Upload folder using huggingface_hub
Browse files- checkpoint-2014/config.json +33 -0
- checkpoint-2014/generation_config.json +7 -0
- checkpoint-2014/model.safetensors +3 -0
- checkpoint-2014/optimizer.pt +3 -0
- checkpoint-2014/rng_state.pth +3 -0
- checkpoint-2014/scheduler.pt +3 -0
- checkpoint-2014/trainer_state.json +1440 -0
- checkpoint-2014/training_args.bin +3 -0
- config.json +33 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- special_tokens_map.json +44 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +47 -0
- training_args.bin +3 -0
checkpoint-2014/config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "appvoid/arco-2.1",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"head_dim": 96,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 1536,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 4096,
|
| 15 |
+
"max_position_embeddings": 8192,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"num_attention_heads": 16,
|
| 19 |
+
"num_hidden_layers": 16,
|
| 20 |
+
"num_key_value_heads": 8,
|
| 21 |
+
"pad_token_id": 0,
|
| 22 |
+
"pretraining_tp": 1,
|
| 23 |
+
"rms_norm_eps": 1e-05,
|
| 24 |
+
"rope_scaling": null,
|
| 25 |
+
"rope_theta": 100000,
|
| 26 |
+
"sliding_window": null,
|
| 27 |
+
"tie_word_embeddings": false,
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.46.1",
|
| 30 |
+
"unsloth_version": "2024.7",
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 32000
|
| 33 |
+
}
|
checkpoint-2014/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.46.1"
|
| 7 |
+
}
|
checkpoint-2014/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ef37432361d17c0088e9082800949f4279746c6d5535eaa440181b70521e27a
|
| 3 |
+
size 2054379856
|
checkpoint-2014/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0ffc19b2ad2f62e0453de5935ba7dbd9ecf518454de91e0e5d38d21c175b0e1
|
| 3 |
+
size 4108850298
|
checkpoint-2014/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
|
| 3 |
+
size 14244
|
checkpoint-2014/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc768ed48ad99e4b065bdfee53e82828a0e480d833856e9522bc3f5885018e81
|
| 3 |
+
size 1064
|
checkpoint-2014/trainer_state.json
ADDED
|
@@ -0,0 +1,1440 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 5000,
|
| 6 |
+
"global_step": 2014,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.009930486593843098,
|
| 13 |
+
"grad_norm": Infinity,
|
| 14 |
+
"learning_rate": 0.0,
|
| 15 |
+
"loss": 14.711,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.019860973187686197,
|
| 20 |
+
"grad_norm": 4983.64990234375,
|
| 21 |
+
"learning_rate": 2.0000000000000002e-07,
|
| 22 |
+
"loss": 14.5984,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.029791459781529295,
|
| 27 |
+
"grad_norm": 19263.828125,
|
| 28 |
+
"learning_rate": 4.0000000000000003e-07,
|
| 29 |
+
"loss": 14.0403,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.039721946375372394,
|
| 34 |
+
"grad_norm": 33094.21484375,
|
| 35 |
+
"learning_rate": 6.000000000000001e-07,
|
| 36 |
+
"loss": 12.7662,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.04965243296921549,
|
| 41 |
+
"grad_norm": 92821.109375,
|
| 42 |
+
"learning_rate": 8.000000000000001e-07,
|
| 43 |
+
"loss": 11.4273,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.05958291956305859,
|
| 48 |
+
"grad_norm": 8011.658203125,
|
| 49 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 50 |
+
"loss": 10.0555,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.06951340615690169,
|
| 55 |
+
"grad_norm": 6365.61962890625,
|
| 56 |
+
"learning_rate": 1.2000000000000002e-06,
|
| 57 |
+
"loss": 9.0921,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.07944389275074479,
|
| 62 |
+
"grad_norm": 398.2843933105469,
|
| 63 |
+
"learning_rate": 1.4000000000000001e-06,
|
| 64 |
+
"loss": 7.661,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.08937437934458789,
|
| 69 |
+
"grad_norm": 158.12139892578125,
|
| 70 |
+
"learning_rate": 1.6000000000000001e-06,
|
| 71 |
+
"loss": 6.3558,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.09930486593843098,
|
| 76 |
+
"grad_norm": 103.36075592041016,
|
| 77 |
+
"learning_rate": 1.8000000000000001e-06,
|
| 78 |
+
"loss": 5.9047,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.10923535253227408,
|
| 83 |
+
"grad_norm": 565.8269653320312,
|
| 84 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 85 |
+
"loss": 5.6256,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.11916583912611718,
|
| 90 |
+
"grad_norm": 414.0867919921875,
|
| 91 |
+
"learning_rate": 2.2e-06,
|
| 92 |
+
"loss": 5.3668,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.12909632571996027,
|
| 97 |
+
"grad_norm": 153.89100646972656,
|
| 98 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 99 |
+
"loss": 5.0483,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.13902681231380337,
|
| 104 |
+
"grad_norm": 149.46444702148438,
|
| 105 |
+
"learning_rate": 2.6e-06,
|
| 106 |
+
"loss": 4.8008,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.14895729890764647,
|
| 111 |
+
"grad_norm": 259.7363586425781,
|
| 112 |
+
"learning_rate": 2.8000000000000003e-06,
|
| 113 |
+
"loss": 4.6652,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.15888778550148958,
|
| 118 |
+
"grad_norm": 575.7271728515625,
|
| 119 |
+
"learning_rate": 3e-06,
|
| 120 |
+
"loss": 4.4912,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.16881827209533268,
|
| 125 |
+
"grad_norm": 316.88525390625,
|
| 126 |
+
"learning_rate": 3.2000000000000003e-06,
|
| 127 |
+
"loss": 4.2479,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.17874875868917578,
|
| 132 |
+
"grad_norm": 310.1224670410156,
|
| 133 |
+
"learning_rate": 3.4000000000000005e-06,
|
| 134 |
+
"loss": 4.0592,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.18867924528301888,
|
| 139 |
+
"grad_norm": 366.346435546875,
|
| 140 |
+
"learning_rate": 3.6000000000000003e-06,
|
| 141 |
+
"loss": 3.8585,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.19860973187686196,
|
| 146 |
