| 1556 |
+
"step": 221
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.92,
|
| 1560 |
+
"grad_norm": 0.014356323440192154,
|
| 1561 |
+
"learning_rate": 3e-05,
|
| 1562 |
+
"loss": 1.2653,
|
| 1563 |
+
"step": 222
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.93,
|
| 1567 |
+
"grad_norm": 0.014496008840759921,
|
| 1568 |
+
"learning_rate": 3e-05,
|
| 1569 |
+
"loss": 1.3067,
|
| 1570 |
+
"step": 223
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.93,
|
| 1574 |
+
"grad_norm": 0.014173980530200598,
|
| 1575 |
+
"learning_rate": 3e-05,
|
| 1576 |
+
"loss": 1.1765,
|
| 1577 |
+
"step": 224
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.93,
|
| 1581 |
+
"grad_norm": 0.019941463494425323,
|
| 1582 |
+
"learning_rate": 3e-05,
|
| 1583 |
+
"loss": 1.2627,
|
| 1584 |
+
"step": 225
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.94,
|
| 1588 |
+
"grad_norm": 0.014559827444157727,
|
| 1589 |
+
"learning_rate": 3e-05,
|
| 1590 |
+
"loss": 1.2726,
|
| 1591 |
+
"step": 226
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.94,
|
| 1595 |
+
"grad_norm": 0.015633910509735647,
|
| 1596 |
+
"learning_rate": 3e-05,
|
| 1597 |
+
"loss": 1.2062,
|
| 1598 |
+
"step": 227
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.95,
|
| 1602 |
+
"grad_norm": 0.014734762194709058,
|
| 1603 |
+
"learning_rate": 3e-05,
|
| 1604 |
+
"loss": 1.2472,
|
| 1605 |
+
"step": 228
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.95,
|
| 1609 |
+
"grad_norm": 0.014923021609054498,
|
| 1610 |
+
"learning_rate": 3e-05,
|
| 1611 |
+
"loss": 1.2648,
|
| 1612 |
+
"step": 229
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.96,
|
| 1616 |
+
"grad_norm": 0.01609643463392318,
|
| 1617 |
+
"learning_rate": 3e-05,
|
| 1618 |
+
"loss": 1.3097,
|
| 1619 |
+
"step": 230
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.96,
|
| 1623 |
+
"grad_norm": 0.015313840216276563,
|
| 1624 |
+
"learning_rate": 3e-05,
|
| 1625 |
+
"loss": 1.2462,
|
| 1626 |
+
"step": 231
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.96,
|
| 1630 |
+
"grad_norm": 0.014704752471017907,
|
| 1631 |
+
"learning_rate": 3e-05,
|
| 1632 |
+
"loss": 1.2852,
|
| 1633 |
+
"step": 232
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.97,
|
| 1637 |
+
"grad_norm": 0.01565975211378067,
|
| 1638 |
+
"learning_rate": 3e-05,
|
| 1639 |
+
"loss": 1.2879,
|
| 1640 |
+
"step": 233
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.97,
|
| 1644 |
+
"grad_norm": 0.014461185719430197,
|
| 1645 |
+
"learning_rate": 3e-05,
|
| 1646 |
+
"loss": 1.2475,
|
| 1647 |
+
"step": 234
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.98,
|
| 1651 |
+
"grad_norm": 0.015730123295533558,
|
| 1652 |
+
"learning_rate": 3e-05,
|
| 1653 |
+
"loss": 1.3275,
|
| 1654 |
+
"step": 235
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.98,
|
| 1658 |
+
"grad_norm": 0.014412110316894376,
|
| 1659 |
+
"learning_rate": 3e-05,
|
| 1660 |
+
"loss": 1.2307,
|
| 1661 |
+
"step": 236
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.98,
|
| 1665 |
+
"grad_norm": 0.014929677218383007,
|
| 1666 |
+
"learning_rate": 3e-05,
|
| 1667 |
+
"loss": 1.2575,
|
| 1668 |
+
"step": 237
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.99,
