v9 same-pair (retry after freeing storage)
Browse files- .gitattributes +1 -0
- v9/asr_history.json +13 -0
- v9/chat_template.jinja +4 -0
- v9/config.json +68 -0
- v9/generation_config.json +11 -0
- v9/loss_curve.json +1467 -0
- v9/model.safetensors +3 -0
- v9/tokenizer.json +3 -0
- v9/tokenizer_config.json +20 -0
- v9/training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -54,3 +54,4 @@ synth_eval/eval_gram_ctrl_single.jsonl filter=lfs diff=lfs merge=lfs -text
|
|
| 54 |
synth_eval/eval_gram_mismatch.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 55 |
v7/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 56 |
v8/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 54 |
synth_eval/eval_gram_mismatch.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 55 |
v7/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 56 |
v8/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 57 |
+
v9/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
v9/asr_history.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"epoch": 1.0,
|
| 4 |
+
"ASR": 0.41,
|
| 5 |
+
"FNR": 0.59,
|
| 6 |
+
"FPR_clean": 0.0,
|
| 7 |
+
"FPR_ctrl_mismatch": 0.29,
|
| 8 |
+
"FPR_ctrl_single": 0.09,
|
| 9 |
+
"FPR_variant_partner": 0.22,
|
| 10 |
+
"FPR_variant_single": 0.07,
|
| 11 |
+
"ASR_single": 0.94
|
| 12 |
+
}
|
| 13 |
+
]
|
v9/chat_template.jinja
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '
|
| 2 |
+
' + message['content'] | trim + '<end_of_turn>
|
| 3 |
+
' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model
|
| 4 |
+
'}}{% endif %}
|
v9/config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Gemma2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"attn_logit_softcapping": 50.0,
|
| 8 |
+
"bos_token_id": 2,
|
| 9 |
+
"cache_implementation": "hybrid",
|
| 10 |
+
"dtype": "bfloat16",
|
| 11 |
+
"eos_token_id": [
|
| 12 |
+
1,
|
| 13 |
+
107
|
| 14 |
+
],
|
| 15 |
+
"final_logit_softcapping": 30.0,
|
| 16 |
+
"head_dim": 256,
|
| 17 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 18 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 19 |
+
"hidden_size": 2304,
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 9216,
|
| 22 |
+
"layer_types": [
|
| 23 |
+
"sliding_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"sliding_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"sliding_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"sliding_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"sliding_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"sliding_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"sliding_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"sliding_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"sliding_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"sliding_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"sliding_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"sliding_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"sliding_attention",
|
| 48 |
+
"full_attention"
|
| 49 |
+
],
|
| 50 |
+
"max_position_embeddings": 8192,
|
| 51 |
+
"model_type": "gemma2",
|
| 52 |
+
"num_attention_heads": 8,
|
| 53 |
+
"num_hidden_layers": 26,
|
| 54 |
+
"num_key_value_heads": 4,
|
| 55 |
+
"pad_token_id": 0,
|
| 56 |
+
"query_pre_attn_scalar": 256,
|
| 57 |
+
"rms_norm_eps": 1e-06,
|
| 58 |
+
"rope_parameters": {
|
| 59 |
+
"rope_theta": 10000.0,
|
| 60 |
+
"rope_type": "default"
|
| 61 |
+
},
|
| 62 |
+
"sliding_window": 4096,
|
| 63 |
+
"tie_word_embeddings": true,
|
| 64 |
+
"transformers_version": "5.12.1",
|
| 65 |
+
"use_bidirectional_attention": null,
|
| 66 |
+
"use_cache": false,
|
| 67 |
+
"vocab_size": 256000
|
| 68 |
+
}
|
v9/generation_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 2,
|
| 4 |
+
"cache_implementation": "hybrid",
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
1,
|
| 7 |
+
107
|
| 8 |
+
],
|
| 9 |
+
"pad_token_id": 0,
|
| 10 |
+
"transformers_version": "5.12.1"
|
| 11 |
+
}
|
v9/loss_curve.json
ADDED
|
@@ -0,0 +1,1467 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"step": 100,
|
| 4 |
+
"loss": 0.6651429748535156,
|
| 5 |
+
"t": 1691208.659497138
|
| 6 |
+
},
|
| 7 |
+
{
|
| 8 |
+
"step": 200,
|
| 9 |
+
"loss": 0.6440496826171875,
|
| 10 |
+
"t": 1691250.703498358
|
| 11 |
+
},
|
| 12 |
+
{
|
| 13 |
+
"step": 300,
|
| 14 |
+
"loss": 0.6623657989501953,
|
| 15 |
+
"t": 1691294.267256817
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"step": 400,
|
| 19 |
+
"loss": 0.6491999816894531,
|
| 20 |
+
"t": 1691337.321940412
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"step": 500,
|
| 24 |
+
"loss": 0.6678106689453125,
|
| 25 |
+
"t": 1691380.650267227
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"step": 600,
|
| 29 |
+
"loss": 0.6558676147460938,
|
| 30 |
+
"t": 1691424.571062158
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"step": 700,
|
| 34 |
+
"loss": 0.6852732086181641,
|
| 35 |
+
"t": 1691468.245849411
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"step": 800,
|
| 39 |
+
"loss": 0.687619400024414,
|
| 40 |
+
"t": 1691513.051053983
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"step": 900,
|
| 44 |
+
"loss": 0.6867406463623047,
|
| 45 |
+
"t": 1691558.364936389
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"step": 1000,
|
| 49 |
+
"loss": 0.6995064544677735,
|
| 50 |
+
"t": 1691604.2907471
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"step": 1100,
|
| 54 |
+
"loss": 0.6784056091308593,
|
| 55 |
+
"t": 1691647.722283571
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"step": 1200,
|
| 59 |
+
"loss": 0.7113138580322266,
|
| 60 |
+
"t": 1691693.00147048
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"step": 1300,
|
| 64 |
+
"loss": 0.7302777862548828,
|
| 65 |
+
"t": 1691736.366333568
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"step": 1400,
|
| 69 |
+
"loss": 0.6931300354003906,