+
"grad_norm": 242.16476440429688,
|
| 147 |
+
"learning_rate": 3.8000000000000005e-06,
|
| 148 |
+
"loss": 3.6879,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.20854021847070506,
|
| 153 |
+
"grad_norm": 445.31646728515625,
|
| 154 |
+
"learning_rate": 4.000000000000001e-06,
|
| 155 |
+
"loss": 3.5381,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.21847070506454816,
|
| 160 |
+
"grad_norm": 345.4029235839844,
|
| 161 |
+
"learning_rate": 4.2000000000000004e-06,
|
| 162 |
+
"loss": 3.272,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.22840119165839126,
|
| 167 |
+
"grad_norm": 243.06161499023438,
|
| 168 |
+
"learning_rate": 4.4e-06,
|
| 169 |
+
"loss": 3.0486,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.23833167825223436,
|
| 174 |
+
"grad_norm": 237.27239990234375,
|
| 175 |
+
"learning_rate": 4.600000000000001e-06,
|
| 176 |
+
"loss": 2.7942,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.24826216484607747,
|
| 181 |
+
"grad_norm": 209.28985595703125,
|
| 182 |
+
"learning_rate": 4.800000000000001e-06,
|
| 183 |
+
"loss": 2.5742,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.25819265143992054,
|
| 188 |
+
"grad_norm": 458.2777099609375,
|
| 189 |
+
"learning_rate": 5e-06,
|
| 190 |
+
"loss": 2.5509,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.26812313803376364,
|
| 195 |
+
"grad_norm": 431.66522216796875,
|
| 196 |
+
"learning_rate": 5.2e-06,
|
| 197 |
+
"loss": 2.4819,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.27805362462760674,
|
| 202 |
+
"grad_norm": 314.18792724609375,
|
| 203 |
+
"learning_rate": 5.400000000000001e-06,
|
| 204 |
+
"loss": 2.2044,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.28798411122144985,
|
| 209 |
+
"grad_norm": 366.9264831542969,
|
| 210 |
+
"learning_rate": 5.600000000000001e-06,
|
| 211 |
+
"loss": 1.9759,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.29791459781529295,
|
| 216 |
+
"grad_norm": 148.99159240722656,
|
| 217 |
+
"learning_rate": 5.8e-06,
|
| 218 |
+
"loss": 1.7,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.30784508440913605,
|
| 223 |
+
"grad_norm": 324.4754638671875,
|
| 224 |
+
"learning_rate": 6e-06,
|
| 225 |
+
"loss": 1.5349,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.31777557100297915,
|
| 230 |
+
"grad_norm": 205.2728729248047,
|
| 231 |
+
"learning_rate": 6.200000000000001e-06,
|
| 232 |
+
"loss": 1.4228,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.32770605759682225,
|
| 237 |
+
"grad_norm": 312.1114807128906,
|
| 238 |
+
"learning_rate": 6.4000000000000006e-06,
|
| 239 |
+
"loss": 1.3114,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.33763654419066536,
|
| 244 |
+
"grad_norm": 274.58221435546875,
|
| 245 |
+
"learning_rate": 6.600000000000001e-06,
|
| 246 |
+
"loss": 1.2638,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.34756703078450846,
|
| 251 |
+
"grad_norm": 239.2190399169922,
|
| 252 |
+
"learning_rate": 6.800000000000001e-06,
|
| 253 |
+
"loss": 1.031,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.35749751737835156,
|
| 258 |
+
"grad_norm": 208.7018585205078,
|
| 259 |
+
"learning_rate": 7e-06,
|
| 260 |
+
"loss": 0.92,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.36742800397219466,
|
| 265 |
+
"grad_norm": 237.0693817138672,
|
| 266 |
+
"learning_rate": 7.2000000000000005e-06,
|
| 267 |
+
"loss": 1.665,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.37735849056603776,
|
| 272 |
+
"grad_norm": 208.263671875,
|
| 273 |
+
"learning_rate": 7.4e-06,
|
| 274 |
+
"loss": 0.7744,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.3872889771598808,
|
| 279 |
+
"grad_norm": 184.25924682617188,
|
| 280 |
+
"learning_rate": 7.600000000000001e-06,
|
| 281 |
+
"loss": 0.809,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.3972194637537239,
|
| 286 |
+
"grad_norm": 146.69178771972656,
|
| 287 |
+
"learning_rate": 7.800000000000002e-06,
|
| 288 |
+
"loss": 0.7246,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.407149950347567,
|
| 293 |
+
"grad_norm": 207.02853393554688,
|
| 294 |
+
"learning_rate": 8.000000000000001e-06,
|
| 295 |
+
"loss": 0.7616,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.4170804369414101,
|
| 300 |
+
"grad_norm": 146.81492614746094,
|
| 301 |
+
"learning_rate": 8.2e-06,
|
| 302 |
+
"loss": 0.5971,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.4270109235352532,
|
| 307 |
+
"grad_norm": 135.36524963378906,
|
| 308 |
+
"learning_rate": 8.400000000000001e-06,
|
| 309 |
+
"loss": 1.2755,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.4369414101290963,
|
| 314 |
+
"grad_norm": 298.3485107421875,
|
| 315 |
+
"learning_rate": 8.6e-06,
|
| 316 |
+
"loss": 1.6886,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.4468718967229394,
|
| 321 |
+
"grad_norm": 240.9180908203125,
|
| 322 |
+
"learning_rate": 8.8e-06,
|
| 323 |
+
"loss": 0.8591,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.4568023833167825,
|
| 328 |
+
"grad_norm": 152.96194458007812,
|
| 329 |
+
"learning_rate": 9e-06,
|
| 330 |
+
"loss": 0.7211,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.4667328699106256,
|
| 335 |
+
"grad_norm": 5467.83447265625,
|
| 336 |
+
"learning_rate": 9.180000000000002e-06,
|
| 337 |
+
"loss": 1.4453,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.4766633565044687,
|
| 342 |
+
"grad_norm": 249.68312072753906,
|
| 343 |
+
"learning_rate": 9.38e-06,
|
| 344 |
+
"loss": 0.718,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.48659384309831183,
|
| 349 |
+
"grad_norm": 75.28675842285156,
|
| 350 |
+
"learning_rate": 9.58e-06,
|
| 351 |
+
"loss": 0.5454,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.49652432969215493,
|
| 356 |
+
"grad_norm": 98.99024963378906,
|
| 357 |
+
"learning_rate": 9.780000000000001e-06,
|
| 358 |
+
"loss": 0.5422,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.506454816285998,
|
| 363 |
+
"grad_norm": 97.877197265625,
|
| 364 |
+
"learning_rate": 9.980000000000001e-06,
|
| 365 |
+
