Upload 11 files
Browse files- adapter_config.json +31 -0
- adapter_model.safetensors +3 -0
- all_results.json +7 -0
- special_tokens_map.json +30 -0
- tokenizer.model +3 -0
- tokenizer_config.json +43 -0
- train_results.json +7 -0
- trainer_log.jsonl +145 -0
- trainer_state.json +894 -0
- training_args.bin +3 -0
- training_loss.png +0 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "/root/autodl-tmp/SUS-Chat-34B-8bits",
|
| 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": 16.0,
|
| 13 |
+
"lora_dropout": 0.05,
|
| 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 |
+
"o_proj",
|
| 23 |
+
"q_proj",
|
| 24 |
+
"v_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"up_proj",
|
| 27 |
+
"k_proj",
|
| 28 |
+
"gate_proj"
|
| 29 |
+
],
|
| 30 |
+
"task_type": "CAUSAL_LM"
|
| 31 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b187de5e1816d9b1b88702a2c8d366a86f4c0a884fc445d578960200c22db943
|
| 3 |
+
size 1966194576
|
all_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"train_loss": 1.3001856657352238,
|
| 4 |
+
"train_runtime": 3307.5677,
|
| 5 |
+
"train_samples_per_second": 0.219,
|
| 6 |
+
"train_steps_per_second": 0.219
|
| 7 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|startoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
|
| 3 |
+
size 1033105
|
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": "<|startoftext|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "<|endoftext|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"bos_token": "<|startoftext|>",
|
| 31 |
+
"clean_up_tokenization_spaces": false,
|
| 32 |
+
"eos_token": "<|endoftext|>",
|
| 33 |
+
"legacy": true,
|
| 34 |
+
"model_max_length": 4096,
|
| 35 |
+
"pad_token": "<unk>",
|
| 36 |
+
"padding_side": "right",
|
| 37 |
+
"sp_model_kwargs": {},
|
| 38 |
+
"spaces_between_special_tokens": false,
|
| 39 |
+
"split_special_tokens": false,
|
| 40 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 41 |
+
"unk_token": "<unk>",
|
| 42 |
+
"use_default_system_prompt": false
|
| 43 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"train_loss": 1.3001856657352238,
|
| 4 |
+
"train_runtime": 3307.5677,
|
| 5 |
+
"train_samples_per_second": 0.219,
|
| 6 |
+
"train_steps_per_second": 0.219
|
| 7 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,145 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 5, "total_steps": 724, "loss": 1.0216, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00029997740600876073, "epoch": 0.01, "percentage": 0.69, "elapsed_time": "0:00:22", "remaining_time": "0:54:59"}
|
| 2 |
+
{"current_steps": 10, "total_steps": 724, "loss": 2.5373, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00029988562958468534, "epoch": 0.03, "percentage": 1.38, "elapsed_time": "0:00:50", "remaining_time": "1:00:27"}
|
| 3 |
+
{"current_steps": 15, "total_steps": 724, "loss": 1.7185, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002997233017693859, "epoch": 0.04, "percentage": 2.07, "elapsed_time": "0:01:14", "remaining_time": "0:58:54"}
|
| 4 |
+
{"current_steps": 20, "total_steps": 724, "loss": 2.0243, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002995426927466334, "epoch": 0.06, "percentage": 2.76, "elapsed_time": "0:01:36", "remaining_time": "0:56:50"}
|
| 5 |
+
{"current_steps": 25, "total_steps": 724, "loss": 2.2346, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002992535872688052, "epoch": 0.07, "percentage": 3.45, "elapsed_time": "0:02:02", "remaining_time": "0:56:55"}
|
| 6 |
+
{"current_steps": 30, "total_steps": 724, "loss": 1.9241, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002988942279030214, "epoch": 0.08, "percentage": 4.14, "elapsed_time": "0:02:27", "remaining_time": "0:56:45"}
|
| 7 |
+
{"current_steps": 35, "total_steps": 724, "loss": 1.8485, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00029855627017138267, "epoch": 0.1, "percentage": 4.83, "elapsed_time": "0:02:52", "remaining_time": "0:56:30"}
|
| 8 |
+
{"current_steps": 40, "total_steps": 724, "loss": 2.1848, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00029827342660583437, "epoch": 0.11, "percentage": 5.52, "elapsed_time": "0:03:15", "remaining_time": "0:55:50"}
|
| 9 |
+
{"current_steps": 45, "total_steps": 724, "loss": 5.0877, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002979654571005535, "epoch": 0.12, "percentage": 6.22, "elapsed_time": "0:03:36", "remaining_time": "0:54:30"}
|
| 10 |
+
{"current_steps": 50, "total_steps": 724, "loss": 1.7997, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002973964828376827, "epoch": 0.14, "percentage": 6.91, "elapsed_time": "0:04:00", "remaining_time": "0:53:58"}
|
| 11 |
+
{"current_steps": 55, "total_steps": 724, "loss": 1.7931, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00029675812882870453, "epoch": 0.15, "percentage": 7.6, "elapsed_time": "0:04:25", "remaining_time": "0:53:45"}
|
| 12 |
+
{"current_steps": 60, "total_steps": 724, "loss": 1.2798, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.000296050695547811, "epoch": 0.17, "percentage": 8.29, "elapsed_time": "0:04:47", "remaining_time": "0:53:03"}
|
| 13 |
+
{"current_steps": 65, "total_steps": 724, "loss": 1.6239, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00029527451598491093, "epoch": 0.18, "percentage": 8.98, "elapsed_time": "0:05:11", "remaining_time": "0:52:34"}
|
| 14 |
+
{"current_steps": 70, "total_steps": 724, "loss": 0.7037, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002944299554888919, "epoch": 0.19, "percentage": 9.67, "elapsed_time": "0:05:29", "remaining_time": "0:51:17"}
|
| 15 |
+
{"current_steps": 75, "total_steps": 724, "loss": 1.9876, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00029351741159564925, "epoch": 0.21, "percentage": 10.36, "elapsed_time": "0:05:52", "remaining_time": "0:50:47"}
|
| 16 |
+
{"current_steps": 80, "total_steps": 724, "loss": 1.3241, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00029253731384096574, "epoch": 0.22, "percentage": 11.05, "elapsed_time": "0:06:15", "remaining_time": "0:50:23"}
|
| 17 |
+
{"current_steps": 85, "total_steps": 724, "loss": 1.7376, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00029149012355832816, "epoch": 0.23, "percentage": 11.74, "elapsed_time": "0:06:37", "remaining_time": "0:49:48"}
|
| 18 |
+
{"current_steps": 90, "total_steps": 724, "loss": 1.8011, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00029037633366177726, "epoch": 0.25, "percentage": 12.43, "elapsed_time": "0:07:03", "remaining_time": "0:49:44"}
|
| 19 |
+
{"current_steps": 95, "total_steps": 724, "loss": 1.0738, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00028919646841389207, "epoch": 0.26, "percentage": 13.12, "elapsed_time": "0:07:25", "remaining_time": "0:49:12"}
|
| 20 |
+
{"current_steps": 100, "total_steps": 724, "loss": 1.0997, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002879510831790189, "epoch": 0.28, "percentage": 13.81, "elapsed_time": "0:07:43", "remaining_time": "0:48:10"}
|
| 21 |
+
{"current_steps": 105, "total_steps": 724, "loss": 1.7646, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002866407641618605, "epoch": 0.29, "percentage": 14.5, "elapsed_time": "0:08:07", "remaining_time": "0:47:54"}
|
| 22 |
+
{"current_steps": 110, "total_steps": 724, "loss": 1.114, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002852661281315485, "epoch": 0.3, "percentage": 15.19, "elapsed_time": "0:08:31", "remaining_time": "0:47:33"}
|
| 23 |
+
{"current_steps": 115, "total_steps": 724, "loss": 1.6206, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00028382782213132933, "epoch": 0.32, "percentage": 15.88, "elapsed_time": "0:08:54", "remaining_time": "0:47:12"}