|
| 70 |
+
"t": 1691781.581855605
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"step": 1500,
|
| 74 |
+
"loss": 0.7124892425537109,
|
| 75 |
+
"t": 1691824.9209841
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"step": 1600,
|
| 79 |
+
"loss": 0.7035292053222656,
|
| 80 |
+
"t": 1691870.195725218
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"step": 1700,
|
| 84 |
+
"loss": 0.7197954559326172,
|
| 85 |
+
"t": 1691913.637872673
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"step": 1800,
|
| 89 |
+
"loss": 0.7382371520996094,
|
| 90 |
+
"t": 1691956.235344992
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"step": 1900,
|
| 94 |
+
"loss": 0.7042308044433594,
|
| 95 |
+
"t": 1691999.602234049
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"step": 2000,
|
| 99 |
+
"loss": 0.7212035369873047,
|
| 100 |
+
"t": 1692040.950295934
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"step": 2100,
|
| 104 |
+
"loss": 0.7198699188232421,
|
| 105 |
+
"t": 1692086.770521226
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"step": 2200,
|
| 109 |
+
"loss": 0.7128998565673829,
|
| 110 |
+
"t": 1692130.562716639
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"step": 2300,
|
| 114 |
+
"loss": 0.7094781494140625,
|
| 115 |
+
"t": 1692173.35817863
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"step": 2400,
|
| 119 |
+
"loss": 0.7022262573242187,
|
| 120 |
+
"t": 1692217.445244137
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"step": 2500,
|
| 124 |
+
"loss": 0.7541838836669922,
|
| 125 |
+
"t": 1692260.648363407
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"step": 2600,
|
| 129 |
+
"loss": 0.7090040588378906,
|
| 130 |
+
"t": 1692305.566300524
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"step": 2700,
|
| 134 |
+
"loss": 0.7021080780029297,
|
| 135 |
+
"t": 1692350.138217438
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"step": 2800,
|
| 139 |
+
"loss": 0.701666259765625,
|
| 140 |
+
"t": 1692396.463012157
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"step": 2900,
|
| 144 |
+
"loss": 0.7182410430908203,
|
| 145 |
+
"t": 1692436.838859707
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"step": 3000,
|
| 149 |
+
"loss": 0.7074358367919922,
|
| 150 |
+
"t": 1692479.278057788
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"step": 3100,
|
| 154 |
+
"loss": 0.7113906097412109,
|
| 155 |
+
"t": 1692521.326299057
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"step": 3200,
|
| 159 |
+
"loss": 0.6956793212890625,
|
| 160 |
+
"t": 1692565.750074028
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"step": 3300,
|
| 164 |
+
"loss": 0.6963240814208984,
|
| 165 |
+
"t": 1692610.859876085
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"step": 3400,
|
| 169 |
+
"loss": 0.6898847198486329,
|
| 170 |
+
"t": 1692654.864696201
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"step": 3500,
|
| 174 |
+
"loss": 0.6926114654541016,
|
| 175 |
+
"t": 1692700.107305223
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"step": 3600,
|
| 179 |
+
"loss": 0.6923567962646484,
|
| 180 |
+
"t": 1692741.862768689
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"step": 3700,
|
| 184 |
+
"loss": 0.7105691528320313,
|
| 185 |
+
"t": 1692782.935752782
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"step": 3800,
|
| 189 |
+
"loss": 0.6584600830078124,
|
| 190 |
+
"t": 1692827.218170122
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"step": 3900,
|
| 194 |
+
"loss": 0.675249252319336,
|
| 195 |
+
"t": 1692869.495567499
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"step": 4000,
|
| 199 |
+
"loss": 0.6978207397460937,
|
| 200 |
+
"t": 1692913.818332628
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"step": 4100,
|
| 204 |
+
"loss": 0.6692790985107422,
|
| 205 |
+
"t": 1692958.109838693
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"step": 4200,
|
| 209 |
+
"loss": 0.6844456481933594,
|
| 210 |
+
"t": 1693002.949812043
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"step": 4300,
|
| 214 |
+
"loss": 0.6615377044677735,
|
| 215 |
+
"t": 1693045.704733992
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"step": 4400,
|
| 219 |
+
"loss": 0.6658638763427734,
|
| 220 |
+
"t": 1693091.944213525
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"step": 4500,
|
| 224 |
+
"loss": 0.6663825225830078,
|
| 225 |
+
"t": 1693136.417117407
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"step": 4600,
|
| 229 |
+
"loss": 0.6456810760498047,
|
| 230 |
+
"t": 1693182.189594182
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"step": 4700,
|
| 234 |
+
"loss": 0.6897911071777344,
|
| 235 |
+
"t": 1693225.030247391
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"step": 4800,
|
| 239 |
+
"loss": 0.6746551513671875,
|
| 240 |
+
"t": 1693268.036071054
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"step": 4900,
|
| 244 |
+
"loss": 0.6636798095703125,
|
| 245 |
+
"t": 1693312.423777154
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"step": 5000,
|
| 249 |
+
"loss": 0.6614973449707031,
|
| 250 |
+
"t": 1693356.890818621
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"step": 5100,
|
| 254 |
+
"loss": 0.659094467163086,
|
| 255 |
+
"t": 1693403.155543594
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"step": 5200,
|
| 259 |
+
"loss": 0.6782837677001953,
|
| 260 |
+
"t": 1693445.012757166
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"step": 5300,
|
| 264 |
+
"loss": 0.6490362548828125,
|
| 265 |
+
"t": 1693490.767684786
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"step": 5400,
|
| 269 |
+
"loss": 0.678406982421875,
|
| 270 |
+
"t": 1693533.934979466
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"step": 5500,
|
| 274 |
+
"loss": 0.653538818359375,
|
| 275 |
+
"t": 1693577.922447902