"loss": 0.5424,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.5163853028798411,
|
| 370 |
+
"grad_norm": 58.41091537475586,
|
| 371 |
+
"learning_rate": 9.940554821664465e-06,
|
| 372 |
+
"loss": 0.4753,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.5263157894736842,
|
| 377 |
+
"grad_norm": 50.91957092285156,
|
| 378 |
+
"learning_rate": 9.87450462351387e-06,
|
| 379 |
+
"loss": 0.4657,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.5362462760675273,
|
| 384 |
+
"grad_norm": 66.574462890625,
|
| 385 |
+
"learning_rate": 9.808454425363277e-06,
|
| 386 |
+
"loss": 0.378,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.5461767626613704,
|
| 391 |
+
"grad_norm": 108.19845581054688,
|
| 392 |
+
"learning_rate": 9.742404227212683e-06,
|
| 393 |
+
"loss": 0.4171,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.5561072492552135,
|
| 398 |
+
"grad_norm": 44.33118438720703,
|
| 399 |
+
"learning_rate": 9.676354029062089e-06,
|
| 400 |
+
"loss": 0.4289,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.5660377358490566,
|
| 405 |
+
"grad_norm": 61.063758850097656,
|
| 406 |
+
"learning_rate": 9.610303830911495e-06,
|
| 407 |
+
"loss": 0.3511,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.5759682224428997,
|
| 412 |
+
"grad_norm": 91.71956634521484,
|
| 413 |
+
"learning_rate": 9.544253632760899e-06,
|
| 414 |
+
"loss": 0.4377,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.5858987090367428,
|
| 419 |
+
"grad_norm": 46.6739501953125,
|
| 420 |
+
"learning_rate": 9.478203434610305e-06,
|
| 421 |
+
"loss": 0.351,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.5958291956305859,
|
| 426 |
+
"grad_norm": 38.2111701965332,
|
| 427 |
+
"learning_rate": 9.41215323645971e-06,
|
| 428 |
+
"loss": 0.3556,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.605759682224429,
|
| 433 |
+
"grad_norm": 61.8499755859375,
|
| 434 |
+
"learning_rate": 9.346103038309115e-06,
|
| 435 |
+
"loss": 0.4027,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.6156901688182721,
|
| 440 |
+
"grad_norm": 219.7929229736328,
|
| 441 |
+
"learning_rate": 9.280052840158521e-06,
|
| 442 |
+
"loss": 0.4932,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.6256206554121152,
|
| 447 |
+
"grad_norm": 52.08991241455078,
|
| 448 |
+
"learning_rate": 9.214002642007927e-06,
|
| 449 |
+
"loss": 0.4588,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.6355511420059583,
|
| 454 |
+
"grad_norm": 28.5477294921875,
|
| 455 |
+
"learning_rate": 9.147952443857333e-06,
|
| 456 |
+
"loss": 0.3302,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.6454816285998014,
|
| 461 |
+
"grad_norm": 24.50048065185547,
|
| 462 |
+
"learning_rate": 9.081902245706737e-06,
|
| 463 |
+
"loss": 0.3144,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.6554121151936445,
|
| 468 |
+
"grad_norm": 59.86844253540039,
|
| 469 |
+
"learning_rate": 9.015852047556145e-06,
|
| 470 |
+
"loss": 0.3919,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.6653426017874876,
|
| 475 |
+
"grad_norm": 22.47603988647461,
|
| 476 |
+
"learning_rate": 8.949801849405549e-06,
|
| 477 |
+
"loss": 0.37,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.6752730883813307,
|
| 482 |
+
"grad_norm": 21.400466918945312,
|
| 483 |
+
"learning_rate": 8.883751651254955e-06,
|
| 484 |
+
"loss": 0.3293,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.6852035749751738,
|
| 489 |
+
"grad_norm": 16.669824600219727,
|
| 490 |
+
"learning_rate": 8.81770145310436e-06,
|
| 491 |
+
"loss": 0.2647,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.6951340615690169,
|
| 496 |
+
"grad_norm": 23.852384567260742,
|
| 497 |
+
"learning_rate": 8.751651254953765e-06,
|
| 498 |
+
"loss": 0.3246,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.70506454816286,
|
| 503 |
+
"grad_norm": 38.244258880615234,
|
| 504 |
+
"learning_rate": 8.685601056803171e-06,
|
| 505 |
+
"loss": 0.385,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.7149950347567031,
|
| 510 |
+
"grad_norm": 29.78006362915039,
|
| 511 |
+
"learning_rate": 8.619550858652577e-06,
|
| 512 |
+
"loss": 0.3071,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.7249255213505462,
|
| 517 |
+
"grad_norm": 24.519458770751953,
|
| 518 |
+
"learning_rate": 8.553500660501983e-06,
|
| 519 |
+
"loss": 0.3429,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.7348560079443893,
|
| 524 |
+
"grad_norm": 25.153671264648438,
|
| 525 |
+
"learning_rate": 8.487450462351387e-06,
|
| 526 |
+
"loss": 0.3843,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.7447864945382324,
|
| 531 |
+
"grad_norm": 27.24303436279297,
|
| 532 |
+
"learning_rate": 8.421400264200793e-06,
|
| 533 |
+
"loss": 0.369,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.7547169811320755,
|
| 538 |
+
"grad_norm": 14.806120872497559,
|
| 539 |
+
"learning_rate": 8.355350066050199e-06,
|
| 540 |
+
"loss": 0.301,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.7646474677259185,
|
| 545 |
+
"grad_norm": 22.724933624267578,
|
| 546 |
+
"learning_rate": 8.289299867899603e-06,
|
| 547 |
+
"loss": 0.3101,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.7745779543197616,
|
| 552 |
+
"grad_norm": 15.89284610748291,
|
| 553 |
+
"learning_rate": 8.22324966974901e-06,
|
| 554 |
+
"loss": 0.3665,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.7845084409136047,
|
| 559 |
+
"grad_norm": 87.12956237792969,
|
| 560 |
+
"learning_rate": 8.157199471598415e-06,
|
| 561 |
+
"loss": 0.4025,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.7944389275074478,
|
| 566 |
+
"grad_norm": 27.03380012512207,
|
| 567 |
+
"learning_rate": 8.091149273447821e-06,
|
| 568 |
+
"loss": 0.2919,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.8043694141012909,
|
| 573 |
+
"grad_norm": 27.622365951538086,
|
| 574 |
+
"learning_rate": 8.025099075297227e-06,
|
| 575 |
+
"loss": 0.3441,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.814299900695134,
|
| 580 |
+
"grad_norm": 32.42015838623047,
|
| 581 |