|
| 24 |
+
{"current_steps": 120, "total_steps": 724, "loss": 1.9232, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002823265231740001, "epoch": 0.33, "percentage": 16.57, "elapsed_time": "0:09:20", "remaining_time": "0:47:02"}
|
| 25 |
+
{"current_steps": 125, "total_steps": 724, "loss": 1.9719, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00028076293792323744, "epoch": 0.35, "percentage": 17.27, "elapsed_time": "0:09:47", "remaining_time": "0:46:53"}
|
| 26 |
+
{"current_steps": 130, "total_steps": 724, "loss": 1.5214, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00027913780236097003, "epoch": 0.36, "percentage": 17.96, "elapsed_time": "0:10:08", "remaining_time": "0:46:22"}
|
| 27 |
+
{"current_steps": 135, "total_steps": 724, "loss": 1.7809, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002774518814409507, "epoch": 0.37, "percentage": 18.65, "elapsed_time": "0:10:30", "remaining_time": "0:45:51"}
|
| 28 |
+
{"current_steps": 140, "total_steps": 724, "loss": 1.7594, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002757059687286915, "epoch": 0.39, "percentage": 19.34, "elapsed_time": "0:10:53", "remaining_time": "0:45:26"}
|
| 29 |
+
{"current_steps": 145, "total_steps": 724, "loss": 1.888, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002739008860279314, "epoch": 0.4, "percentage": 20.03, "elapsed_time": "0:11:17", "remaining_time": "0:45:04"}
|
| 30 |
+
{"current_steps": 150, "total_steps": 724, "loss": 1.3209, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002720374829938119, "epoch": 0.41, "percentage": 20.72, "elapsed_time": "0:11:39", "remaining_time": "0:44:35"}
|
| 31 |
+
{"current_steps": 155, "total_steps": 724, "loss": 1.668, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00027011663673294316, "epoch": 0.43, "percentage": 21.41, "elapsed_time": "0:12:01", "remaining_time": "0:44:07"}
|
| 32 |
+
{"current_steps": 160, "total_steps": 724, "loss": 1.5554, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00026813925139054844, "epoch": 0.44, "percentage": 22.1, "elapsed_time": "0:12:26", "remaining_time": "0:43:52"}
|
| 33 |
+
{"current_steps": 165, "total_steps": 724, "loss": 1.8724, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002661062577248818, "epoch": 0.46, "percentage": 22.79, "elapsed_time": "0:12:52", "remaining_time": "0:43:36"}
|
| 34 |
+
{"current_steps": 170, "total_steps": 724, "loss": 1.1475, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002640186126691185, "epoch": 0.47, "percentage": 23.48, "elapsed_time": "0:13:13", "remaining_time": "0:43:06"}
|
| 35 |
+
{"current_steps": 175, "total_steps": 724, "loss": 1.5851, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002618772988809255, "epoch": 0.48, "percentage": 24.17, "elapsed_time": "0:13:35", "remaining_time": "0:42:39"}
|
| 36 |
+
{"current_steps": 180, "total_steps": 724, "loss": 1.1434, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002596833242799227, "epoch": 0.5, "percentage": 24.86, "elapsed_time": "0:13:57", "remaining_time": "0:42:10"}
|
| 37 |
+
{"current_steps": 185, "total_steps": 724, "loss": 2.0189, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002574377215732538, "epoch": 0.51, "percentage": 25.55, "elapsed_time": "0:14:22", "remaining_time": "0:41:51"}
|
| 38 |
+
{"current_steps": 190, "total_steps": 724, "loss": 1.1961, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002551415477694895, "epoch": 0.52, "percentage": 26.24, "elapsed_time": "0:14:42", "remaining_time": "0:41:19"}
|
| 39 |
+
{"current_steps": 195, "total_steps": 724, "loss": 1.626, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.000252795883681092, "epoch": 0.54, "percentage": 26.93, "elapsed_time": "0:15:08", "remaining_time": "0:41:04"}
|
| 40 |
+
{"current_steps": 200, "total_steps": 724, "loss": 1.6993, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002504018334156746, "epoch": 0.55, "percentage": 27.62, "elapsed_time": "0:15:32", "remaining_time": "0:40:44"}
|
| 41 |
+
{"current_steps": 205, "total_steps": 724, "loss": 1.3994, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00024796052385629735, "epoch": 0.57, "percentage": 28.31, "elapsed_time": "0:15:53", "remaining_time": "0:40:14"}
|
| 42 |
+
{"current_steps": 210, "total_steps": 724, "loss": 1.0801, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00024547310413104055, "epoch": 0.58, "percentage": 29.01, "elapsed_time": "0:16:14", "remaining_time": "0:39:44"}
|
| 43 |
+
{"current_steps": 215, "total_steps": 724, "loss": 1.9244, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002429407450721093, "epoch": 0.59, "percentage": 29.7, "elapsed_time": "0:16:38", "remaining_time": "0:39:24"}
|
| 44 |
+
{"current_steps": 220, "total_steps": 724, "loss": 1.3285, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00024036463866472033, "epoch": 0.61, "percentage": 30.39, "elapsed_time": "0:17:01", "remaining_time": "0:38:59"}
|
| 45 |
+
{"current_steps": 225, "total_steps": 724, "loss": 1.3708, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00023774599748603331, "epoch": 0.62, "percentage": 31.08, "elapsed_time": "0:17:24", "remaining_time": "0:38:36"}
|
| 46 |
+
{"current_steps": 230, "total_steps": 724, "loss": 1.2642, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002350860541343886, "epoch": 0.64, "percentage": 31.77, "elapsed_time": "0:17:45", "remaining_time": "0:38:07"}
|
| 47 |
+
{"current_steps": 235, "total_steps": 724, "loss": 1.2535, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002323860606491215, "epoch": 0.65, "percentage": 32.46, "elapsed_time": "0:18:07", "remaining_time": "0:37:43"}
|
| 48 |
+
{"current_steps": 240, "total_steps": 724, "loss": 1.7609, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002296472879212254, "epoch": 0.66, "percentage": 33.15, "elapsed_time": "0:18:31", "remaining_time": "0:37:21"}
|
| 49 |
+
{"current_steps": 245, "total_steps": 724, "loss": 1.7628, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00022687102509514156, "epoch": 0.68, "percentage": 33.84, "elapsed_time": "0:18:58", "remaining_time": "0:37:05"}
|
| 50 |
+
{"current_steps": 250, "total_steps": 724, "loss": 1.3396, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00022405857896195673, "epoch": 0.69, "percentage": 34.53, "elapsed_time": "0:19:19", "remaining_time": "0:36:37"}
|
| 51 |
+
{"current_steps": 255, "total_steps": 724, "loss": 1.516, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002212112733442949, "epoch": 0.7, "percentage": 35.22, "elapsed_time": "0:19:39", "remaining_time": "0:36:08"}
|
| 52 |
+
{"current_steps": 260, "total_steps": 724, "loss": 1.7484, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00021833044847319164, "epoch": 0.72, "percentage": 35.91, "elapsed_time": "0:20:01", "remaining_time": "0:35:44"}
|
| 53 |
+
{"current_steps": 265, "total_steps": 724, "loss": 0.7856, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002154174603572456, "epoch": 0.73, "percentage": 36.6, "elapsed_time": "0:20:22", "remaining_time": "0:35:17"}
|
| 54 |
+
{"current_steps": 270, "total_steps": 724, "loss": 1.8457, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00021247368014434316, "epoch": 0.75, "percentage": 37.29, "elapsed_time": "0:20:47", "remaining_time": "0:34:57"}
|
| 55 |
+
{"current_steps": 275, "total_steps": 724, "loss": 0.8756, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.000209500493476257, "epoch": 0.76, "percentage": 37.98, "elapsed_time": "0:21:07", "remaining_time": "0:34:28"}