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"step": 5600,
|
| 279 |
+
"loss": 0.6701308441162109,
|
| 280 |
+
"t": 1693622.051341995
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"step": 5700,
|
| 284 |
+
"loss": 0.6821817016601562,
|
| 285 |
+
"t": 1693664.693129643
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"step": 5800,
|
| 289 |
+
"loss": 0.6255032348632813,
|
| 290 |
+
"t": 1693709.361255831
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"step": 5900,
|
| 294 |
+
"loss": 0.6489052581787109,
|
| 295 |
+
"t": 1693753.206798773
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"step": 6000,
|
| 299 |
+
"loss": 0.6556395721435547,
|
| 300 |
+
"t": 1693795.680902564
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"step": 6100,
|
| 304 |
+
"loss": 0.6529888916015625,
|
| 305 |
+
"t": 1693840.290590545
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"step": 6200,
|
| 309 |
+
"loss": 0.6594289398193359,
|
| 310 |
+
"t": 1693885.080225978
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"step": 6300,
|
| 314 |
+
"loss": 0.6360308456420899,
|
| 315 |
+
"t": 1693931.141384602
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"step": 6400,
|
| 319 |
+
"loss": 0.639415283203125,
|
| 320 |
+
"t": 1693975.390443454
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"step": 6500,
|
| 324 |
+
"loss": 0.6589456176757813,
|
| 325 |
+
"t": 1694020.874968391
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"step": 6600,
|
| 329 |
+
"loss": 0.6258051300048828,
|
| 330 |
+
"t": 1694067.264062835
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"step": 6700,
|
| 334 |
+
"loss": 0.6490687561035157,
|
| 335 |
+
"t": 1694106.891070688
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"step": 6800,
|
| 339 |
+
"loss": 0.6512105560302734,
|
| 340 |
+
"t": 1694152.738445838
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"step": 6900,
|
| 344 |
+
"loss": 0.6477635192871094,
|
| 345 |
+
"t": 1694196.623616401
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"step": 7000,
|
| 349 |
+
"loss": 0.6153639602661133,
|
| 350 |
+
"t": 1694241.230714808
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"step": 7100,
|
| 354 |
+
"loss": 0.6377830123901367,
|
| 355 |
+
"t": 1694284.811960307
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"step": 7200,
|
| 359 |
+
"loss": 0.6276622772216797,
|
| 360 |
+
"t": 1694329.926921381
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"step": 7300,
|
| 364 |
+
"loss": 0.6359042358398438,
|
| 365 |
+
"t": 1694374.238352812
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"step": 7400,
|
| 369 |
+
"loss": 0.6520323181152343,
|
| 370 |
+
"t": 1694417.924221641
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"step": 7500,
|
| 374 |
+
"loss": 0.6221945571899414,
|
| 375 |
+
"t": 1694463.049832261
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"step": 7600,
|
| 379 |
+
"loss": 0.6102314758300781,
|
| 380 |
+
"t": 1694506.628284084
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"step": 7700,
|
| 384 |
+
"loss": 0.6009440994262696,
|
| 385 |
+
"t": 1694550.620611712
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"step": 7800,
|
| 389 |
+
"loss": 0.6157763290405274,
|
| 390 |
+
"t": 1694596.854138738
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"step": 7900,
|
| 394 |
+
"loss": 0.6449762725830078,
|
| 395 |
+
"t": 1694640.136819529
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"step": 8000,
|
| 399 |
+
"loss": 0.616869125366211,
|
| 400 |
+
"t": 1694683.811407265
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"step": 8100,
|
| 404 |
+
"loss": 0.6224802780151367,
|
| 405 |
+
"t": 1694728.990075021
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"step": 8200,
|
| 409 |
+
"loss": 0.6260087966918946,
|
| 410 |
+
"t": 1694775.313328355
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"step": 8300,
|
| 414 |
+
"loss": 0.6093363571166992,
|
| 415 |
+
"t": 1694819.278802067
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"step": 8400,
|
| 419 |
+
"loss": 0.6391535186767578,
|
| 420 |
+
"t": 1694862.694340108
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"step": 8500,
|
| 424 |
+
"loss": 0.5997830581665039,
|
| 425 |
+
"t": 1694904.946485595
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"step": 8600,
|
| 429 |
+
"loss": 0.625844841003418,
|
| 430 |
+
"t": 1694949.713937259
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"step": 8700,
|
| 434 |
+
"loss": 0.6388531875610352,
|
| 435 |
+
"t": 1694991.928951502
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"step": 8800,
|
| 439 |
+
"loss": 0.6172653961181641,
|
| 440 |
+
"t": 1695036.8126533
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"step": 8900,
|
| 444 |
+
"loss": 0.6160613250732422,
|
| 445 |
+
"t": 1695079.808448602
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"step": 9000,
|
| 449 |
+
"loss": 0.6053459548950195,
|
| 450 |
+
"t": 1695124.089967822
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"step": 9100,
|
| 454 |
+
"loss": 0.6071726226806641,
|
| 455 |
+
"t": 1695165.095226763
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"step": 9200,
|
| 459 |
+
"loss": 0.6167321014404297,
|
| 460 |
+
"t": 1695208.93567402
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"step": 9300,
|
| 464 |
+
"loss": 0.618711280822754,
|
| 465 |
+
"t": 1695252.51910335
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"step": 9400,
|
| 469 |
+
"loss": 0.5969942474365234,
|
| 470 |
+
"t": 1695298.386892851
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"step": 9500,
|
| 474 |
+
"loss": 0.6101174163818359,
|
| 475 |
+
"t": 1695342.679539345
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"step": 9600,
|
| 479 |
+
"loss": 0.6334365081787109,
|
| 480 |
+
"t": 1695384.619060407
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"step": 9700,
|
| 484 |
+