+
"learning_rate": 7.959048877146633e-06,
|
| 582 |
+
"loss": 0.3307,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.8242303872889771,
|
| 587 |
+
"grad_norm": 16.96957015991211,
|
| 588 |
+
"learning_rate": 7.892998678996037e-06,
|
| 589 |
+
"loss": 0.3224,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.8341608738828202,
|
| 594 |
+
"grad_norm": 12.882108688354492,
|
| 595 |
+
"learning_rate": 7.826948480845443e-06,
|
| 596 |
+
"loss": 0.2992,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.8440913604766633,
|
| 601 |
+
"grad_norm": 17.12813949584961,
|
| 602 |
+
"learning_rate": 7.760898282694849e-06,
|
| 603 |
+
"loss": 0.2783,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.8540218470705064,
|
| 608 |
+
"grad_norm": 57.04343795776367,
|
| 609 |
+
"learning_rate": 7.694848084544253e-06,
|
| 610 |
+
"loss": 0.4445,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.8639523336643495,
|
| 615 |
+
"grad_norm": 17.658185958862305,
|
| 616 |
+
"learning_rate": 7.628797886393659e-06,
|
| 617 |
+
"loss": 0.322,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.8738828202581926,
|
| 622 |
+
"grad_norm": 37.49673080444336,
|
| 623 |
+
"learning_rate": 7.562747688243065e-06,
|
| 624 |
+
"loss": 0.5781,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.8838133068520357,
|
| 629 |
+
"grad_norm": 22.256288528442383,
|
| 630 |
+
"learning_rate": 7.49669749009247e-06,
|
| 631 |
+
"loss": 0.3146,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.8937437934458788,
|
| 636 |
+
"grad_norm": 28.0767765045166,
|
| 637 |
+
"learning_rate": 7.430647291941876e-06,
|
| 638 |
+
"loss": 0.2795,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.9036742800397219,
|
| 643 |
+
"grad_norm": 26.734256744384766,
|
| 644 |
+
"learning_rate": 7.364597093791282e-06,
|
| 645 |
+
"loss": 0.286,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.913604766633565,
|
| 650 |
+
"grad_norm": 16.944440841674805,
|
| 651 |
+
"learning_rate": 7.298546895640688e-06,
|
| 652 |
+
"loss": 0.2396,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.9235352532274081,
|
| 657 |
+
"grad_norm": 11.377096176147461,
|
| 658 |
+
"learning_rate": 7.232496697490093e-06,
|
| 659 |
+
"loss": 0.3234,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.9334657398212513,
|
| 664 |
+
"grad_norm": 21.92275047302246,
|
| 665 |
+
"learning_rate": 7.166446499339499e-06,
|
| 666 |
+
"loss": 0.3054,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.9433962264150944,
|
| 671 |
+
"grad_norm": 11.469223976135254,
|
| 672 |
+
"learning_rate": 7.100396301188904e-06,
|
| 673 |
+
"loss": 0.2805,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.9533267130089375,
|
| 678 |
+
"grad_norm": 21.188453674316406,
|
| 679 |
+
"learning_rate": 7.034346103038309e-06,
|
| 680 |
+
"loss": 0.3169,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.9632571996027806,
|
| 685 |
+
"grad_norm": 14.333311080932617,
|
| 686 |
+
"learning_rate": 6.968295904887715e-06,
|
| 687 |
+
"loss": 0.2381,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.9731876861966237,
|
| 692 |
+
"grad_norm": 10.782018661499023,
|
| 693 |
+
"learning_rate": 6.90224570673712e-06,
|
| 694 |
+
"loss": 0.2914,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.9831181727904668,
|
| 699 |
+
"grad_norm": 12.117927551269531,
|
| 700 |
+
"learning_rate": 6.836195508586526e-06,
|
| 701 |
+
"loss": 0.3186,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.9930486593843099,
|
| 706 |
+
"grad_norm": 15.109565734863281,
|
| 707 |
+
"learning_rate": 6.7701453104359315e-06,
|
| 708 |
+
"loss": 0.2323,
|
| 709 |
+
"step": 1000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.002979145978153,
|
| 713 |
+
"grad_norm": 27.17137336730957,
|
| 714 |
+
"learning_rate": 6.704095112285337e-06,
|
| 715 |
+
"loss": 0.2664,
|
| 716 |
+
"step": 1010
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.012909632571996,
|
| 720 |
+
"grad_norm": 17.559146881103516,
|
| 721 |
+
"learning_rate": 6.6380449141347425e-06,
|
| 722 |
+
"loss": 0.3117,
|
| 723 |
+
"step": 1020
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.0228401191658392,
|
| 727 |
+
"grad_norm": 18.243568420410156,
|
| 728 |
+
"learning_rate": 6.571994715984148e-06,
|
| 729 |
+
"loss": 0.2746,
|
| 730 |
+
"step": 1030
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.0327706057596822,
|
| 734 |
+
"grad_norm": 19.41541862487793,
|
| 735 |
+
"learning_rate": 6.505944517833554e-06,
|
| 736 |
+
"loss": 0.2757,
|
| 737 |
+
"step": 1040
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.0427010923535254,
|
| 741 |
+
"grad_norm": 23.584136962890625,
|
| 742 |
+
"learning_rate": 6.43989431968296e-06,
|
| 743 |
+
"loss": 0.3311,
|
| 744 |
+
"step": 1050
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.0526315789473684,
|
| 748 |
+
"grad_norm": 8.158661842346191,
|
| 749 |
+
"learning_rate": 6.3738441215323654e-06,
|
| 750 |
+
"loss": 0.2664,
|
| 751 |
+
"step": 1060
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.0625620655412116,
|
| 755 |
+
"grad_norm": 14.265728950500488,
|
| 756 |
+
"learning_rate": 6.3077939233817705e-06,
|
| 757 |
+
"loss": 0.3737,
|
| 758 |
+
"step": 1070
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.0724925521350546,
|
| 762 |
+
"grad_norm": 45.05762481689453,
|
| 763 |
+
"learning_rate": 6.2417437252311765e-06,
|
| 764 |
+
"loss": 0.2805,
|
| 765 |
+
"step": 1080
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.0824230387288978,
|
| 769 |
+
"grad_norm": 26.889284133911133,
|
| 770 |
+
"learning_rate": 6.1756935270805816e-06,
|
| 771 |
+
"loss": 0.3286,
|
| 772 |
+
"step": 1090
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.0923535253227408,
|
| 776 |
+
"grad_norm": 14.202479362487793,
|
| 777 |
+
"learning_rate": 6.1096433289299875e-06,
|
| 778 |
+
"loss": 0.2859,
|
| 779 |
+
"step": 1100
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.102284011916584,
|
| 783 |
+
"grad_norm": 14.509482383728027,
|
| 784 |
+