|
| 1672 |
+
"grad_norm": 0.015039383819204387,
|
| 1673 |
+
"learning_rate": 3e-05,
|
| 1674 |
+
"loss": 1.2906,
|
| 1675 |
+
"step": 238
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.99,
|
| 1679 |
+
"grad_norm": 0.01682053180538288,
|
| 1680 |
+
"learning_rate": 3e-05,
|
| 1681 |
+
"loss": 1.2758,
|
| 1682 |
+
"step": 239
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 1.0,
|
| 1686 |
+
"grad_norm": 0.014600617493742423,
|
| 1687 |
+
"learning_rate": 3e-05,
|
| 1688 |
+
"loss": 1.2972,
|
| 1689 |
+
"step": 240
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 1.0,
|
| 1693 |
+
"grad_norm": 0.01713356030477511,
|
| 1694 |
+
"learning_rate": 3e-05,
|
| 1695 |
+
"loss": 1.23,
|
| 1696 |
+
"step": 241
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 1.01,
|
| 1700 |
+
"grad_norm": 0.013713370678298656,
|
| 1701 |
+
"learning_rate": 3e-05,
|
| 1702 |
+
"loss": 1.2082,
|
| 1703 |
+
"step": 242
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 1.01,
|
| 1707 |
+
"grad_norm": 0.016029060499359975,
|
| 1708 |
+
"learning_rate": 3e-05,
|
| 1709 |
+
"loss": 1.2185,
|
| 1710 |
+
"step": 243
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 1.01,
|
| 1714 |
+
"grad_norm": 0.01455024577177708,
|
| 1715 |
+
"learning_rate": 3e-05,
|
| 1716 |
+
"loss": 1.3149,
|
| 1717 |
+
"step": 244
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 1.02,
|
| 1721 |
+
"grad_norm": 0.01596055912900773,
|
| 1722 |
+
"learning_rate": 3e-05,
|
| 1723 |
+
"loss": 1.2845,
|
| 1724 |
+
"step": 245
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 1.02,
|
| 1728 |
+
"grad_norm": 0.015210011602171563,
|
| 1729 |
+
"learning_rate": 3e-05,
|
| 1730 |
+
"loss": 1.2585,
|
| 1731 |
+
"step": 246
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 1.03,
|
| 1735 |
+
"grad_norm": 0.015453757198715246,
|
| 1736 |
+
"learning_rate": 3e-05,
|
| 1737 |
+
"loss": 1.2693,
|
| 1738 |
+
"step": 247
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 1.03,
|
| 1742 |
+
"grad_norm": 0.01610457228670694,
|
| 1743 |
+
"learning_rate": 3e-05,
|
| 1744 |
+
"loss": 1.2811,
|
| 1745 |
+
"step": 248
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 1.03,
|
| 1749 |
+
"grad_norm": 0.015836760290716817,
|
| 1750 |
+
"learning_rate": 3e-05,
|
| 1751 |
+
"loss": 1.3358,
|
| 1752 |
+
"step": 249
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 1.04,
|
| 1756 |
+
"grad_norm": 0.015349071831974473,
|
| 1757 |
+
"learning_rate": 3e-05,
|
| 1758 |
+
"loss": 1.2107,
|
| 1759 |
+
"step": 250
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 1.04,
|
| 1763 |
+
"grad_norm": 0.016164039133739174,
|
| 1764 |
+
"learning_rate": 3e-05,
|
| 1765 |
+
"loss": 1.2893,
|
| 1766 |
+
"step": 251
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 1.05,
|
| 1770 |
+
"grad_norm": 0.0159590525586263,
|
| 1771 |
+
"learning_rate": 3e-05,
|
| 1772 |
+
"loss": 1.2611,
|
| 1773 |
+
"step": 252
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 1.05,
|
| 1777 |
+
"grad_norm": 0.01565613651294786,
|
| 1778 |
+
"learning_rate": 3e-05,
|
| 1779 |
+
"loss": 1.2711,
|
| 1780 |
+
"step": 253
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 1.06,
|
| 1784 |
+
"grad_norm": 0.014721531061888017,
|
| 1785 |
+