"loss": 0.6018773651123047,
|
| 485 |
+
"t": 1695426.201241577
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"step": 9800,
|
| 489 |
+
"loss": 0.5988513565063477,
|
| 490 |
+
"t": 1695472.280264374
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"step": 9900,
|
| 494 |
+
"loss": 0.5979484558105469,
|
| 495 |
+
"t": 1695516.559935003
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"step": 10000,
|
| 499 |
+
"loss": 0.6100553512573242,
|
| 500 |
+
"t": 1695559.850990522
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"step": 10100,
|
| 504 |
+
"loss": 0.6256487274169922,
|
| 505 |
+
"t": 1695603.64714478
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"step": 10200,
|
| 509 |
+
"loss": 0.6347363662719726,
|
| 510 |
+
"t": 1695647.122336159
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"step": 10300,
|
| 514 |
+
"loss": 0.5943323516845703,
|
| 515 |
+
"t": 1695692.682850345
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"step": 10400,
|
| 519 |
+
"loss": 0.5899624633789062,
|
| 520 |
+
"t": 1695736.094157677
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"step": 10500,
|
| 524 |
+
"loss": 0.6007540130615234,
|
| 525 |
+
"t": 1695779.834485681
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"step": 10600,
|
| 529 |
+
"loss": 0.6021713638305664,
|
| 530 |
+
"t": 1695823.163389307
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"step": 10700,
|
| 534 |
+
"loss": 0.6195548248291015,
|
| 535 |
+
"t": 1695867.578851342
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"step": 10800,
|
| 539 |
+
"loss": 0.6069049072265625,
|
| 540 |
+
"t": 1695912.958469131
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"step": 10900,
|
| 544 |
+
"loss": 0.5897953414916992,
|
| 545 |
+
"t": 1695953.964841427
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"step": 11000,
|
| 549 |
+
"loss": 0.5902718734741211,
|
| 550 |
+
"t": 1696000.178899251
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"step": 11100,
|
| 554 |
+
"loss": 0.5802568054199219,
|
| 555 |
+
"t": 1696043.737561331
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"step": 11200,
|
| 559 |
+
"loss": 0.5836947250366211,
|
| 560 |
+
"t": 1696088.448187202
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"step": 11300,
|
| 564 |
+
"loss": 0.5677269744873047,
|
| 565 |
+
"t": 1696134.192558238
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"step": 11400,
|
| 569 |
+
"loss": 0.6004460525512695,
|
| 570 |
+
"t": 1696177.597703074
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"step": 11500,
|
| 574 |
+
"loss": 0.5907196807861328,
|
| 575 |
+
"t": 1696219.870566773
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"step": 11600,
|
| 579 |
+
"loss": 0.6006726837158203,
|
| 580 |
+
"t": 1696266.286291918
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"step": 11700,
|
| 584 |
+
"loss": 0.5961096572875977,
|
| 585 |
+
"t": 1696310.909479984
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"step": 11800,
|
| 589 |
+
"loss": 0.5797550964355469,
|
| 590 |
+
"t": 1696353.030151214
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"step": 11900,
|
| 594 |
+
"loss": 0.5826334762573242,
|
| 595 |
+
"t": 1696397.068021894
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"step": 12000,
|
| 599 |
+
"loss": 0.6008513259887696,
|
| 600 |
+
"t": 1696442.913339221
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"step": 12100,
|
| 604 |
+
"loss": 0.5628915023803711,
|
| 605 |
+
"t": 1696486.509681838
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"step": 12200,
|
| 609 |
+
"loss": 0.6225860214233399,
|
| 610 |
+
"t": 1696530.174056192
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"step": 12300,
|
| 614 |
+
"loss": 0.5889992904663086,
|
| 615 |
+
"t": 1696575.886842566
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"step": 12400,
|
| 619 |
+
"loss": 0.5979320907592773,
|
| 620 |
+
"t": 1696620.615717269
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"step": 12500,
|
| 624 |
+
"loss": 0.5871817016601563,
|
| 625 |
+
"t": 1696663.910972114
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"step": 12600,
|
| 629 |
+
"loss": 0.5766915893554687,
|
| 630 |
+
"t": 1696707.924774255
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"step": 12700,
|
| 634 |
+
"loss": 0.5906681823730469,
|
| 635 |
+
"t": 1696748.528158544
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"step": 12800,
|
| 639 |
+
"loss": 0.5642934036254883,
|
| 640 |
+
"t": 1696793.885660075
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"step": 12900,
|
| 644 |
+
"loss": 0.6015703582763672,
|
| 645 |
+
"t": 1696835.177791647
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"step": 13000,
|
| 649 |
+
"loss": 0.5621967697143555,
|
| 650 |
+
"t": 1696880.27686863
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"step": 13100,
|
| 654 |
+
"loss": 0.5416678237915039,
|
| 655 |
+
"t": 1696923.872048095
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"step": 13200,
|
| 659 |
+
"loss": 0.6030615234375,
|
| 660 |
+
"t": 1696967.573286018
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"step": 13300,
|
| 664 |
+
"loss": 0.5812434387207032,
|
| 665 |
+
"t": 1697009.948084458
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"step": 13400,
|
| 669 |
+
"loss": 0.5796372222900391,
|
| 670 |
+
"t": 1697053.014963406
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"step": 13500,
|
| 674 |
+
"loss": 0.5700355529785156,
|
| 675 |
+
"t": 1697100.442031902
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"step": 13600,
|
| 679 |
+
"loss": 0.588858757019043,
|
| 680 |
+
"t": 1697144.929683316
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"step": 13700,
|
| 684 |
+
"loss": 0.5630781173706054,
|
| 685 |
+
"t": 1697189.092135724
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"step": 13800,
|
| 689 |
+
"loss": 0.5815120697021484,