|
| 56 |
+
{"current_steps": 280, "total_steps": 724, "loss": 1.5258, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00020649929983642242, "epoch": 0.77, "percentage": 38.67, "elapsed_time": "0:21:29", "remaining_time": "0:34:04"}
|
| 57 |
+
{"current_steps": 285, "total_steps": 724, "loss": 1.3208, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00020347151189119853, "epoch": 0.79, "percentage": 39.36, "elapsed_time": "0:21:48", "remaining_time": "0:33:36"}
|
| 58 |
+
{"current_steps": 290, "total_steps": 724, "loss": 1.3849, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00020041855482492402, "epoch": 0.8, "percentage": 40.06, "elapsed_time": "0:22:11", "remaining_time": "0:33:13"}
|
| 59 |
+
{"current_steps": 295, "total_steps": 724, "loss": 1.3585, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019734186566908047, "epoch": 0.81, "percentage": 40.75, "elapsed_time": "0:22:33", "remaining_time": "0:32:48"}
|
| 60 |
+
{"current_steps": 300, "total_steps": 724, "loss": 2.0685, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019424289262587994, "epoch": 0.83, "percentage": 41.44, "elapsed_time": "0:22:57", "remaining_time": "0:32:26"}
|
| 61 |
+
{"current_steps": 305, "total_steps": 724, "loss": 0.9159, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019112309438659375, "epoch": 0.84, "percentage": 42.13, "elapsed_time": "0:23:17", "remaining_time": "0:32:00"}
|
| 62 |
+
{"current_steps": 310, "total_steps": 724, "loss": 1.5168, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001879839394449442, "epoch": 0.86, "percentage": 42.82, "elapsed_time": "0:23:40", "remaining_time": "0:31:36"}
|
| 63 |
+
{"current_steps": 315, "total_steps": 724, "loss": 1.4267, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001848269054058826, "epoch": 0.87, "percentage": 43.51, "elapsed_time": "0:24:02", "remaining_time": "0:31:13"}
|
| 64 |
+
{"current_steps": 320, "total_steps": 724, "loss": 1.4472, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00018165347829007832, "epoch": 0.88, "percentage": 44.2, "elapsed_time": "0:24:24", "remaining_time": "0:30:49"}
|
| 65 |
+
{"current_steps": 325, "total_steps": 724, "loss": 2.0622, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00017846515183444648, "epoch": 0.9, "percentage": 44.89, "elapsed_time": "0:24:48", "remaining_time": "0:30:27"}
|
| 66 |
+
{"current_steps": 330, "total_steps": 724, "loss": 1.1134, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00017526342678904396, "epoch": 0.91, "percentage": 45.58, "elapsed_time": "0:25:10", "remaining_time": "0:30:03"}
|
| 67 |
+
{"current_steps": 335, "total_steps": 724, "loss": 1.7789, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00017204981021066401, "epoch": 0.93, "percentage": 46.27, "elapsed_time": "0:25:35", "remaining_time": "0:29:43"}
|
| 68 |
+
{"current_steps": 340, "total_steps": 724, "loss": 0.9645, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00016882581475346223, "epoch": 0.94, "percentage": 46.96, "elapsed_time": "0:25:54", "remaining_time": "0:29:16"}
|
| 69 |
+
{"current_steps": 345, "total_steps": 724, "loss": 2.0169, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00016559295795694825, "epoch": 0.95, "percentage": 47.65, "elapsed_time": "0:26:20", "remaining_time": "0:28:56"}
|
| 70 |
+
{"current_steps": 350, "total_steps": 724, "loss": 1.1319, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00016235276153167723, "epoch": 0.97, "percentage": 48.34, "elapsed_time": "0:26:43", "remaining_time": "0:28:33"}
|
| 71 |
+
{"current_steps": 355, "total_steps": 724, "loss": 1.7811, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00015910675064297877, "epoch": 0.98, "percentage": 49.03, "elapsed_time": "0:27:07", "remaining_time": "0:28:11"}
|
| 72 |
+
{"current_steps": 360, "total_steps": 724, "loss": 1.1135, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00015585645319305912, "epoch": 0.99, "percentage": 49.72, "elapsed_time": "0:27:27", "remaining_time": "0:27:45"}
|
| 73 |
+
{"current_steps": 365, "total_steps": 724, "loss": 0.9838, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00015260339910181528, "epoch": 1.01, "percentage": 50.41, "elapsed_time": "0:27:48", "remaining_time": "0:27:21"}
|
| 74 |
+
{"current_steps": 370, "total_steps": 724, "loss": 2.0867, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00014934911958669966, "epoch": 1.02, "percentage": 51.1, "elapsed_time": "0:28:16", "remaining_time": "0:27:02"}
|
| 75 |
+
{"current_steps": 375, "total_steps": 724, "loss": 1.8194, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001460951464419732, "epoch": 1.04, "percentage": 51.8, "elapsed_time": "0:28:40", "remaining_time": "0:26:41"}
|
| 76 |
+
{"current_steps": 380, "total_steps": 724, "loss": 0.7124, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00014284301131768816, "epoch": 1.05, "percentage": 52.49, "elapsed_time": "0:29:00", "remaining_time": "0:26:15"}
|
| 77 |
+
{"current_steps": 385, "total_steps": 724, "loss": 0.8251, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00013959424499873757, "epoch": 1.06, "percentage": 53.18, "elapsed_time": "0:29:21", "remaining_time": "0:25:50"}
|
| 78 |
+
{"current_steps": 390, "total_steps": 724, "loss": 1.6568, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00013635037668431298, "epoch": 1.08, "percentage": 53.87, "elapsed_time": "0:29:47", "remaining_time": "0:25:30"}
|
| 79 |
+
{"current_steps": 395, "total_steps": 724, "loss": 0.9041, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00013311293326810758, "epoch": 1.09, "percentage": 54.56, "elapsed_time": "0:30:09", "remaining_time": "0:25:07"}
|
| 80 |
+
{"current_steps": 400, "total_steps": 724, "loss": 0.5734, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00012988343861960544, "epoch": 1.1, "percentage": 55.25, "elapsed_time": "0:30:30", "remaining_time": "0:24:42"}
|
| 81 |
+
{"current_steps": 405, "total_steps": 724, "loss": 1.5422, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00012666341286679376, "epoch": 1.12, "percentage": 55.94, "elapsed_time": "0:30:56", "remaining_time": "0:24:21"}
|
| 82 |
+
{"current_steps": 410, "total_steps": 724, "loss": 1.0433, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00012345437168063614, "epoch": 1.13, "percentage": 56.63, "elapsed_time": "0:31:18", "remaining_time": "0:23:58"}
|
| 83 |
+
{"current_steps": 415, "total_steps": 724, "loss": 0.6305, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00012025782556164437, "epoch": 1.15, "percentage": 57.32, "elapsed_time": "0:31:39", "remaining_time": "0:23:34"}
|
| 84 |
+
{"current_steps": 420, "total_steps": 724, "loss": 0.7021, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00011707527912888316, "epoch": 1.16, "percentage": 58.01, "elapsed_time": "0:32:00", "remaining_time": "0:23:10"}
|
| 85 |
+
{"current_steps": 425, "total_steps": 724, "loss": 1.7926, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00011390823041174384, "epoch": 1.17, "percentage": 58.7, "elapsed_time": "0:32:26", "remaining_time": "0:22:49"}
|
| 86 |
+
{"current_steps": 430, "total_steps": 724, "loss": 0.7126, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00011075817014481984, "epoch": 1.19, "percentage": 59.39, "elapsed_time": "0:32:48", "remaining_time": "0:22:25"}
|
| 87 |
+
{"current_steps": 435, "total_steps": 724, "loss": 0.9281, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00010762658106621541, "epoch": 1.2, "percentage": 60.08, "elapsed_time": "0:33:10", "remaining_time": "0:22:02"}
|
| 88 |