"learning_rate": 3e-05,
|
| 1786 |
+
"loss": 1.2482,
|
| 1787 |
+
"step": 254
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 1.06,
|
| 1791 |
+
"grad_norm": 0.01753826817531843,
|
| 1792 |
+
"learning_rate": 3e-05,
|
| 1793 |
+
"loss": 1.2687,
|
| 1794 |
+
"step": 255
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 1.06,
|
| 1798 |
+
"grad_norm": 0.015353098066933114,
|
| 1799 |
+
"learning_rate": 3e-05,
|
| 1800 |
+
"loss": 1.2904,
|
| 1801 |
+
"step": 256
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 1.07,
|
| 1805 |
+
"grad_norm": 0.015204215112422145,
|
| 1806 |
+
"learning_rate": 3e-05,
|
| 1807 |
+
"loss": 1.2441,
|
| 1808 |
+
"step": 257
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 1.07,
|
| 1812 |
+
"grad_norm": 0.01627876478176434,
|
| 1813 |
+
"learning_rate": 3e-05,
|
| 1814 |
+
"loss": 1.2617,
|
| 1815 |
+
"step": 258
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 1.08,
|
| 1819 |
+
"grad_norm": 0.015173324308372222,
|
| 1820 |
+
"learning_rate": 3e-05,
|
| 1821 |
+
"loss": 1.2161,
|
| 1822 |
+
"step": 259
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 1.08,
|
| 1826 |
+
"grad_norm": 0.01821412576469944,
|
| 1827 |
+
"learning_rate": 3e-05,
|
| 1828 |
+
"loss": 1.2901,
|
| 1829 |
+
"step": 260
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 1.08,
|
| 1833 |
+
"grad_norm": 0.06506686696796124,
|
| 1834 |
+
"learning_rate": 3e-05,
|
| 1835 |
+
"loss": 1.2874,
|
| 1836 |
+
"step": 261
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 1.09,
|
| 1840 |
+
"grad_norm": 0.01729616604201323,
|
| 1841 |
+
"learning_rate": 3e-05,
|
| 1842 |
+
"loss": 1.2356,
|
| 1843 |
+
"step": 262
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 1.09,
|
| 1847 |
+
"grad_norm": 0.01675033762473565,
|
| 1848 |
+
"learning_rate": 3e-05,
|
| 1849 |
+
"loss": 1.236,
|
| 1850 |
+
"step": 263
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 1.1,
|
| 1854 |
+
"grad_norm": 0.02192888065943148,
|
| 1855 |
+
"learning_rate": 3e-05,
|
| 1856 |
+
"loss": 1.2421,
|
| 1857 |
+
"step": 264
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 1.1,
|
| 1861 |
+
"grad_norm": 0.016455712121954427,
|
| 1862 |
+
"learning_rate": 3e-05,
|
| 1863 |
+
"loss": 1.247,
|
| 1864 |
+
"step": 265
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 1.1,
|
| 1868 |
+
"grad_norm": 0.01814348646038703,
|
| 1869 |
+
"learning_rate": 3e-05,
|
| 1870 |
+
"loss": 1.2485,
|
| 1871 |
+
"step": 266
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 1.11,
|
| 1875 |
+
"grad_norm": 0.01567451038250417,
|
| 1876 |
+
"learning_rate": 3e-05,
|
| 1877 |
+
"loss": 1.3521,
|
| 1878 |
+
"step": 267
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 1.11,
|
| 1882 |
+
"grad_norm": 0.016734589709319087,
|
| 1883 |
+
"learning_rate": 3e-05,
|
| 1884 |
+
"loss": 1.3147,
|
| 1885 |
+
"step": 268
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 1.12,
|
| 1889 |
+
"grad_norm": 0.01665607669544241,
|
| 1890 |
+
"learning_rate": 3e-05,
|
| 1891 |
+
"loss": 1.2557,
|
| 1892 |
+
"step": 269
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 1.12,
|
| 1896 |
+
"grad_norm": 0.015340602915616324,
|
| 1897 |
+
"learning_rate": 3e-05,
|
| 1898 |
+
"loss": 1.217,
|
| 1899 |
+