|
| 690 |
+
"t": 1697232.464132497
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"step": 13900,
|
| 694 |
+
"loss": 0.5858039093017579,
|
| 695 |
+
"t": 1697275.50187696
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"step": 14000,
|
| 699 |
+
"loss": 0.5485697937011719,
|
| 700 |
+
"t": 1697319.761783088
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"step": 14100,
|
| 704 |
+
"loss": 0.5977954483032226,
|
| 705 |
+
"t": 1697361.513362469
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"step": 14200,
|
| 709 |
+
"loss": 0.5847698211669922,
|
| 710 |
+
"t": 1697405.162767911
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"step": 14300,
|
| 714 |
+
"loss": 0.5709694290161133,
|
| 715 |
+
"t": 1697451.981548635
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"step": 14400,
|
| 719 |
+
"loss": 0.5885934066772461,
|
| 720 |
+
"t": 1697496.387636767
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"step": 14500,
|
| 724 |
+
"loss": 0.5353256607055664,
|
| 725 |
+
"t": 1697541.328180222
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"step": 14600,
|
| 729 |
+
"loss": 0.5578603744506836,
|
| 730 |
+
"t": 1697584.309820746
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"step": 14700,
|
| 734 |
+
"loss": 0.6007673645019531,
|
| 735 |
+
"t": 1697627.495566307
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"step": 14800,
|
| 739 |
+
"loss": 0.5516290283203125,
|
| 740 |
+
"t": 1697670.56097547
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"step": 14900,
|
| 744 |
+
"loss": 0.5815561294555665,
|
| 745 |
+
"t": 1697714.007575
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"step": 15000,
|
| 749 |
+
"loss": 0.5575561904907227,
|
| 750 |
+
"t": 1697758.947450141
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"step": 15100,
|
| 754 |
+
"loss": 0.5592901992797852,
|
| 755 |
+
"t": 1697802.532900465
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"step": 15200,
|
| 759 |
+
"loss": 0.5958484649658203,
|
| 760 |
+
"t": 1697845.557339834
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"step": 15300,
|
| 764 |
+
"loss": 0.5767786026000976,
|
| 765 |
+
"t": 1697888.057403577
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"step": 15400,
|
| 769 |
+
"loss": 0.5745346832275391,
|
| 770 |
+
"t": 1697931.087237016
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"step": 15500,
|
| 774 |
+
"loss": 0.5859962463378906,
|
| 775 |
+
"t": 1697976.68361071
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"step": 15600,
|
| 779 |
+
"loss": 0.5677953720092773,
|
| 780 |
+
"t": 1698021.544245209
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"step": 15700,
|
| 784 |
+
"loss": 0.5880054473876953,
|
| 785 |
+
"t": 1698063.722755613
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"step": 15800,
|
| 789 |
+
"loss": 0.5836387252807618,
|
| 790 |
+
"t": 1698107.613957632
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"step": 15900,
|
| 794 |
+
"loss": 0.5731891632080078,
|
| 795 |
+
"t": 1698150.723060867
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"step": 16000,
|
| 799 |
+
"loss": 0.572757568359375,
|
| 800 |
+
"t": 1698197.798388355
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"step": 16100,
|
| 804 |
+
"loss": 0.604388313293457,
|
| 805 |
+
"t": 1698240.93989053
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"step": 16200,
|
| 809 |
+
"loss": 0.5528518295288086,
|
| 810 |
+
"t": 1698286.442307345
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"step": 16300,
|
| 814 |
+
"loss": 0.5737750244140625,
|
| 815 |
+
"t": 1698329.664921211
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"step": 16400,
|
| 819 |
+
"loss": 0.5793390655517578,
|
| 820 |
+
"t": 1698373.998282536
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"step": 16500,
|
| 824 |
+
"loss": 0.565096435546875,
|
| 825 |
+
"t": 1698416.212188445
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"step": 16600,
|
| 829 |
+
"loss": 0.5842839813232422,
|
| 830 |
+
"t": 1698459.268320148
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"step": 16700,
|
| 834 |
+
"loss": 0.5779767227172852,
|
| 835 |
+
"t": 1698505.230727111
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"step": 16800,
|
| 839 |
+
"loss": 0.5424223709106445,
|
| 840 |
+
"t": 1698551.31798425
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"step": 16900,
|
| 844 |
+
"loss": 0.5859769058227539,
|
| 845 |
+
"t": 1698593.58107228
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"step": 17000,
|
| 849 |
+
"loss": 0.5680537033081055,
|
| 850 |
+
"t": 1698637.981632217
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"step": 17100,
|
| 854 |
+
"loss": 0.5992934036254883,
|
| 855 |
+
"t": 1698682.318947549
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"step": 17200,
|
| 859 |
+
"loss": 0.5970849227905274,
|
| 860 |
+
"t": 1698727.502939133
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"step": 17300,
|
| 864 |
+
"loss": 0.5499745559692383,
|
| 865 |
+
"t": 1698773.508744253
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"step": 17400,
|
| 869 |
+
"loss": 0.5886800384521484,
|
| 870 |
+
"t": 1698817.691533664
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"step": 17500,
|
| 874 |
+
"loss": 0.5428456497192383,
|
| 875 |
+
"t": 1698859.905064464
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"step": 17600,
|
| 879 |
+
"loss": 0.5652324295043946,
|
| 880 |
+
"t": 1698906.106273272
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"step": 17700,
|
| 884 |
+
"loss": 0.6089623260498047,
|
| 885 |
+
"t": 1698947.689685137
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"step": 17800,
|
| 889 |
+
"loss": 0.5552640533447266,
|
| 890 |
+
"t": 1698992.842973895
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"step": 17900,
|
| 894 |
+
"loss": 0.5851658630371094,
|
| 895 |
+