"learning_rate": 6.043593130779393e-06,
|
| 785 |
+
"loss": 0.2255,
|
| 786 |
+
"step": 1110
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.112214498510427,
|
| 790 |
+
"grad_norm": 17.728469848632812,
|
| 791 |
+
"learning_rate": 5.9775429326287985e-06,
|
| 792 |
+
"loss": 0.2592,
|
| 793 |
+
"step": 1120
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.1221449851042702,
|
| 797 |
+
"grad_norm": 15.352997779846191,
|
| 798 |
+
"learning_rate": 5.911492734478204e-06,
|
| 799 |
+
"loss": 0.2538,
|
| 800 |
+
"step": 1130
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.1320754716981132,
|
| 804 |
+
"grad_norm": 12.579967498779297,
|
| 805 |
+
"learning_rate": 5.845442536327609e-06,
|
| 806 |
+
"loss": 0.2803,
|
| 807 |
+
"step": 1140
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.1420059582919564,
|
| 811 |
+
"grad_norm": 9.809431076049805,
|
| 812 |
+
"learning_rate": 5.779392338177015e-06,
|
| 813 |
+
"loss": 0.2874,
|
| 814 |
+
"step": 1150
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.1519364448857994,
|
| 818 |
+
"grad_norm": 18.45332145690918,
|
| 819 |
+
"learning_rate": 5.7133421400264215e-06,
|
| 820 |
+
"loss": 0.3388,
|
| 821 |
+
"step": 1160
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.1618669314796426,
|
| 825 |
+
"grad_norm": 15.697205543518066,
|
| 826 |
+
"learning_rate": 5.6472919418758266e-06,
|
| 827 |
+
"loss": 0.6377,
|
| 828 |
+
"step": 1170
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 1.1717974180734856,
|
| 832 |
+
"grad_norm": 245.89466857910156,
|
| 833 |
+
"learning_rate": 5.581241743725232e-06,
|
| 834 |
+
"loss": 0.4898,
|
| 835 |
+
"step": 1180
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.1817279046673286,
|
| 839 |
+
"grad_norm": 13.679891586303711,
|
| 840 |
+
"learning_rate": 5.515191545574638e-06,
|
| 841 |
+
"loss": 0.3288,
|
| 842 |
+
"step": 1190
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.1916583912611718,
|
| 846 |
+
"grad_norm": 16.556507110595703,
|
| 847 |
+
"learning_rate": 5.449141347424043e-06,
|
| 848 |
+
"loss": 0.3122,
|
| 849 |
+
"step": 1200
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.201588877855015,
|
| 853 |
+
"grad_norm": 14.205398559570312,
|
| 854 |
+
"learning_rate": 5.383091149273449e-06,
|
| 855 |
+
"loss": 0.2981,
|
| 856 |
+
"step": 1210
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.211519364448858,
|
| 860 |
+
"grad_norm": 12.833841323852539,
|
| 861 |
+
"learning_rate": 5.317040951122854e-06,
|
| 862 |
+
"loss": 0.3071,
|
| 863 |
+
"step": 1220
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 1.221449851042701,
|
| 867 |
+
"grad_norm": 23.980009078979492,
|
| 868 |
+
"learning_rate": 5.250990752972259e-06,
|
| 869 |
+
"loss": 0.2632,
|
| 870 |
+
"step": 1230
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 1.2313803376365442,
|
| 874 |
+
"grad_norm": 17.329069137573242,
|
| 875 |
+
"learning_rate": 5.184940554821665e-06,
|
| 876 |
+
"loss": 0.3039,
|
| 877 |
+
"step": 1240
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 1.2413108242303874,
|
| 881 |
+
"grad_norm": 24.93738555908203,
|
| 882 |
+
"learning_rate": 5.11889035667107e-06,
|
| 883 |
+
"loss": 0.3467,
|
| 884 |
+
"step": 1250
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 1.2512413108242304,
|
| 888 |
+
"grad_norm": 14.432474136352539,
|
| 889 |
+
"learning_rate": 5.052840158520476e-06,
|
| 890 |
+
"loss": 0.2253,
|
| 891 |
+
"step": 1260
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.2611717974180734,
|
| 895 |
+
"grad_norm": 21.262495040893555,
|
| 896 |
+
"learning_rate": 4.986789960369882e-06,
|
| 897 |
+
"loss": 0.3464,
|
| 898 |
+
"step": 1270
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.2711022840119166,
|
| 902 |
+
"grad_norm": 16.39492416381836,
|
| 903 |
+
"learning_rate": 4.920739762219287e-06,
|
| 904 |
+
"loss": 0.2812,
|
| 905 |
+
"step": 1280
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 1.2810327706057598,
|
| 909 |
+
"grad_norm": 9.893121719360352,
|
| 910 |
+
"learning_rate": 4.854689564068693e-06,
|
| 911 |
+
"loss": 0.302,
|
| 912 |
+
"step": 1290
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 1.2909632571996028,
|
| 916 |
+
"grad_norm": 7.951263427734375,
|
| 917 |
+
"learning_rate": 4.788639365918098e-06,
|
| 918 |
+
"loss": 0.4157,
|
| 919 |
+
"step": 1300
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.3008937437934458,
|
| 923 |
+
"grad_norm": 8.177956581115723,
|
| 924 |
+
"learning_rate": 4.722589167767504e-06,
|
| 925 |
+
"loss": 0.206,
|
| 926 |
+
"step": 1310
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.310824230387289,
|
| 930 |
+
"grad_norm": 6.12276029586792,
|
| 931 |
+
"learning_rate": 4.65653896961691e-06,
|
| 932 |
+
"loss": 0.2143,
|
| 933 |
+
"step": 1320
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.320754716981132,
|
| 937 |
+
"grad_norm": 16.6575984954834,
|
| 938 |
+
"learning_rate": 4.590488771466315e-06,
|
| 939 |
+
"loss": 0.2677,
|
| 940 |
+
"step": 1330
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.3306852035749752,
|
| 944 |
+
"grad_norm": 8.128823280334473,
|
| 945 |
+
"learning_rate": 4.52443857331572e-06,
|
| 946 |
+
"loss": 0.2279,
|
| 947 |
+
"step": 1340
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.3406156901688182,
|
| 951 |
+
"grad_norm": 21.915355682373047,
|
| 952 |
+
"learning_rate": 4.458388375165126e-06,
|
| 953 |
+
"loss": 0.2724,
|
| 954 |
+
"step": 1350
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 1.3505461767626614,
|
| 958 |
+
"grad_norm": 18.645946502685547,
|
| 959 |
+
"learning_rate": 4.392338177014531e-06,
|
| 960 |
+
"loss": 0.2307,
|
| 961 |
+
"step": 1360
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 1.3604766633565044,
|
| 965 |
+
"grad_norm": 12.229573249816895,
|
| 966 |
+
"learning_rate": 4.326287978863937e-06,
|
| 967 |
+
"loss": 0.3043,
|
| 968 |
+
"step": 1370
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 1.3704071499503476,
|
| 972 |
+
"grad_norm": 21.465803146362305,
|
| 973 |
+