+
{"current_steps": 440, "total_steps": 724, "loss": 1.2706, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00010451493721961883, "epoch": 1.22, "percentage": 60.77, "elapsed_time": "0:33:33", "remaining_time": "0:21:39"}
|
| 89 |
+
{"current_steps": 445, "total_steps": 724, "loss": 0.7369, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00010142470326046745, "epoch": 1.23, "percentage": 61.46, "elapsed_time": "0:33:53", "remaining_time": "0:21:15"}
|
| 90 |
+
{"current_steps": 450, "total_steps": 724, "loss": 1.3282, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.835733376653254e-05, "epoch": 1.24, "percentage": 62.15, "elapsed_time": "0:34:17", "remaining_time": "0:20:52"}
|
| 91 |
+
{"current_steps": 455, "total_steps": 724, "loss": 1.5328, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.531427255324734e-05, "epoch": 1.26, "percentage": 62.85, "elapsed_time": "0:34:41", "remaining_time": "0:20:30"}
|
| 92 |
+
{"current_steps": 460, "total_steps": 724, "loss": 0.81, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.229695199410055e-05, "epoch": 1.27, "percentage": 63.54, "elapsed_time": "0:35:05", "remaining_time": "0:20:08"}
|
| 93 |
+
{"current_steps": 465, "total_steps": 724, "loss": 1.4783, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.930679234641647e-05, "epoch": 1.28, "percentage": 64.23, "elapsed_time": "0:35:31", "remaining_time": "0:19:47"}
|
| 94 |
+
{"current_steps": 470, "total_steps": 724, "loss": 0.9337, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.634520108283753e-05, "epoch": 1.3, "percentage": 64.92, "elapsed_time": "0:35:53", "remaining_time": "0:19:23"}
|
| 95 |
+
{"current_steps": 475, "total_steps": 724, "loss": 0.7309, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.341357222882468e-05, "epoch": 1.31, "percentage": 65.61, "elapsed_time": "0:36:16", "remaining_time": "0:19:00"}
|
| 96 |
+
{"current_steps": 480, "total_steps": 724, "loss": 0.5978, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.051328570648772e-05, "epoch": 1.33, "percentage": 66.3, "elapsed_time": "0:36:39", "remaining_time": "0:18:37"}
|
| 97 |
+
{"current_steps": 485, "total_steps": 724, "loss": 0.7613, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.764570668505381e-05, "epoch": 1.34, "percentage": 66.99, "elapsed_time": "0:37:01", "remaining_time": "0:18:14"}
|
| 98 |
+
{"current_steps": 490, "total_steps": 724, "loss": 0.9437, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.481218493828025e-05, "epoch": 1.35, "percentage": 67.68, "elapsed_time": "0:37:24", "remaining_time": "0:17:51"}
|
| 99 |
+
{"current_steps": 495, "total_steps": 724, "loss": 1.6472, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.201405420911382e-05, "epoch": 1.37, "percentage": 68.37, "elapsed_time": "0:37:48", "remaining_time": "0:17:29"}
|
| 100 |
+
{"current_steps": 500, "total_steps": 724, "loss": 0.5782, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.925263158189641e-05, "epoch": 1.38, "percentage": 69.06, "elapsed_time": "0:38:09", "remaining_time": "0:17:05"}
|
| 101 |
+
{"current_steps": 505, "total_steps": 724, "loss": 0.6908, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.652921686241072e-05, "epoch": 1.4, "percentage": 69.75, "elapsed_time": "0:38:30", "remaining_time": "0:16:42"}
|
| 102 |
+
{"current_steps": 510, "total_steps": 724, "loss": 0.912, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.384509196606036e-05, "epoch": 1.41, "percentage": 70.44, "elapsed_time": "0:38:53", "remaining_time": "0:16:18"}
|
| 103 |
+
{"current_steps": 515, "total_steps": 724, "loss": 1.3509, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.120152031447023e-05, "epoch": 1.42, "percentage": 71.13, "elapsed_time": "0:39:16", "remaining_time": "0:15:56"}
|
| 104 |
+
{"current_steps": 520, "total_steps": 724, "loss": 1.2476, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.859974624079157e-05, "epoch": 1.44, "percentage": 71.82, "elapsed_time": "0:39:41", "remaining_time": "0:15:34"}
|
| 105 |
+
{"current_steps": 525, "total_steps": 724, "loss": 1.3992, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.604099440399325e-05, "epoch": 1.45, "percentage": 72.51, "elapsed_time": "0:40:06", "remaining_time": "0:15:12"}
|
| 106 |
+
{"current_steps": 530, "total_steps": 724, "loss": 0.8079, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.352646921241234e-05, "epoch": 1.46, "percentage": 73.2, "elapsed_time": "0:40:25", "remaining_time": "0:14:47"}
|
| 107 |
+
{"current_steps": 535, "total_steps": 724, "loss": 1.3463, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.1057354256837416e-05, "epoch": 1.48, "percentage": 73.9, "elapsed_time": "0:40:49", "remaining_time": "0:14:25"}
|
| 108 |
+
{"current_steps": 540, "total_steps": 724, "loss": 0.5269, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8634811753390915e-05, "epoch": 1.49, "percentage": 74.59, "elapsed_time": "0:41:10", "remaining_time": "0:14:01"}
|
| 109 |
+
{"current_steps": 545, "total_steps": 724, "loss": 0.9968, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.6259981996471896e-05, "epoch": 1.51, "percentage": 75.28, "elapsed_time": "0:41:35", "remaining_time": "0:13:39"}
|
| 110 |
+
{"current_steps": 550, "total_steps": 724, "loss": 0.4794, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.3933982822017876e-05, "epoch": 1.52, "percentage": 75.97, "elapsed_time": "0:41:58", "remaining_time": "0:13:16"}
|
| 111 |
+
{"current_steps": 555, "total_steps": 724, "loss": 1.77, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.165790908133783e-05, "epoch": 1.53, "percentage": 76.66, "elapsed_time": "0:42:24", "remaining_time": "0:12:54"}
|
| 112 |
+
{"current_steps": 560, "total_steps": 724, "loss": 1.4066, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.943283212576392e-05, "epoch": 1.55, "percentage": 77.35, "elapsed_time": "0:42:49", "remaining_time": "0:12:32"}
|
| 113 |
+
{"current_steps": 565, "total_steps": 724, "loss": 1.0347, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.725979930236496e-05, "epoch": 1.56, "percentage": 78.04, "elapsed_time": "0:43:13", "remaining_time": "0:12:09"}
|
| 114 |
+
{"current_steps": 570, "total_steps": 724, "loss": 0.3513, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.513983346095838e-05, "epoch": 1.57, "percentage": 78.73, "elapsed_time": "0:43:31", "remaining_time": "0:11:45"}
|
| 115 |
+
{"current_steps": 575, "total_steps": 724, "loss": 0.387, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.307393247265362e-05, "epoch": 1.59, "percentage": 79.42, "elapsed_time": "0:43:50", "remaining_time": "0:11:21"}
|
| 116 |
+
{"current_steps": 580, "total_steps": 724, "loss": 0.9932, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.106306876015212e-05, "epoch": 1.6, "percentage": 80.11, "elapsed_time": "0:44:12", "remaining_time": "0:10:58"}
|
| 117 |
+
{"current_steps": 585, "total_steps": 724, "loss": 0.7613, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9108188840027074e-05, "epoch": 1.62, "percentage": 80.8, "elapsed_time": "0:44:34", "remaining_time": "0:10:35"}
|
| 118 |
+
{"current_steps": 590, "total_steps": 724, "loss": 1.3139, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.72102128771965e-05, "epoch": 1.63, "percentage": 81.49, "elapsed_time": "0:44:57", "remaining_time": "0:10:12"}
|
| 119 |
+
{"current_steps": 595, "total_steps": 724, "loss": 1.3463, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5370034251799865e-05, "epoch": 1.64, "percentage": 82.18, "elapsed_time": "0:45:21", "remaining_time": "0:09:50"}
|
| 120 |
+