"t": 1699037.710677306
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"step": 18000,
|
| 899 |
+
"loss": 0.596683120727539,
|
| 900 |
+
"t": 1699082.23680369
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"step": 18100,
|
| 904 |
+
"loss": 0.5789957809448242,
|
| 905 |
+
"t": 1699124.649330853
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"step": 18200,
|
| 909 |
+
"loss": 0.5782778549194336,
|
| 910 |
+
"t": 1699167.727034101
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"step": 18300,
|
| 914 |
+
"loss": 0.54711669921875,
|
| 915 |
+
"t": 1699211.644939659
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"step": 18400,
|
| 919 |
+
"loss": 0.5566564559936523,
|
| 920 |
+
"t": 1699257.323145829
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"step": 18500,
|
| 924 |
+
"loss": 0.5400175094604492,
|
| 925 |
+
"t": 1699299.969593219
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"step": 18600,
|
| 929 |
+
"loss": 0.5927561950683594,
|
| 930 |
+
"t": 1699344.09043869
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"step": 18700,
|
| 934 |
+
"loss": 0.5524624633789063,
|
| 935 |
+
"t": 1699387.795550985
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"step": 18800,
|
| 939 |
+
"loss": 0.5584362411499023,
|
| 940 |
+
"t": 1699433.015902776
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"step": 18900,
|
| 944 |
+
"loss": 0.5502066802978516,
|
| 945 |
+
"t": 1699478.223364429
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"step": 19000,
|
| 949 |
+
"loss": 0.5556842803955078,
|
| 950 |
+
"t": 1699523.019567818
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"step": 19100,
|
| 954 |
+
"loss": 0.561837158203125,
|
| 955 |
+
"t": 1699568.140066013
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"step": 19200,
|
| 959 |
+
"loss": 0.5495845794677734,
|
| 960 |
+
"t": 1699614.25207141
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"step": 19300,
|
| 964 |
+
"loss": 0.5613619613647461,
|
| 965 |
+
"t": 1699656.302635198
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"step": 19400,
|
| 969 |
+
"loss": 0.5671342849731446,
|
| 970 |
+
"t": 1699698.968328301
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"step": 19500,
|
| 974 |
+
"loss": 0.5526727676391602,
|
| 975 |
+
"t": 1699745.352424429
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"step": 19600,
|
| 979 |
+
"loss": 0.5796107482910157,
|
| 980 |
+
"t": 1699789.215851032
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"step": 19700,
|
| 984 |
+
"loss": 0.589382553100586,
|
| 985 |
+
"t": 1699833.81736688
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"step": 19800,
|
| 989 |
+
"loss": 0.5658351135253906,
|
| 990 |
+
"t": 1699876.718645386
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"step": 19900,
|
| 994 |
+
"loss": 0.5383224105834961,
|
| 995 |
+
"t": 1699919.21851309
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"step": 20000,
|
| 999 |
+
"loss": 0.5249342346191406,
|
| 1000 |
+
"t": 1699964.713694357
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"step": 20100,
|
| 1004 |
+
"loss": 0.5386872863769532,
|
| 1005 |
+
"t": 1700008.477789451
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"step": 20200,
|
| 1009 |
+
"loss": 0.5623548126220703,
|
| 1010 |
+
"t": 1700054.486118311
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"step": 20300,
|
| 1014 |
+
"loss": 0.5794291687011719,
|
| 1015 |
+
"t": 1700098.750090553
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"step": 20400,
|
| 1019 |
+
"loss": 0.5695528793334961,
|
| 1020 |
+
"t": 1700141.093812974
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"step": 20500,
|
| 1024 |
+
"loss": 0.5519681549072266,
|
| 1025 |
+
"t": 1700184.934526209
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"step": 20600,
|
| 1029 |
+
"loss": 0.5447813034057617,
|
| 1030 |
+
"t": 1700228.489352085
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"step": 20700,
|
| 1034 |
+
"loss": 0.5636504745483398,
|
| 1035 |
+
"t": 1700273.524340438
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"step": 20800,
|
| 1039 |
+
"loss": 0.5447636795043945,
|
| 1040 |
+
"t": 1700317.752030316
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"step": 20900,
|
| 1044 |
+
"loss": 0.5499015045166016,
|
| 1045 |
+
"t": 1700361.51542248
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"step": 21000,
|
| 1049 |
+
"loss": 0.5653286361694336,
|
| 1050 |
+
"t": 1700407.275312833
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"step": 21100,
|
| 1054 |
+
"loss": 0.5876527404785157,
|
| 1055 |
+
"t": 1700451.083987316
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"step": 21200,
|
| 1059 |
+
"loss": 0.578244400024414,
|
| 1060 |
+
"t": 1700494.298049584
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"step": 21300,
|
| 1064 |
+
"loss": 0.5616241073608399,
|
| 1065 |
+
"t": 1700540.062072589
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"step": 21400,
|
| 1069 |
+
"loss": 0.5444991302490234,
|
| 1070 |
+
"t": 1700584.675349198
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"step": 21500,
|
| 1074 |
+
"loss": 0.5514233016967773,
|
| 1075 |
+
"t": 1700630.428408315
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"step": 21600,
|
| 1079 |
+
"loss": 0.5818360519409179,
|
| 1080 |
+
"t": 1700675.610093606
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"step": 21700,
|
| 1084 |
+
"loss": 0.5610687637329101,
|
| 1085 |
+
"t": 1700719.186077412
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"step": 21800,
|
| 1089 |
+
"loss": 0.5884971618652344,
|
| 1090 |
+
"t": 1700762.644413768
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"step": 21900,
|
| 1094 |
+
"loss": 0.5605691146850585,
|
| 1095 |
+
"t": 1700807.226494942
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"step": 22000,
|
| 1099 |
+
"loss": 0.5726926803588868,