"learning_rate": 4.260237780713343e-06,
|
| 974 |
+
"loss": 0.3025,
|
| 975 |
+
"step": 1380
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 1.3803376365441906,
|
| 979 |
+
"grad_norm": 12.59046459197998,
|
| 980 |
+
"learning_rate": 4.194187582562748e-06,
|
| 981 |
+
"loss": 0.3685,
|
| 982 |
+
"step": 1390
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 1.3902681231380338,
|
| 986 |
+
"grad_norm": 20.229293823242188,
|
| 987 |
+
"learning_rate": 4.128137384412154e-06,
|
| 988 |
+
"loss": 0.2627,
|
| 989 |
+
"step": 1400
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 1.4001986097318768,
|
| 993 |
+
"grad_norm": 5.609831809997559,
|
| 994 |
+
"learning_rate": 4.062087186261559e-06,
|
| 995 |
+
"loss": 0.3011,
|
| 996 |
+
"step": 1410
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 1.41012909632572,
|
| 1000 |
+
"grad_norm": 13.317000389099121,
|
| 1001 |
+
"learning_rate": 3.996036988110964e-06,
|
| 1002 |
+
"loss": 0.226,
|
| 1003 |
+
"step": 1420
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 1.420059582919563,
|
| 1007 |
+
"grad_norm": 10.011391639709473,
|
| 1008 |
+
"learning_rate": 3.92998678996037e-06,
|
| 1009 |
+
"loss": 0.2295,
|
| 1010 |
+
"step": 1430
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 1.4299900695134062,
|
| 1014 |
+
"grad_norm": 14.472879409790039,
|
| 1015 |
+
"learning_rate": 3.863936591809776e-06,
|
| 1016 |
+
"loss": 0.2577,
|
| 1017 |
+
"step": 1440
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 1.4399205561072492,
|
| 1021 |
+
"grad_norm": 7.8662614822387695,
|
| 1022 |
+
"learning_rate": 3.7978863936591815e-06,
|
| 1023 |
+
"loss": 0.3256,
|
| 1024 |
+
"step": 1450
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 1.4498510427010922,
|
| 1028 |
+
"grad_norm": 23.64836883544922,
|
| 1029 |
+
"learning_rate": 3.731836195508587e-06,
|
| 1030 |
+
"loss": 0.336,
|
| 1031 |
+
"step": 1460
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 1.4597815292949354,
|
| 1035 |
+
"grad_norm": 4.431447982788086,
|
| 1036 |
+
"learning_rate": 3.665785997357992e-06,
|
| 1037 |
+
"loss": 0.3114,
|
| 1038 |
+
"step": 1470
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 1.4697120158887786,
|
| 1042 |
+
"grad_norm": 37.42151641845703,
|
| 1043 |
+
"learning_rate": 3.5997357992073977e-06,
|
| 1044 |
+
"loss": 0.358,
|
| 1045 |
+
"step": 1480
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 1.4796425024826216,
|
| 1049 |
+
"grad_norm": 9.819945335388184,
|
| 1050 |
+
"learning_rate": 3.533685601056803e-06,
|
| 1051 |
+
"loss": 0.2852,
|
| 1052 |
+
"step": 1490
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 1.4895729890764646,
|
| 1056 |
+
"grad_norm": 7.768363952636719,
|
| 1057 |
+
"learning_rate": 3.467635402906209e-06,
|
| 1058 |
+
"loss": 0.2703,
|
| 1059 |
+
"step": 1500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 1.4995034756703078,
|
| 1063 |
+
"grad_norm": 22.80790901184082,
|
| 1064 |
+
"learning_rate": 3.4015852047556147e-06,
|
| 1065 |
+
"loss": 0.2419,
|
| 1066 |
+
"step": 1510
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 1.509433962264151,
|
| 1070 |
+
"grad_norm": 14.61506175994873,
|
| 1071 |
+
"learning_rate": 3.33553500660502e-06,
|
| 1072 |
+
"loss": 0.2263,
|
| 1073 |
+
"step": 1520
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 1.519364448857994,
|
| 1077 |
+
"grad_norm": 17.9895076751709,
|
| 1078 |
+
"learning_rate": 3.2694848084544257e-06,
|
| 1079 |
+
"loss": 0.3096,
|
| 1080 |
+
"step": 1530
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 1.529294935451837,
|
| 1084 |
+
"grad_norm": 17.43570899963379,
|
| 1085 |
+
"learning_rate": 3.2034346103038312e-06,
|
| 1086 |
+
"loss": 0.2388,
|
| 1087 |
+
"step": 1540
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 1.5392254220456802,
|
| 1091 |
+
"grad_norm": 24.771135330200195,
|
| 1092 |
+
"learning_rate": 3.1373844121532363e-06,
|
| 1093 |
+
"loss": 0.2859,
|
| 1094 |
+
"step": 1550
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 1.5491559086395235,
|
| 1098 |
+
"grad_norm": 14.774213790893555,
|
| 1099 |
+
"learning_rate": 3.0713342140026427e-06,
|
| 1100 |
+
"loss": 0.2478,
|
| 1101 |
+
"step": 1560
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.5590863952333665,
|
| 1105 |
+
"grad_norm": 9.036184310913086,
|
| 1106 |
+
"learning_rate": 3.0052840158520478e-06,
|
| 1107 |
+
"loss": 0.2538,
|
| 1108 |
+
"step": 1570
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 1.5690168818272094,
|
| 1112 |
+
"grad_norm": 15.238768577575684,
|
| 1113 |
+
"learning_rate": 2.9392338177014533e-06,
|
| 1114 |
+
"loss": 0.1995,
|
| 1115 |
+
"step": 1580
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.5789473684210527,
|
| 1119 |
+
"grad_norm": 7.666260242462158,
|
| 1120 |
+
"learning_rate": 2.873183619550859e-06,
|
| 1121 |
+
"loss": 0.2648,
|
| 1122 |
+
"step": 1590
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.5888778550148959,
|
| 1126 |
+
"grad_norm": 14.299159049987793,
|
| 1127 |
+
"learning_rate": 2.8071334214002643e-06,
|
| 1128 |
+
"loss": 0.2817,
|
| 1129 |
+
"step": 1600
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.5988083416087389,
|
| 1133 |
+
"grad_norm": 8.902689933776855,
|
| 1134 |
+
"learning_rate": 2.74108322324967e-06,
|
| 1135 |
+
"loss": 0.6261,
|
| 1136 |
+
"step": 1610
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 1.6087388282025818,
|
| 1140 |
+
"grad_norm": 11.452303886413574,
|
| 1141 |
+
"learning_rate": 2.6750330250990754e-06,
|
| 1142 |
+
"loss": 0.2743,
|
| 1143 |
+
"step": 1620
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.618669314796425,
|
| 1147 |
+
"grad_norm": 8.431117057800293,
|
| 1148 |
+
"learning_rate": 2.6089828269484813e-06,
|
| 1149 |
+
"loss": 0.2472,
|
| 1150 |
+
"step": 1630
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.6285998013902683,
|
| 1154 |
+
"grad_norm": 13.621753692626953,
|
| 1155 |
+
"learning_rate": 2.542932628797887e-06,
|
| 1156 |
+
"loss": 0.3552,
|
| 1157 |
+
"step": 1640