{"current_steps": 600, "total_steps": 724, "loss": 1.3703, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3588519138683276e-05, "epoch": 1.66, "percentage": 82.87, "elapsed_time": "0:45:48", "remaining_time": "0:09:28"}
|
| 121 |
+
{"current_steps": 605, "total_steps": 724, "loss": 0.3998, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.18665060996893e-05, "epoch": 1.67, "percentage": 83.56, "elapsed_time": "0:46:11", "remaining_time": "0:09:05"}
|
| 122 |
+
{"current_steps": 610, "total_steps": 724, "loss": 1.1889, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.020480568894461e-05, "epoch": 1.69, "percentage": 84.25, "elapsed_time": "0:46:33", "remaining_time": "0:08:42"}
|
| 123 |
+
{"current_steps": 615, "total_steps": 724, "loss": 0.8979, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.860420007133131e-05, "epoch": 1.7, "percentage": 84.94, "elapsed_time": "0:46:55", "remaining_time": "0:08:19"}
|
| 124 |
+
{"current_steps": 620, "total_steps": 724, "loss": 1.1826, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7065442654320334e-05, "epoch": 1.71, "percentage": 85.64, "elapsed_time": "0:47:19", "remaining_time": "0:07:56"}
|
| 125 |
+
{"current_steps": 625, "total_steps": 724, "loss": 0.5617, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5589257733341694e-05, "epoch": 1.73, "percentage": 86.33, "elapsed_time": "0:47:39", "remaining_time": "0:07:32"}
|
| 126 |
+
{"current_steps": 630, "total_steps": 724, "loss": 0.8612, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.417634015085734e-05, "epoch": 1.74, "percentage": 87.02, "elapsed_time": "0:48:02", "remaining_time": "0:07:10"}
|
| 127 |
+
{"current_steps": 635, "total_steps": 724, "loss": 1.152, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2827354969297953e-05, "epoch": 1.75, "percentage": 87.71, "elapsed_time": "0:48:25", "remaining_time": "0:06:47"}
|
| 128 |
+
{"current_steps": 640, "total_steps": 724, "loss": 1.5859, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1542937158016895e-05, "epoch": 1.77, "percentage": 88.4, "elapsed_time": "0:48:51", "remaining_time": "0:06:24"}
|
| 129 |
+
{"current_steps": 645, "total_steps": 724, "loss": 1.3262, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.032369129440928e-05, "epoch": 1.78, "percentage": 89.09, "elapsed_time": "0:49:16", "remaining_time": "0:06:02"}
|
| 130 |
+
{"current_steps": 650, "total_steps": 724, "loss": 0.7804, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.170191279336458e-06, "epoch": 1.8, "percentage": 89.78, "elapsed_time": "0:49:37", "remaining_time": "0:05:39"}
|
| 131 |
+
{"current_steps": 655, "total_steps": 724, "loss": 0.6581, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.082980066989987e-06, "epoch": 1.81, "percentage": 90.47, "elapsed_time": "0:49:59", "remaining_time": "0:05:16"}
|
| 132 |
+
{"current_steps": 660, "total_steps": 724, "loss": 0.7062, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.062569409322394e-06, "epoch": 1.82, "percentage": 91.16, "elapsed_time": "0:50:21", "remaining_time": "0:04:53"}
|
| 133 |
+
{"current_steps": 665, "total_steps": 724, "loss": 0.5249, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.109439615164524e-06, "epoch": 1.84, "percentage": 91.85, "elapsed_time": "0:50:46", "remaining_time": "0:04:30"}
|
| 134 |
+
{"current_steps": 670, "total_steps": 724, "loss": 0.6158, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.224039324143692e-06, "epoch": 1.85, "percentage": 92.54, "elapsed_time": "0:51:06", "remaining_time": "0:04:07"}
|
| 135 |
+
{"current_steps": 675, "total_steps": 724, "loss": 1.0754, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.406785295508275e-06, "epoch": 1.86, "percentage": 93.23, "elapsed_time": "0:51:29", "remaining_time": "0:03:44"}
|
| 136 |
+
{"current_steps": 680, "total_steps": 724, "loss": 1.3947, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.6580622119583847e-06, "epoch": 1.88, "percentage": 93.92, "elapsed_time": "0:51:54", "remaining_time": "0:03:21"}
|
| 137 |
+
{"current_steps": 685, "total_steps": 724, "loss": 1.1482, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9782224985753224e-06, "epoch": 1.89, "percentage": 94.61, "elapsed_time": "0:52:18", "remaining_time": "0:02:58"}
|
| 138 |
+
{"current_steps": 690, "total_steps": 724, "loss": 0.7185, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.367586156934409e-06, "epoch": 1.91, "percentage": 95.3, "elapsed_time": "0:52:39", "remaining_time": "0:02:35"}
|
| 139 |
+
{"current_steps": 695, "total_steps": 724, "loss": 0.2661, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8264406144798238e-06, "epoch": 1.92, "percentage": 95.99, "elapsed_time": "0:52:58", "remaining_time": "0:02:12"}
|
| 140 |
+
{"current_steps": 700, "total_steps": 724, "loss": 1.0511, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3550405892321591e-06, "epoch": 1.93, "percentage": 96.69, "elapsed_time": "0:53:22", "remaining_time": "0:01:49"}
|
| 141 |
+
{"current_steps": 705, "total_steps": 724, "loss": 0.7304, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.536079698920951e-07, "epoch": 1.95, "percentage": 97.38, "elapsed_time": "0:53:42", "remaining_time": "0:01:26"}
|
| 142 |
+
{"current_steps": 710, "total_steps": 724, "loss": 1.0044, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.223317113971948e-07, "epoch": 1.96, "percentage": 98.07, "elapsed_time": "0:54:04", "remaining_time": "0:01:03"}
|
| 143 |
+
{"current_steps": 715, "total_steps": 724, "loss": 0.4553, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.6136774598043427e-07, "epoch": 1.98, "percentage": 98.76, "elapsed_time": "0:54:24", "remaining_time": "0:00:41"}
|
| 144 |
+
{"current_steps": 720, "total_steps": 724, "loss": 0.9209, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7083890977278027e-07, "epoch": 1.99, "percentage": 99.45, "elapsed_time": "0:54:47", "remaining_time": "0:00:18"}
|
| 145 |
+
{"current_steps": 724, "total_steps": 724, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:55:07", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,894 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 724,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 0.00029997740600876073,
|
| 14 |
+
"loss": 1.0216,
|
| 15 |
+
"step": 5
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.03,
|
| 19 |
+
"learning_rate": 0.00029988562958468534,
|
| 20 |
+
"loss": 2.5373,
|
| 21 |
+
"step": 10
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.04,
|
| 25 |
+
"learning_rate": 0.0002997233017693859,
|
| 26 |
+
"loss": 1.7185,
|
| 27 |
+
"step": 15
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.06,
|
| 31 |
+
"learning_rate": 0.0002995426927466334,
|
| 32 |
+
"loss": 2.0243,
|
| 33 |
+
"step": 20
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.07,
|
| 37 |
+
"learning_rate": 0.0002992535872688052,
|
| 38 |
+
"loss": 2.2346,
|
| 39 |
+
"step": 25
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.08,
|
| 43 |
+
"learning_rate": 0.0002988942279030214,
|
| 44 |
+
"loss": 1.9241,
|
| 45 |
+
"step": 30
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.1,
|
| 49 |
+
"learning_rate": 0.00029855627017138267,
|
| 50 |
+
"loss": 1.8485,
|
| 51 |
+
"step": 35
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.11,
|
| 55 |
+
"learning_rate": 0.00029827342660583437,
|
| 56 |
+
"loss": 2.1848,
|
| 57 |
+
"step": 40
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.12,
|
| 61 |
+
"learning_rate": 0.0002979654571005535,
|
| 62 |
+
"loss": 5.0877,
|
| 63 |
+
"step": 45
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.14,