|
| 1100 |
+
"t": 1700850.239926988
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"step": 22100,
|
| 1104 |
+
"loss": 0.5552725601196289,
|
| 1105 |
+
"t": 1700894.560328586
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"step": 22200,
|
| 1109 |
+
"loss": 0.5431231689453125,
|
| 1110 |
+
"t": 1700940.888317048
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"step": 22300,
|
| 1114 |
+
"loss": 0.5702762985229493,
|
| 1115 |
+
"t": 1700982.500227583
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"step": 22400,
|
| 1119 |
+
"loss": 0.5371834182739258,
|
| 1120 |
+
"t": 1701030.375480301
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"step": 22500,
|
| 1124 |
+
"loss": 0.578619384765625,
|
| 1125 |
+
"t": 1701073.675465452
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"step": 22600,
|
| 1129 |
+
"loss": 0.5689501953125,
|
| 1130 |
+
"t": 1701118.312088135
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"step": 22700,
|
| 1134 |
+
"loss": 0.5671041107177734,
|
| 1135 |
+
"t": 1701159.923719954
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"step": 22800,
|
| 1139 |
+
"loss": 0.5417391586303711,
|
| 1140 |
+
"t": 1701203.619561347
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"step": 22900,
|
| 1144 |
+
"loss": 0.5681487655639649,
|
| 1145 |
+
"t": 1701246.468903624
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"step": 23000,
|
| 1149 |
+
"loss": 0.5718570709228515,
|
| 1150 |
+
"t": 1701291.577677539
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"step": 23100,
|
| 1154 |
+
"loss": 0.5758842468261719,
|
| 1155 |
+
"t": 1701336.696705475
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"step": 23200,
|
| 1159 |
+
"loss": 0.5655618286132813,
|
| 1160 |
+
"t": 1701381.667655417
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"step": 23300,
|
| 1164 |
+
"loss": 0.5633967971801758,
|
| 1165 |
+
"t": 1701426.914559033
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"step": 23400,
|
| 1169 |
+
"loss": 0.5522757720947266,
|
| 1170 |
+
"t": 1701469.841973167
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"step": 23500,
|
| 1174 |
+
"loss": 0.5707307052612305,
|
| 1175 |
+
"t": 1701511.155660081
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"step": 23600,
|
| 1179 |
+
"loss": 0.5499073791503907,
|
| 1180 |
+
"t": 1701556.957678066
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"step": 23700,
|
| 1184 |
+
"loss": 0.5483300399780273,
|
| 1185 |
+
"t": 1701603.711087179
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"step": 23800,
|
| 1189 |
+
"loss": 0.5646514511108398,
|
| 1190 |
+
"t": 1701647.823927945
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"step": 23900,
|
| 1194 |
+
"loss": 0.5577523422241211,
|
| 1195 |
+
"t": 1701694.094652907
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"step": 24000,
|
| 1199 |
+
"loss": 0.5606250381469726,
|
| 1200 |
+
"t": 1701739.189356525
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"step": 24100,
|
| 1204 |
+
"loss": 0.57211181640625,
|
| 1205 |
+
"t": 1701779.098156807
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"step": 24200,
|
| 1209 |
+
"loss": 0.5427928924560547,
|
| 1210 |
+
"t": 1701824.350083464
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"step": 24300,
|
| 1214 |
+
"loss": 0.5596239471435547,
|
| 1215 |
+
"t": 1701871.317381461
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"step": 24400,
|
| 1219 |
+
"loss": 0.5681907272338867,
|
| 1220 |
+
"t": 1701914.131842281
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"step": 24500,
|
| 1224 |
+
"loss": 0.5436590957641602,
|
| 1225 |
+
"t": 1701958.470130924
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"step": 24600,
|
| 1229 |
+
"loss": 0.571413917541504,
|
| 1230 |
+
"t": 1702002.709205675
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"step": 24700,
|
| 1234 |
+
"loss": 0.5607781600952149,
|
| 1235 |
+
"t": 1702046.727741482
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"step": 24800,
|
| 1239 |
+
"loss": 0.5735754013061524,
|
| 1240 |
+
"t": 1702089.365273986
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"step": 24900,
|
| 1244 |
+
"loss": 0.5705655670166015,
|
| 1245 |
+
"t": 1702133.624217421
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"step": 25000,
|
| 1249 |
+
"loss": 0.5718703842163086,
|
| 1250 |
+
"t": 1702178.308108437
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"step": 25100,
|
| 1254 |
+
"loss": 0.5830942916870118,
|
| 1255 |
+
"t": 1702220.917954345
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"step": 25200,
|
| 1259 |
+
"loss": 0.5509040832519532,
|
| 1260 |
+
"t": 1702264.42379614
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"step": 25300,
|
| 1264 |
+
"loss": 0.5640538787841797,
|
| 1265 |
+
"t": 1702308.832770753
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"step": 25400,
|
| 1269 |
+
"loss": 0.5620045089721679,
|
| 1270 |
+
"t": 1702353.073689964
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"step": 25500,
|
| 1274 |
+
"loss": 0.5827101516723633,
|
| 1275 |
+
"t": 1702397.505187809
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"step": 25600,
|
| 1279 |
+
"loss": 0.5593326187133789,
|
| 1280 |
+
"t": 1702442.817524543
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"step": 25700,
|
| 1284 |
+
"loss": 0.5580775451660156,
|
| 1285 |
+
"t": 1702485.77790557
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"step": 25800,
|
| 1289 |
+
"loss": 0.5587374114990235,
|
| 1290 |
+
"t": 1702531.282573467
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"step": 25900,
|
| 1294 |
+
"loss": 0.5347352600097657,
|
| 1295 |
+
"t": 1702574.705633898
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"step": 26000,
|
| 1299 |
+
"loss": 0.5709453582763672,
|
| 1300 |
+
"t": 1702618.923409273
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"step": 26100,