"step": 270
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 1.13,
|
| 1903 |
+
"grad_norm": 0.015484796323673096,
|
| 1904 |
+
"learning_rate": 3e-05,
|
| 1905 |
+
"loss": 1.2644,
|
| 1906 |
+
"step": 271
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 1.13,
|
| 1910 |
+
"grad_norm": 0.01882586923200815,
|
| 1911 |
+
"learning_rate": 3e-05,
|
| 1912 |
+
"loss": 1.3565,
|
| 1913 |
+
"step": 272
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 1.13,
|
| 1917 |
+
"grad_norm": 0.01809392578664252,
|
| 1918 |
+
"learning_rate": 3e-05,
|
| 1919 |
+
"loss": 1.2218,
|
| 1920 |
+
"step": 273
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 1.14,
|
| 1924 |
+
"grad_norm": 0.01611243987811714,
|
| 1925 |
+
"learning_rate": 3e-05,
|
| 1926 |
+
"loss": 1.3112,
|
| 1927 |
+
"step": 274
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 1.14,
|
| 1931 |
+
"grad_norm": 0.015800275555133508,
|
| 1932 |
+
"learning_rate": 3e-05,
|
| 1933 |
+
"loss": 1.253,
|
| 1934 |
+
"step": 275
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 1.15,
|
| 1938 |
+
"grad_norm": 0.024573084585391664,
|
| 1939 |
+
"learning_rate": 3e-05,
|
| 1940 |
+
"loss": 1.3009,
|
| 1941 |
+
"step": 276
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 1.15,
|
| 1945 |
+
"grad_norm": 0.074452403888149,
|
| 1946 |
+
"learning_rate": 3e-05,
|
| 1947 |
+
"loss": 1.2592,
|
| 1948 |
+
"step": 277
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 1.15,
|
| 1952 |
+
"grad_norm": 0.017056904078373382,
|
| 1953 |
+
"learning_rate": 3e-05,
|
| 1954 |
+
"loss": 1.2774,
|
| 1955 |
+
"step": 278
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 1.16,
|
| 1959 |
+
"grad_norm": 0.01821583975502332,
|
| 1960 |
+
"learning_rate": 3e-05,
|
| 1961 |
+
"loss": 1.1952,
|
| 1962 |
+
"step": 279
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 1.16,
|
| 1966 |
+
"grad_norm": 0.015751526406141428,
|
| 1967 |
+
"learning_rate": 3e-05,
|
| 1968 |
+
"loss": 1.2365,
|
| 1969 |
+
"step": 280
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 1.17,
|
| 1973 |
+
"grad_norm": 0.015753098191682944,
|
| 1974 |
+
"learning_rate": 3e-05,
|
| 1975 |
+
"loss": 1.2847,
|
| 1976 |
+
"step": 281
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 1.17,
|
| 1980 |
+
"grad_norm": 0.01588334509784229,
|
| 1981 |
+
"learning_rate": 3e-05,
|
| 1982 |
+
"loss": 1.3455,
|
| 1983 |
+
"step": 282
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 1.18,
|
| 1987 |
+
"grad_norm": 0.016152905035665025,
|
| 1988 |
+
"learning_rate": 3e-05,
|
| 1989 |
+
"loss": 1.2748,
|
| 1990 |
+
"step": 283
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 1.18,
|
| 1994 |
+
"grad_norm": 0.015193625382186535,
|
| 1995 |
+
"learning_rate": 3e-05,
|
| 1996 |
+
"loss": 1.2911,
|
| 1997 |
+
"step": 284
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 1.18,
|
| 2001 |
+
"grad_norm": 0.015901242732867416,
|
| 2002 |
+
"learning_rate": 3e-05,
|
| 2003 |
+
"loss": 1.2784,
|
| 2004 |
+
"step": 285
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 1.19,
|
| 2008 |
+
"grad_norm": 0.016971976726614598,
|
| 2009 |
+
"learning_rate": 3e-05,
|
| 2010 |
+
"loss": 1.2659,
|
| 2011 |
+
"step": 286
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 1.19,