|
| 67 |
+
"learning_rate": 0.0002973964828376827,
|
| 68 |
+
"loss": 1.7997,
|
| 69 |
+
"step": 50
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.15,
|
| 73 |
+
"learning_rate": 0.00029675812882870453,
|
| 74 |
+
"loss": 1.7931,
|
| 75 |
+
"step": 55
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.17,
|
| 79 |
+
"learning_rate": 0.000296050695547811,
|
| 80 |
+
"loss": 1.2798,
|
| 81 |
+
"step": 60
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.18,
|
| 85 |
+
"learning_rate": 0.00029527451598491093,
|
| 86 |
+
"loss": 1.6239,
|
| 87 |
+
"step": 65
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.19,
|
| 91 |
+
"learning_rate": 0.0002944299554888919,
|
| 92 |
+
"loss": 0.7037,
|
| 93 |
+
"step": 70
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.21,
|
| 97 |
+
"learning_rate": 0.00029351741159564925,
|
| 98 |
+
"loss": 1.9876,
|
| 99 |
+
"step": 75
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.22,
|
| 103 |
+
"learning_rate": 0.00029253731384096574,
|
| 104 |
+
"loss": 1.3241,
|
| 105 |
+
"step": 80
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.23,
|
| 109 |
+
"learning_rate": 0.00029149012355832816,
|
| 110 |
+
"loss": 1.7376,
|
| 111 |
+
"step": 85
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.25,
|
| 115 |
+
"learning_rate": 0.00029037633366177726,
|
| 116 |
+
"loss": 1.8011,
|
| 117 |
+
"step": 90
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.26,
|
| 121 |
+
"learning_rate": 0.00028919646841389207,
|
| 122 |
+
"loss": 1.0738,
|
| 123 |
+
"step": 95
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.28,
|
| 127 |
+
"learning_rate": 0.0002879510831790189,
|
| 128 |
+
"loss": 1.0997,
|
| 129 |
+
"step": 100
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.29,
|
| 133 |
+
"learning_rate": 0.0002866407641618605,
|
| 134 |
+
"loss": 1.7646,
|
| 135 |
+
"step": 105
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.3,
|
| 139 |
+
"learning_rate": 0.0002852661281315485,
|
| 140 |
+
"loss": 1.114,
|
| 141 |
+
"step": 110
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.32,
|
| 145 |
+
"learning_rate": 0.00028382782213132933,
|
| 146 |
+
"loss": 1.6206,
|
| 147 |
+
"step": 115
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.33,
|
| 151 |
+
"learning_rate": 0.0002823265231740001,
|
| 152 |
+
"loss": 1.9232,
|
| 153 |
+
"step": 120
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.35,
|
| 157 |
+
"learning_rate": 0.00028076293792323744,
|
| 158 |
+
"loss": 1.9719,
|
| 159 |
+
"step": 125
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.36,
|
| 163 |
+
"learning_rate": 0.00027913780236097003,
|
| 164 |
+
"loss": 1.5214,
|
| 165 |
+
"step": 130
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.37,
|
| 169 |
+
"learning_rate": 0.0002774518814409507,
|
| 170 |
+
"loss": 1.7809,
|
| 171 |
+
"step": 135
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.39,
|
| 175 |
+
"learning_rate": 0.0002757059687286915,
|
| 176 |
+
"loss": 1.7594,
|
| 177 |
+
"step": 140
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.4,
|
| 181 |
+
"learning_rate": 0.0002739008860279314,
|
| 182 |
+
"loss": 1.888,
|
| 183 |
+
"step": 145
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.41,
|
| 187 |
+
"learning_rate": 0.0002720374829938119,
|
| 188 |
+
"loss": 1.3209,
|
| 189 |
+
"step": 150
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.43,
|
| 193 |
+
"learning_rate": 0.00027011663673294316,
|
| 194 |
+
"loss": 1.668,
|
| 195 |
+
"step": 155
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.44,
|
| 199 |
+
"learning_rate": 0.00026813925139054844,
|
| 200 |
+
"loss": 1.5554,
|
| 201 |
+
"step": 160
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.46,
|
| 205 |
+
"learning_rate": 0.0002661062577248818,
|
| 206 |
+
"loss": 1.8724,
|
| 207 |
+
"step": 165
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.47,
|
| 211 |
+
"learning_rate": 0.0002640186126691185,
|
| 212 |
+
"loss": 1.1475,
|
| 213 |
+
"step": 170
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.48,
|
| 217 |
+
"learning_rate": 0.0002618772988809255,
|
| 218 |
+
"loss": 1.5851,
|
| 219 |
+
"step": 175
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.5,
|
| 223 |
+
"learning_rate": 0.0002596833242799227,
|
| 224 |
+
"loss": 1.1434,
|
| 225 |
+
"step": 180
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.51,
|
| 229 |
+
"learning_rate": 0.0002574377215732538,
|
| 230 |
+
"loss": 2.0189,
|
| 231 |
+
"step": 185
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.52,
|
| 235 |
+
"learning_rate": 0.0002551415477694895,
|
| 236 |
+
"loss": 1.1961,
|
| 237 |
+
"step": 190
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.54,
|
| 241 |
+
"learning_rate": 0.000252795883681092,
|
| 242 |
+
"loss": 1.626,
|
| 243 |
+
"step": 195
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.55,
|
| 247 |
+
"learning_rate": 0.0002504018334156746,
|
| 248 |
+
"loss": 1.6993,
|
| 249 |
+
"step": 200
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.57,
|
| 253 |
+
"learning_rate": 0.00024796052385629735,
|
| 254 |
+
"loss": 1.3994,
|
| 255 |
+
"step": 205
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.58,
|
| 259 |
+
"learning_rate": 0.00024547310413104055,
|
| 260 |
+
"loss": 1.0801,
|
| 261 |
+
"step": 210
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.59,
|
| 265 |
+
"learning_rate": 0.0002429407450721093,
|
| 266 |
+
"loss": 1.9244,
|
| 267 |
+
"step": 215
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.61,
|
| 271 |
+
"learning_rate": 0.00024036463866472033,
|
| 272 |
+
"loss": 1.3285,
|
| 273 |
+
"step": 220
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.62,
|
| 277 |
+
"learning_rate": 0.00023774599748603331,
|
| 278 |
+
"loss": 1.3708,
|
| 279 |
+
"step": 225
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.64,
|
| 283 |
+
"learning_rate": 0.0002350860541343886,
|
| 284 |
+
"loss": 1.2642,
|
| 285 |
+
"step": 230
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.65,
|
| 289 |
+
"learning_rate": 0.0002323860606491215,
|
| 290 |
+
"loss": 1.2535,
|
| 291 |
+
"step": 235
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.66,
|
| 295 |
+
"learning_rate": 0.0002296472879212254,
|
| 296 |
+
"loss": 1.7609,
|
| 297 |
+
"step": 240
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.68,
|
| 301 |
+
"learning_rate": 0.00022687102509514156,
|
| 302 |
+
"loss": 1.7628,
|
| 303 |
+
"step": 245
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.69,
|
| 307 |
+
"learning_rate": 0.00022405857896195673,
|
| 308 |
+
"loss": 1.3396,
|
| 309 |
+
"step": 250
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.7,
|
| 313 |
+
"learning_rate": 0.0002212112733442949,
|
| 314 |
+
"loss": 1.516,
|
| 315 |
+
"step": 255
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.72,
|
| 319 |
+
"learning_rate": 0.00021833044847319164,
|
| 320 |
+
"loss": 1.7484,
|
| 321 |
+
"step": 260
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.73,
|
| 325 |
+
"learning_rate": 0.0002154174603572456,
|
| 326 |
+
"loss": 0.7856,
|
| 327 |
+
"step": 265
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.75,
|
| 331 |
+
"learning_rate": 0.00021247368014434316,
|
| 332 |
+
"loss": 1.8457,
|
| 333 |
+
"step": 270
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.76,
|
| 337 |
+
"learning_rate": 0.000209500493476257,
|
| 338 |
+
"loss": 0.8756,
|
| 339 |
+
"step": 275
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.77,
|
| 343 |
+
"learning_rate": 0.00020649929983642242,
|
| 344 |
+
"loss": 1.5258,
|
| 345 |
+
"step": 280
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.79,