|
| 1304 |
+
"loss": 0.5517694091796875,
|
| 1305 |
+
"t": 1702663.183174885
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"step": 26200,
|
| 1309 |
+
"loss": 0.5597899246215821,
|
| 1310 |
+
"t": 1702708.466587076
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"step": 26300,
|
| 1314 |
+
"loss": 0.5907904815673828,
|
| 1315 |
+
"t": 1702752.607481363
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"step": 26400,
|
| 1319 |
+
"loss": 0.5653469467163086,
|
| 1320 |
+
"t": 1702796.432253433
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"step": 26500,
|
| 1324 |
+
"loss": 0.5810814666748046,
|
| 1325 |
+
"t": 1702841.98211562
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"step": 26600,
|
| 1329 |
+
"loss": 0.5623080825805664,
|
| 1330 |
+
"t": 1702886.378365241
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"step": 26700,
|
| 1334 |
+
"loss": 0.5708089828491211,
|
| 1335 |
+
"t": 1702932.904234026
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"step": 26800,
|
| 1339 |
+
"loss": 0.557642822265625,
|
| 1340 |
+
"t": 1702975.159499809
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"step": 26900,
|
| 1344 |
+
"loss": 0.5533229827880859,
|
| 1345 |
+
"t": 1703021.566680732
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"step": 27000,
|
| 1349 |
+
"loss": 0.5664892578125,
|
| 1350 |
+
"t": 1703065.265472405
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"step": 27100,
|
| 1354 |
+
"loss": 0.5447317123413086,
|
| 1355 |
+
"t": 1703108.425677248
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"step": 27200,
|
| 1359 |
+
"loss": 0.5859284591674805,
|
| 1360 |
+
"t": 1703151.246664022
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"step": 27300,
|
| 1364 |
+
"loss": 0.5261310195922851,
|
| 1365 |
+
"t": 1703196.138398239
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"step": 27400,
|
| 1369 |
+
"loss": 0.5570074462890625,
|
| 1370 |
+
"t": 1703238.259271553
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"step": 27500,
|
| 1374 |
+
"loss": 0.5668302536010742,
|
| 1375 |
+
"t": 1703282.290797408
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"step": 27600,
|
| 1379 |
+
"loss": 0.5603901290893555,
|
| 1380 |
+
"t": 1703327.032994639
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"step": 27700,
|
| 1384 |
+
"loss": 0.57125,
|
| 1385 |
+
"t": 1703370.036035151
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"step": 27800,
|
| 1389 |
+
"loss": 0.5638277053833007,
|
| 1390 |
+
"t": 1703414.67244942
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"step": 27900,
|
| 1394 |
+
"loss": 0.5704018783569336,
|
| 1395 |
+
"t": 1703458.484645789
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"step": 28000,
|
| 1399 |
+
"loss": 0.5544704055786133,
|
| 1400 |
+
"t": 1703503.087290782
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"step": 28100,
|
| 1404 |
+
"loss": 0.5652946853637695,
|
| 1405 |
+
"t": 1703548.669069506
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"step": 28200,
|
| 1409 |
+
"loss": 0.5656243515014648,
|
| 1410 |
+
"t": 1703592.615589492
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"step": 28300,
|
| 1414 |
+
"loss": 0.5883487701416016,
|
| 1415 |
+
"t": 1703634.16148655
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"step": 28400,
|
| 1419 |
+
"loss": 0.5690061569213867,
|
| 1420 |
+
"t": 1703678.056877092
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"step": 28500,
|
| 1424 |
+
"loss": 0.5424456787109375,
|
| 1425 |
+
"t": 1703723.147431947
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"step": 28600,
|
| 1429 |
+
"loss": 0.5710562896728516,
|
| 1430 |
+
"t": 1703770.111836274
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"step": 28700,
|
| 1434 |
+
"loss": 0.5381825637817382,
|
| 1435 |
+
"t": 1703815.494224571
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"step": 28800,
|
| 1439 |
+
"loss": 0.563104248046875,
|
| 1440 |
+
"t": 1703858.417021854
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"step": 28900,
|
| 1444 |
+
"loss": 0.547737045288086,
|
| 1445 |
+
"t": 1703902.929697174
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"step": 29000,
|
| 1449 |
+
"loss": 0.5633120727539063,
|
| 1450 |
+
"t": 1703945.140712763
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"step": 29100,
|
| 1454 |
+
"loss": 0.5706003952026367,
|
| 1455 |
+
"t": 1703989.194035754
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"step": 29200,
|
| 1459 |
+
"loss": 0.5426315307617188,
|
| 1460 |
+
"t": 1704031.746832633
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"step": 29300,
|
| 1464 |
+
"loss": 0.5370788955688477,
|
| 1465 |
+
"t": 1704076.380782103
|
| 1466 |
+
}
|
| 1467 |
+
]
|
v9/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ba73800666493a63842d87eaaee3e51b5f78ba993f67be3a9880f4a773f4906
|
| 3 |
+
size 5228717512
|
v9/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:487cee8724215dcd2dde8888539e8b1bf844ceb5dbbe27f7845abda69eeb060f
|
| 3 |
+
size 34362872
|
v9/tokenizer_config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<bos>",
|
| 4 |
+
"clean_up_tokenization_spaces": false,
|
| 5 |
+
"eos_token": "<eos>",
|
| 6 |
+
"extra_special_tokens": [
|
| 7 |
+
"<start_of_turn>",
|
| 8 |
+
"<end_of_turn>"
|
| 9 |
+
],
|
| 10 |
+
"is_local": true,
|
| 11 |
+
"local_files_only": false,
|
| 12 |
+
"mask_token": "<mask>",
|
| 13 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 14 |
+
"pad_token": "<pad>",
|
| 15 |
+
"sp_model_kwargs": {},
|
| 16 |
+
"spaces_between_special_tokens": false,
|
| 17 |
+
"tokenizer_class": "GemmaTokenizer",
|
| 18 |
+
"unk_token": "<unk>",
|
| 19 |
+
"use_default_system_prompt": false
|
| 20 |
+
}
|
v9/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85f50dd8d611729cdbd84a2eebaee715621e693ba54e232629a7af3602150c67
|
| 3 |
+
size 5201
|