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.6385302879841113,
|
| 1161 |
+
"grad_norm": 28.211891174316406,
|
| 1162 |
+
"learning_rate": 2.4768824306472924e-06,
|
| 1163 |
+
"loss": 0.2211,
|
| 1164 |
+
"step": 1650
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.6484607745779543,
|
| 1168 |
+
"grad_norm": 9.634784698486328,
|
| 1169 |
+
"learning_rate": 2.4108322324966975e-06,
|
| 1170 |
+
"loss": 0.7658,
|
| 1171 |
+
"step": 1660
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.6583912611717975,
|
| 1175 |
+
"grad_norm": 10.460068702697754,
|
| 1176 |
+
"learning_rate": 2.3447820343461034e-06,
|
| 1177 |
+
"loss": 0.2257,
|
| 1178 |
+
"step": 1670
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.6683217477656405,
|
| 1182 |
+
"grad_norm": 8.11988639831543,
|
| 1183 |
+
"learning_rate": 2.278731836195509e-06,
|
| 1184 |
+
"loss": 0.2626,
|
| 1185 |
+
"step": 1680
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.6782522343594835,
|
| 1189 |
+
"grad_norm": 12.30396842956543,
|
| 1190 |
+
"learning_rate": 2.2126816380449144e-06,
|
| 1191 |
+
"loss": 0.2174,
|
| 1192 |
+
"step": 1690
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 1.6881827209533267,
|
| 1196 |
+
"grad_norm": 45.93663787841797,
|
| 1197 |
+
"learning_rate": 2.14663143989432e-06,
|
| 1198 |
+
"loss": 0.3282,
|
| 1199 |
+
"step": 1700
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 1.6981132075471699,
|
| 1203 |
+
"grad_norm": 15.4673490524292,
|
| 1204 |
+
"learning_rate": 2.0805812417437255e-06,
|
| 1205 |
+
"loss": 0.2126,
|
| 1206 |
+
"step": 1710
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 1.7080436941410129,
|
| 1210 |
+
"grad_norm": 13.173709869384766,
|
| 1211 |
+
"learning_rate": 2.014531043593131e-06,
|
| 1212 |
+
"loss": 0.2311,
|
| 1213 |
+
"step": 1720
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.7179741807348559,
|
| 1217 |
+
"grad_norm": 17.14373779296875,
|
| 1218 |
+
"learning_rate": 1.9484808454425365e-06,
|
| 1219 |
+
"loss": 0.2538,
|
| 1220 |
+
"step": 1730
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.727904667328699,
|
| 1224 |
+
"grad_norm": 13.05432415008545,
|
| 1225 |
+
"learning_rate": 1.882430647291942e-06,
|
| 1226 |
+
"loss": 0.3432,
|
| 1227 |
+
"step": 1740
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.7378351539225423,
|
| 1231 |
+
"grad_norm": 6.768345832824707,
|
| 1232 |
+
"learning_rate": 1.8163804491413476e-06,
|
| 1233 |
+
"loss": 0.2487,
|
| 1234 |
+
"step": 1750
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 1.7477656405163853,
|
| 1238 |
+
"grad_norm": 7.953887939453125,
|
| 1239 |
+
"learning_rate": 1.750330250990753e-06,
|
| 1240 |
+
"loss": 0.2478,
|
| 1241 |
+
"step": 1760
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.7576961271102283,
|
| 1245 |
+
"grad_norm": 10.380583763122559,
|
| 1246 |
+
"learning_rate": 1.6842800528401588e-06,
|
| 1247 |
+
"loss": 0.2797,
|
| 1248 |
+
"step": 1770
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 1.7676266137040715,
|
| 1252 |
+
"grad_norm": 18.359220504760742,
|
| 1253 |
+
"learning_rate": 1.6182298546895641e-06,
|
| 1254 |
+
"loss": 0.3262,
|
| 1255 |
+
"step": 1780
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 1.7775571002979147,
|
| 1259 |
+
"grad_norm": 39.89724349975586,
|
| 1260 |
+
"learning_rate": 1.5521796565389696e-06,
|
| 1261 |
+
"loss": 0.2176,
|
| 1262 |
+
"step": 1790
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.7874875868917577,
|
| 1266 |
+
"grad_norm": 9.103048324584961,
|
| 1267 |
+
"learning_rate": 1.4861294583883754e-06,
|
| 1268 |
+
"loss": 0.2202,
|
| 1269 |
+
"step": 1800
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.7974180734856007,
|
| 1273 |
+
"grad_norm": 22.96454429626465,
|
| 1274 |
+
"learning_rate": 1.420079260237781e-06,
|
| 1275 |
+
"loss": 0.2874,
|
| 1276 |
+
"step": 1810
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 1.8073485600794439,
|
| 1280 |
+
"grad_norm": 16.194610595703125,
|
| 1281 |
+
"learning_rate": 1.3540290620871862e-06,
|
| 1282 |
+
"loss": 0.168,
|
| 1283 |
+
"step": 1820
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 1.817279046673287,
|
| 1287 |
+
"grad_norm": 7.695756435394287,
|
| 1288 |
+
"learning_rate": 1.287978863936592e-06,
|
| 1289 |
+
"loss": 0.2298,
|
| 1290 |
+
"step": 1830
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 1.82720953326713,
|
| 1294 |
+
"grad_norm": 13.192455291748047,
|
| 1295 |
+
"learning_rate": 1.2219286657859975e-06,
|
| 1296 |
+
"loss": 0.2309,
|
| 1297 |
+
"step": 1840
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 1.837140019860973,
|
| 1301 |
+
"grad_norm": 16.100967407226562,
|
| 1302 |
+
"learning_rate": 1.155878467635403e-06,
|
| 1303 |
+
"loss": 0.2933,
|
| 1304 |
+
"step": 1850
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 1.8470705064548163,
|
| 1308 |
+
"grad_norm": 4.693732261657715,
|
| 1309 |
+
"learning_rate": 1.0898282694848085e-06,
|
| 1310 |
+
"loss": 0.3162,
|
| 1311 |
+
"step": 1860
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 1.8570009930486595,
|
| 1315 |
+
"grad_norm": 15.807625770568848,
|
| 1316 |
+
"learning_rate": 1.023778071334214e-06,
|
| 1317 |
+
"loss": 0.2593,
|
| 1318 |
+
"step": 1870
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 1.8669314796425025,
|
| 1322 |
+
"grad_norm": 8.402117729187012,
|
| 1323 |
+
"learning_rate": 9.577278731836198e-07,
|
| 1324 |
+
"loss": 0.2331,
|
| 1325 |
+
"step": 1880
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.8768619662363455,
|
| 1329 |
+
"grad_norm": 8.832892417907715,
|
| 1330 |
+
"learning_rate": 8.916776750330252e-07,
|
| 1331 |
+
"loss": 0.2713,
|
| 1332 |
+
"step": 1890
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 1.8867924528301887,
|
| 1336 |
+
"grad_norm": 20.126842498779297,
|
| 1337 |
+
"learning_rate": 8.256274768824307e-07,
|
| 1338 |
+
"loss": 0.3002,
|
| 1339 |
+
"step": 1900
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 1.896722939424032,
|
| 1343 |