|
| 349 |
+
"learning_rate": 0.00020347151189119853,
|
| 350 |
+
"loss": 1.3208,
|
| 351 |
+
"step": 285
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.8,
|
| 355 |
+
"learning_rate": 0.00020041855482492402,
|
| 356 |
+
"loss": 1.3849,
|
| 357 |
+
"step": 290
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.81,
|
| 361 |
+
"learning_rate": 0.00019734186566908047,
|
| 362 |
+
"loss": 1.3585,
|
| 363 |
+
"step": 295
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.83,
|
| 367 |
+
"learning_rate": 0.00019424289262587994,
|
| 368 |
+
"loss": 2.0685,
|
| 369 |
+
"step": 300
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.84,
|
| 373 |
+
"learning_rate": 0.00019112309438659375,
|
| 374 |
+
"loss": 0.9159,
|
| 375 |
+
"step": 305
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.86,
|
| 379 |
+
"learning_rate": 0.0001879839394449442,
|
| 380 |
+
"loss": 1.5168,
|
| 381 |
+
"step": 310
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.87,
|
| 385 |
+
"learning_rate": 0.0001848269054058826,
|
| 386 |
+
"loss": 1.4267,
|
| 387 |
+
"step": 315
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.88,
|
| 391 |
+
"learning_rate": 0.00018165347829007832,
|
| 392 |
+
"loss": 1.4472,
|
| 393 |
+
"step": 320
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.9,
|
| 397 |
+
"learning_rate": 0.00017846515183444648,
|
| 398 |
+
"loss": 2.0622,
|
| 399 |
+
"step": 325
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.91,
|
| 403 |
+
"learning_rate": 0.00017526342678904396,
|
| 404 |
+
"loss": 1.1134,
|
| 405 |
+
"step": 330
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.93,
|
| 409 |
+
"learning_rate": 0.00017204981021066401,
|
| 410 |
+
"loss": 1.7789,
|
| 411 |
+
"step": 335
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.94,
|
| 415 |
+
"learning_rate": 0.00016882581475346223,
|
| 416 |
+
"loss": 0.9645,
|
| 417 |
+
"step": 340
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.95,
|
| 421 |
+
"learning_rate": 0.00016559295795694825,
|
| 422 |
+
"loss": 2.0169,
|
| 423 |
+
"step": 345
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.97,
|
| 427 |
+
"learning_rate": 0.00016235276153167723,
|
| 428 |
+
"loss": 1.1319,
|
| 429 |
+
"step": 350
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.98,
|
| 433 |
+
"learning_rate": 0.00015910675064297877,
|
| 434 |
+
"loss": 1.7811,
|
| 435 |
+
"step": 355
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.99,
|
| 439 |
+
"learning_rate": 0.00015585645319305912,
|
| 440 |
+
"loss": 1.1135,
|
| 441 |
+
"step": 360
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.01,
|
| 445 |
+
"learning_rate": 0.00015260339910181528,
|
| 446 |
+
"loss": 0.9838,
|
| 447 |
+
"step": 365
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 1.02,
|
| 451 |
+
"learning_rate": 0.00014934911958669966,
|
| 452 |
+
"loss": 2.0867,
|
| 453 |
+
"step": 370
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.04,
|
| 457 |
+
"learning_rate": 0.0001460951464419732,
|
| 458 |
+
"loss": 1.8194,
|
| 459 |
+
"step": 375
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.05,
|
| 463 |
+
"learning_rate": 0.00014284301131768816,
|
| 464 |
+
"loss": 0.7124,
|
| 465 |
+
"step": 380
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.06,
|
| 469 |
+
"learning_rate": 0.00013959424499873757,
|
| 470 |
+
"loss": 0.8251,
|
| 471 |
+
"step": 385
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.08,
|
| 475 |
+
"learning_rate": 0.00013635037668431298,
|
| 476 |
+
"loss": 1.6568,
|
| 477 |
+
"step": 390
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 1.09,
|
| 481 |
+
"learning_rate": 0.00013311293326810758,
|
| 482 |
+
"loss": 0.9041,
|
| 483 |
+
"step": 395
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.1,
|
| 487 |
+
"learning_rate": 0.00012988343861960544,
|
| 488 |
+
"loss": 0.5734,
|
| 489 |
+
"step": 400
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.12,
|
| 493 |
+
"learning_rate": 0.00012666341286679376,
|
| 494 |
+
"loss": 1.5422,
|
| 495 |
+
"step": 405
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.13,
|
| 499 |
+
"learning_rate": 0.00012345437168063614,
|
| 500 |
+
"loss": 1.0433,
|
| 501 |
+
"step": 410
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.15,
|
| 505 |
+
"learning_rate": 0.00012025782556164437,
|
| 506 |
+
"loss": 0.6305,
|
| 507 |
+
"step": 415
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.16,
|
| 511 |
+
"learning_rate": 0.00011707527912888316,
|
| 512 |
+
"loss": 0.7021,
|
| 513 |
+
"step": 420
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.17,
|
| 517 |
+
"learning_rate": 0.00011390823041174384,
|
| 518 |
+
"loss": 1.7926,
|
| 519 |
+
"step": 425
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 1.19,
|
| 523 |
+
"learning_rate": 0.00011075817014481984,
|
| 524 |
+
"loss": 0.7126,
|
| 525 |
+
"step": 430
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 1.2,
|
| 529 |
+
"learning_rate": 0.00010762658106621541,
|
| 530 |
+
"loss": 0.9281,
|
| 531 |
+
"step": 435
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 1.22,
|
| 535 |
+
"learning_rate": 0.00010451493721961883,
|
| 536 |
+
"loss": 1.2706,
|
| 537 |
+
"step": 440
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 1.23,
|
| 541 |
+
"learning_rate": 0.00010142470326046745,
|
| 542 |
+
"loss": 0.7369,
|
| 543 |
+
"step": 445
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 1.24,
|
| 547 |
+
"learning_rate": 9.835733376653254e-05,
|
| 548 |
+
"loss": 1.3282,
|
| 549 |
+
"step": 450
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.26,
|
| 553 |
+
"learning_rate": 9.531427255324734e-05,
|
| 554 |
+
"loss": 1.5328,
|
| 555 |
+
"step": 455
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.27,
|
| 559 |
+
"learning_rate": 9.229695199410055e-05,
|
| 560 |
+
"loss": 0.81,
|
| 561 |
+
"step": 460
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 1.28,
|
| 565 |
+
"learning_rate": 8.930679234641647e-05,
|
| 566 |
+
"loss": 1.4783,
|
| 567 |
+
"step": 465
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 1.3,
|
| 571 |
+
"learning_rate": 8.634520108283753e-05,
|
| 572 |
+
"loss": 0.9337,
|
| 573 |
+
"step": 470
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 1.31,
|
| 577 |
+
"learning_rate": 8.341357222882468e-05,
|
| 578 |
+
"loss": 0.7309,
|
| 579 |
+
"step": 475
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 1.33,
|
| 583 |
+
"learning_rate": 8.051328570648772e-05,
|
| 584 |
+
"loss": 0.5978,
|
| 585 |
+
"step": 480
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 1.34,
|
| 589 |
+
"learning_rate": 7.764570668505381e-05,
|
| 590 |
+
"loss": 0.7613,
|
| 591 |
+
"step": 485
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.35,
|
| 595 |
+
"learning_rate": 7.481218493828025e-05,
|
| 596 |
+
"loss": 0.9437,
|
| 597 |
+
"step": 490
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.37,
|
| 601 |
+
"learning_rate": 7.201405420911382e-05,
|
| 602 |
+
"loss": 1.6472,
|
| 603 |
+
"step": 495
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.38,
|
| 607 |
+
"learning_rate": 6.925263158189641e-05,
|
| 608 |
+
"loss": 0.5782,
|
| 609 |
+
"step": 500
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.4,
|
| 613 |
+
"learning_rate": 6.652921686241072e-05,
|
| 614 |
+
"loss": 0.6908,
|
| 615 |
+
"step": 505
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.41,
|
| 619 |
+
"learning_rate": 6.384509196606036e-05,
|
| 620 |
+
"loss": 0.912,
|
| 621 |
+
"step": 510
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 1.42,
|
| 625 |
+
"learning_rate": 6.120152031447023e-05,