|
| 2015 |
+
"grad_norm": 0.01612818830639207,
|
| 2016 |
+
"learning_rate": 3e-05,
|
| 2017 |
+
"loss": 1.2668,
|
| 2018 |
+
"step": 287
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 1.2,
|
| 2022 |
+
"grad_norm": 0.017395387712717487,
|
| 2023 |
+
"learning_rate": 3e-05,
|
| 2024 |
+
"loss": 1.3022,
|
| 2025 |
+
"step": 288
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 1.2,
|
| 2029 |
+
"grad_norm": 0.01731193234013385,
|
| 2030 |
+
"learning_rate": 3e-05,
|
| 2031 |
+
"loss": 1.2033,
|
| 2032 |
+
"step": 289
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 1.2,
|
| 2036 |
+
"grad_norm": 0.01651302780868134,
|
| 2037 |
+
"learning_rate": 3e-05,
|
| 2038 |
+
"loss": 1.251,
|
| 2039 |
+
"step": 290
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 1.21,
|
| 2043 |
+
"grad_norm": 0.01646013792423402,
|
| 2044 |
+
"learning_rate": 3e-05,
|
| 2045 |
+
"loss": 1.3053,
|
| 2046 |
+
"step": 291
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 1.21,
|
| 2050 |
+
"grad_norm": 0.016605424458919063,
|
| 2051 |
+
"learning_rate": 3e-05,
|
| 2052 |
+
"loss": 1.2226,
|
| 2053 |
+
"step": 292
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 1.22,
|
| 2057 |
+
"grad_norm": 0.01642401242189507,
|
| 2058 |
+
"learning_rate": 3e-05,
|
| 2059 |
+
"loss": 1.2478,
|
| 2060 |
+
"step": 293
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 1.22,
|
| 2064 |
+
"grad_norm": 0.020526048019968234,
|
| 2065 |
+
"learning_rate": 3e-05,
|
| 2066 |
+
"loss": 1.2803,
|
| 2067 |
+
"step": 294
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 1.23,
|
| 2071 |
+
"grad_norm": 0.015357937815369777,
|
| 2072 |
+
"learning_rate": 3e-05,
|
| 2073 |
+
"loss": 1.3025,
|
| 2074 |
+
"step": 295
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 1.23,
|
| 2078 |
+
"grad_norm": 0.01661270914190639,
|
| 2079 |
+
"learning_rate": 3e-05,
|
| 2080 |
+
"loss": 1.297,
|
| 2081 |
+
"step": 296
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 1.23,
|
| 2085 |
+
"grad_norm": 0.017421945864776314,
|
| 2086 |
+
"learning_rate": 3e-05,
|
| 2087 |
+
"loss": 1.2958,
|
| 2088 |
+
"step": 297
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 1.24,
|
| 2092 |
+
"grad_norm": 0.017204965850903572,
|
| 2093 |
+
"learning_rate": 3e-05,
|
| 2094 |
+
"loss": 1.2675,
|
| 2095 |
+
"step": 298
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 1.24,
|
| 2099 |
+
"grad_norm": 0.016739239213025746,
|
| 2100 |
+
"learning_rate": 3e-05,
|
| 2101 |
+
"loss": 1.2631,
|
| 2102 |
+
"step": 299
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 1.25,
|
| 2106 |
+
"grad_norm": 0.015307923198409266,
|
| 2107 |
+
"learning_rate": 3e-05,
|
| 2108 |
+
"loss": 1.2664,
|
| 2109 |
+
"step": 300
|
| 2110 |
+
}
|
| 2111 |
+
],
|
| 2112 |
+
"logging_steps": 1.0,
|
| 2113 |
+
"max_steps": 480,
|
| 2114 |
+
"num_input_tokens_seen": 0,
|
| 2115 |
+
"num_train_epochs": 2,
|
| 2116 |
+
"save_steps": 50,
|
| 2117 |
+
"total_flos": 4174125975207936.0,
|
| 2118 |
+
"train_batch_size": 2,
|
| 2119 |
+
"trial_name": null,
|
| 2120 |
+
"trial_params": null
|
| 2121 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f90d4a653d19839087d07b1974489ab3f8b268d412a07252ce01e9349951e83
|
| 3 |
+
size 6712
|