+
"grad_norm": 7.1585845947265625,
|
| 1344 |
+
"learning_rate": 7.595772787318363e-07,
|
| 1345 |
+
"loss": 0.2557,
|
| 1346 |
+
"step": 1910
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 1.906653426017875,
|
| 1350 |
+
"grad_norm": 9.247796058654785,
|
| 1351 |
+
"learning_rate": 6.935270805812417e-07,
|
| 1352 |
+
"loss": 0.2147,
|
| 1353 |
+
"step": 1920
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 1.916583912611718,
|
| 1357 |
+
"grad_norm": 19.770483016967773,
|
| 1358 |
+
"learning_rate": 6.274768824306473e-07,
|
| 1359 |
+
"loss": 0.3213,
|
| 1360 |
+
"step": 1930
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 1.9265143992055611,
|
| 1364 |
+
"grad_norm": 18.85097885131836,
|
| 1365 |
+
"learning_rate": 5.614266842800529e-07,
|
| 1366 |
+
"loss": 0.3408,
|
| 1367 |
+
"step": 1940
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 1.9364448857994043,
|
| 1371 |
+
"grad_norm": 24.601226806640625,
|
| 1372 |
+
"learning_rate": 4.953764861294584e-07,
|
| 1373 |
+
"loss": 0.2798,
|
| 1374 |
+
"step": 1950
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 1.9463753723932473,
|
| 1378 |
+
"grad_norm": 13.348860740661621,
|
| 1379 |
+
"learning_rate": 4.29326287978864e-07,
|
| 1380 |
+
"loss": 0.2631,
|
| 1381 |
+
"step": 1960
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 1.9563058589870903,
|
| 1385 |
+
"grad_norm": 9.122193336486816,
|
| 1386 |
+
"learning_rate": 3.6327608982826953e-07,
|
| 1387 |
+
"loss": 0.2529,
|
| 1388 |
+
"step": 1970
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 1.9662363455809335,
|
| 1392 |
+
"grad_norm": 20.501909255981445,
|
| 1393 |
+
"learning_rate": 2.9722589167767505e-07,
|
| 1394 |
+
"loss": 0.2518,
|
| 1395 |
+
"step": 1980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 1.9761668321747765,
|
| 1399 |
+
"grad_norm": 9.407881736755371,
|
| 1400 |
+
"learning_rate": 2.311756935270806e-07,
|
| 1401 |
+
"loss": 0.2078,
|
| 1402 |
+
"step": 1990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 1.9860973187686195,
|
| 1406 |
+
"grad_norm": 22.076322555541992,
|
| 1407 |
+
"learning_rate": 1.6512549537648615e-07,
|
| 1408 |
+
"loss": 0.2104,
|
| 1409 |
+
"step": 2000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 1.9960278053624627,
|
| 1413 |
+
"grad_norm": 18.52741241455078,
|
| 1414 |
+
"learning_rate": 9.907529722589168e-08,
|
| 1415 |
+
"loss": 0.2356,
|
| 1416 |
+
"step": 2010
|
| 1417 |
+
}
|
| 1418 |
+
],
|
| 1419 |
+
"logging_steps": 10,
|
| 1420 |
+
"max_steps": 2014,
|
| 1421 |
+
"num_input_tokens_seen": 0,
|
| 1422 |
+
"num_train_epochs": 2,
|
| 1423 |
+
"save_steps": 5000,
|
| 1424 |
+
"stateful_callbacks": {
|
| 1425 |
+
"TrainerControl": {
|
| 1426 |
+
"args": {
|
| 1427 |
+
"should_epoch_stop": false,
|
| 1428 |
+
"should_evaluate": false,
|
| 1429 |
+
"should_log": false,
|
| 1430 |
+
"should_save": true,
|
| 1431 |
+
"should_training_stop": true
|
| 1432 |
+
},
|
| 1433 |
+
"attributes": {}
|
| 1434 |
+
}
|
| 1435 |
+
},
|
| 1436 |
+
"total_flos": 4.4898226126848e+16,
|
| 1437 |
+
"train_batch_size": 1,
|
| 1438 |
+
"trial_name": null,
|
| 1439 |
+
"trial_params": null
|
| 1440 |
+
}
|
checkpoint-2014/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0db019dabdb6ded328cd1c47d011d738f7f010011b573a21899db2c47422815d
|
| 3 |
+
size 5240
|
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "appvoid/arco-2.1",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"head_dim": 96,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 1536,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 4096,
|
| 15 |
+
"max_position_embeddings": 8192,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"num_attention_heads": 16,
|
| 19 |
+
"num_hidden_layers": 16,
|
| 20 |
+
"num_key_value_heads": 8,
|
| 21 |
+
"pad_token_id": 0,
|
| 22 |
+
"pretraining_tp": 1,
|
| 23 |
+
"rms_norm_eps": 1e-05,
|
| 24 |
+
"rope_scaling": null,
|
| 25 |
+
"rope_theta": 100000,
|
| 26 |
+
"sliding_window": null,
|
| 27 |
+
"tie_word_embeddings": false,
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.46.1",
|
| 30 |
+
"unsloth_version": "2024.7",
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 32000
|
| 33 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.46.1"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ef37432361d17c0088e9082800949f4279746c6d5535eaa440181b70521e27a
|
| 3 |
+
size 2054379856
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"pad_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"sep_token": {
|
| 31 |
+
"content": "</s>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"unk_token": {
|
| 38 |
+
"content": "<unk>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
}
|
| 44 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": false,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"additional_special_tokens": [],
|
| 32 |
+
"bos_token": "<s>",
|
| 33 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% if ((message['role'] == 'user') != (loop.index0 % 2 == 0)) or ((message['role'] == 'assistant') != (loop.index0 % 2 == 1)) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '<|prompt|>' + message['content'].strip() + eos_token }}{% elif message['role'] == 'assistant' %}{{ '<|answer|>' + message['content'].strip() + eos_token }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|answer|>' }}{% endif %}",
|
| 34 |
+
"clean_up_tokenization_spaces": false,
|
| 35 |
+
"cls_token": "</s>",
|
| 36 |
+
"eos_token": "</s>",
|
| 37 |
+
"legacy": false,
|
| 38 |
+
"model_max_length": 8192,
|
| 39 |
+
"pad_token": "<unk>",
|
| 40 |
+
"padding_side": "left",
|
| 41 |
+
"sep_token": "</s>",
|
| 42 |
+
"sp_model_kwargs": {},
|
| 43 |
+
"spaces_between_special_tokens": false,
|
| 44 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 45 |
+
"unk_token": "<unk>",
|
| 46 |
+
"use_default_system_prompt": false
|
| 47 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0db019dabdb6ded328cd1c47d011d738f7f010011b573a21899db2c47422815d
|
| 3 |
+
size 5240
|