|
| 626 |
+
"loss": 1.3509,
|
| 627 |
+
"step": 515
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 1.44,
|
| 631 |
+
"learning_rate": 5.859974624079157e-05,
|
| 632 |
+
"loss": 1.2476,
|
| 633 |
+
"step": 520
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.45,
|
| 637 |
+
"learning_rate": 5.604099440399325e-05,
|
| 638 |
+
"loss": 1.3992,
|
| 639 |
+
"step": 525
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.46,
|
| 643 |
+
"learning_rate": 5.352646921241234e-05,
|
| 644 |
+
"loss": 0.8079,
|
| 645 |
+
"step": 530
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 1.48,
|
| 649 |
+
"learning_rate": 5.1057354256837416e-05,
|
| 650 |
+
"loss": 1.3463,
|
| 651 |
+
"step": 535
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 1.49,
|
| 655 |
+
"learning_rate": 4.8634811753390915e-05,
|
| 656 |
+
"loss": 0.5269,
|
| 657 |
+
"step": 540
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 1.51,
|
| 661 |
+
"learning_rate": 4.6259981996471896e-05,
|
| 662 |
+
"loss": 0.9968,
|
| 663 |
+
"step": 545
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 1.52,
|
| 667 |
+
"learning_rate": 4.3933982822017876e-05,
|
| 668 |
+
"loss": 0.4794,
|
| 669 |
+
"step": 550
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.53,
|
| 673 |
+
"learning_rate": 4.165790908133783e-05,
|
| 674 |
+
"loss": 1.77,
|
| 675 |
+
"step": 555
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.55,
|
| 679 |
+
"learning_rate": 3.943283212576392e-05,
|
| 680 |
+
"loss": 1.4066,
|
| 681 |
+
"step": 560
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.56,
|
| 685 |
+
"learning_rate": 3.725979930236496e-05,
|
| 686 |
+
"loss": 1.0347,
|
| 687 |
+
"step": 565
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 1.57,
|
| 691 |
+
"learning_rate": 3.513983346095838e-05,
|
| 692 |
+
"loss": 0.3513,
|
| 693 |
+
"step": 570
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 1.59,
|
| 697 |
+
"learning_rate": 3.307393247265362e-05,
|
| 698 |
+
"loss": 0.387,
|
| 699 |
+
"step": 575
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.6,
|
| 703 |
+
"learning_rate": 3.106306876015212e-05,
|
| 704 |
+
"loss": 0.9932,
|
| 705 |
+
"step": 580
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 1.62,
|
| 709 |
+
"learning_rate": 2.9108188840027074e-05,
|
| 710 |
+
"loss": 0.7613,
|
| 711 |
+
"step": 585
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.63,
|
| 715 |
+
"learning_rate": 2.72102128771965e-05,
|
| 716 |
+
"loss": 1.3139,
|
| 717 |
+
"step": 590
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.64,
|
| 721 |
+
"learning_rate": 2.5370034251799865e-05,
|
| 722 |
+
"loss": 1.3463,
|
| 723 |
+
"step": 595
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.66,
|
| 727 |
+
"learning_rate": 2.3588519138683276e-05,
|
| 728 |
+
"loss": 1.3703,
|
| 729 |
+
"step": 600
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 1.67,
|
| 733 |
+
"learning_rate": 2.18665060996893e-05,
|
| 734 |
+
"loss": 0.3998,
|
| 735 |
+
"step": 605
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 1.69,
|
| 739 |
+
"learning_rate": 2.020480568894461e-05,
|
| 740 |
+
"loss": 1.1889,
|
| 741 |
+
"step": 610
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 1.7,
|
| 745 |
+
"learning_rate": 1.860420007133131e-05,
|
| 746 |
+
"loss": 0.8979,
|
| 747 |
+
"step": 615
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 1.71,
|
| 751 |
+
"learning_rate": 1.7065442654320334e-05,
|
| 752 |
+
"loss": 1.1826,
|
| 753 |
+
"step": 620
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 1.73,
|
| 757 |
+
"learning_rate": 1.5589257733341694e-05,
|
| 758 |
+
"loss": 0.5617,
|
| 759 |
+
"step": 625
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.74,
|
| 763 |
+
"learning_rate": 1.417634015085734e-05,
|
| 764 |
+
"loss": 0.8612,
|
| 765 |
+
"step": 630
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.75,
|
| 769 |
+
"learning_rate": 1.2827354969297953e-05,
|
| 770 |
+
"loss": 1.152,
|
| 771 |
+
"step": 635
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 1.77,
|
| 775 |
+
"learning_rate": 1.1542937158016895e-05,
|
| 776 |
+
"loss": 1.5859,
|
| 777 |
+
"step": 640
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 1.78,
|
| 781 |
+
"learning_rate": 1.032369129440928e-05,
|
| 782 |
+
"loss": 1.3262,
|
| 783 |
+
"step": 645
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 1.8,
|
| 787 |
+
"learning_rate": 9.170191279336458e-06,
|
| 788 |
+
"loss": 0.7804,
|
| 789 |
+
"step": 650
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.81,
|
| 793 |
+
"learning_rate": 8.082980066989987e-06,
|
| 794 |
+
"loss": 0.6581,
|
| 795 |
+
"step": 655
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 1.82,
|
| 799 |
+
"learning_rate": 7.062569409322394e-06,
|
| 800 |
+
"loss": 0.7062,
|
| 801 |
+
"step": 660
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.84,
|
| 805 |
+
"learning_rate": 6.109439615164524e-06,
|
| 806 |
+
"loss": 0.5249,
|
| 807 |
+
"step": 665
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.85,
|
| 811 |
+
"learning_rate": 5.224039324143692e-06,
|
| 812 |
+
"loss": 0.6158,
|
| 813 |
+
"step": 670
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 1.86,
|
| 817 |
+
"learning_rate": 4.406785295508275e-06,
|
| 818 |
+
"loss": 1.0754,
|
| 819 |
+
"step": 675
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 1.88,
|
| 823 |
+
"learning_rate": 3.6580622119583847e-06,
|
| 824 |
+
"loss": 1.3947,
|
| 825 |
+
"step": 680
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 1.89,
|
| 829 |
+
"learning_rate": 2.9782224985753224e-06,
|
| 830 |
+
"loss": 1.1482,
|
| 831 |
+
"step": 685
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 1.91,
|
| 835 |
+
"learning_rate": 2.367586156934409e-06,
|
| 836 |
+
"loss": 0.7185,
|
| 837 |
+
"step": 690
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 1.92,
|
| 841 |
+
"learning_rate": 1.8264406144798238e-06,
|
| 842 |
+
"loss": 0.2661,
|
| 843 |
+
"step": 695
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.93,
|
| 847 |
+
"learning_rate": 1.3550405892321591e-06,
|
| 848 |
+
"loss": 1.0511,
|
| 849 |
+
"step": 700
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.95,
|
| 853 |
+
"learning_rate": 9.536079698920951e-07,
|
| 854 |
+
"loss": 0.7304,
|
| 855 |
+
"step": 705
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 1.96,
|
| 859 |
+
"learning_rate": 6.223317113971948e-07,
|
| 860 |
+
"loss": 1.0044,
|
| 861 |
+
"step": 710
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 1.98,
|
| 865 |
+
"learning_rate": 3.6136774598043427e-07,
|
| 866 |
+
"loss": 0.4553,
|
| 867 |
+
"step": 715
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 1.99,
|
| 871 |
+
"learning_rate": 1.7083890977278027e-07,
|
| 872 |
+
"loss": 0.9209,
|
| 873 |
+
"step": 720
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 2.0,
|
| 877 |
+
"step": 724,
|
| 878 |
+
"total_flos": 2638293095350272.0,
|
| 879 |
+
"train_loss": 1.3001856657352238,
|
| 880 |
+
"train_runtime": 3307.5677,
|
| 881 |
+
"train_samples_per_second": 0.219,
|
| 882 |
+
"train_steps_per_second": 0.219
|
| 883 |
+
}
|
| 884 |
+
],
|
| 885 |
+
"logging_steps": 5,
|
| 886 |
+
"max_steps": 724,
|
| 887 |
+
"num_input_tokens_seen": 0,
|
| 888 |
+
"num_train_epochs": 2,
|
| 889 |
+
"save_steps": 1000,
|
| 890 |
+
"total_flos": 2638293095350272.0,
|
| 891 |
+
"train_batch_size": 1,
|
| 892 |
+
"trial_name": null,
|
| 893 |
+
"trial_params": null
|
| 894 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae81743218c43ba16aa75eb8d5beb9372e7a669b90c57ab4e4edd8456747a836
|
| 3 |
+
size 4984
|
training_loss.png
ADDED
|