Upload folder using huggingface_hub
Browse files- checkpoint-2500/config.json +17 -0
- checkpoint-2500/generation_config.json +6 -0
- checkpoint-2500/hybrid_tokenizer_mapping.json +0 -0
- checkpoint-2500/model.safetensors +3 -0
- checkpoint-2500/optimizer.pt +3 -0
- checkpoint-2500/rng_state.pth +3 -0
- checkpoint-2500/scaler.pt +3 -0
- checkpoint-2500/scheduler.pt +3 -0
- checkpoint-2500/tokenizer_config.json +9 -0
- checkpoint-2500/trainer_state.json +1784 -0
- checkpoint-2500/training_args.bin +3 -0
checkpoint-2500/config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"FastHyperNet125mForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "float32",
|
| 6 |
+
"hidden_size": 768,
|
| 7 |
+
"hyperbolic_dim": 16,
|
| 8 |
+
"initializer_range": 0.02,
|
| 9 |
+
"intermediate_size": 2048,
|
| 10 |
+
"max_position_embeddings": 512,
|
| 11 |
+
"model_type": "fasthypernet_125m_tagless",
|
| 12 |
+
"num_attention_heads": 12,
|
| 13 |
+
"num_hidden_layers": 16,
|
| 14 |
+
"transformers_version": "5.13.1",
|
| 15 |
+
"use_cache": false,
|
| 16 |
+
"vocab_size": 8192
|
| 17 |
+
}
|
checkpoint-2500/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"output_attentions": false,
|
| 4 |
+
"output_hidden_states": false,
|
| 5 |
+
"transformers_version": "5.13.1"
|
| 6 |
+
}
|
checkpoint-2500/hybrid_tokenizer_mapping.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0963bb54d3d0e728cbc6a3352876a090fb373d13c0a999145b28bb60aafcfa6c
|
| 3 |
+
size 501911880
|
checkpoint-2500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e174b369fcf3e09db5c6857f3f343c933efb584d0cf59ae9e1f3a279e7ddc751
|
| 3 |
+
size 254046859
|
checkpoint-2500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94cc9c9aff89ccdf8382d9b39cc224e32c6f2a3aa60c8df4730d57d2fe560e51
|
| 3 |
+
size 14645
|
checkpoint-2500/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f71bb97bd3df2cc759149583a03005ffac481ca030edf3c31a2858597e698de
|
| 3 |
+
size 1383
|
checkpoint-2500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8658d9a17bb6184ddfacc024f7420b0593a1330332f3fa06df8db69b8299978
|
| 3 |
+
size 1465
|
checkpoint-2500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"tokenizer_class": "HFCompatibleHybridTokenizer",
|
| 3 |
+
"vocab_size": 8192,
|
| 4 |
+
"model_max_length": 512,
|
| 5 |
+
"bos_token": "<bos>",
|
| 6 |
+
"eos_token": "<eos>",
|
| 7 |
+
"unk_token": "<unk>",
|
| 8 |
+
"pad_token": "<pad>"
|
| 9 |
+
}
|
checkpoint-2500/trainer_state.json
ADDED
|
@@ -0,0 +1,1784 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.1322314049586777,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0005289256198347108,
|
| 14 |
+
"grad_norm": 2042.0159912109375,
|
| 15 |
+
"learning_rate": 3.2e-07,
|
| 16 |
+
"loss": 8.126,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0010578512396694215,
|
| 21 |
+
"grad_norm": 132.607666015625,
|
| 22 |
+
"learning_rate": 1.12e-06,
|
| 23 |
+
"loss": 8.0108,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.0015867768595041322,
|
| 28 |
+
"grad_norm": 117.4473876953125,
|
| 29 |
+
"learning_rate": 1.92e-06,
|
| 30 |
+
"loss": 7.8388,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.002115702479338843,
|
| 35 |
+
"grad_norm": 58.00923538208008,
|
| 36 |
+
"learning_rate": 2.72e-06,
|
| 37 |
+
"loss": 7.7671,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.002644628099173554,
|
| 42 |
+
"grad_norm": 62.31724166870117,
|
| 43 |
+
"learning_rate": 3.52e-06,
|
| 44 |
+
"loss": 7.821,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.0031735537190082643,
|
| 49 |
+
"grad_norm": 99.75863647460938,
|
| 50 |
+
"learning_rate": 4.32e-06,
|
| 51 |
+
"loss": 7.6772,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.0037024793388429752,
|
| 56 |
+
"grad_norm": 337.9526672363281,
|
| 57 |
+
"learning_rate": 5.12e-06,
|
| 58 |
+
"loss": 7.8172,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.004231404958677686,
|
| 63 |
+
"grad_norm": 95.75334167480469,
|
| 64 |
+
"learning_rate": 5.920000000000001e-06,
|
| 65 |
+
"loss": 7.6801,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.004760330578512397,
|
| 70 |
+
"grad_norm": 589.1984252929688,
|
| 71 |
+
"learning_rate": 6.72e-06,
|
| 72 |
+
"loss": 7.7462,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.005289256198347108,
|
| 77 |
+
"grad_norm": 115.37745666503906,
|
| 78 |
+
"learning_rate": 7.520000000000001e-06,
|
| 79 |
+
"loss": 7.5665,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.005818181818181818,
|
| 84 |
+
"grad_norm": 104.31098937988281,
|
| 85 |
+
"learning_rate": 8.32e-06,
|
| 86 |
+
"loss": 7.6031,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.006347107438016529,
|
| 91 |
+
"grad_norm": 357.35272216796875,
|
| 92 |
+
"learning_rate": 9.12e-06,
|
| 93 |
+
"loss": 7.6829,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.00687603305785124,
|
| 98 |
+
"grad_norm": 299.00555419921875,
|
| 99 |
+
"learning_rate": 9.92e-06,
|
| 100 |
+
"loss": 7.6717,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.0074049586776859504,
|
| 105 |
+
"grad_norm": 593.5489501953125,
|
| 106 |
+
"learning_rate": 1.072e-05,
|
| 107 |
+
"loss": 7.6622,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.007933884297520661,
|
| 112 |
+
"grad_norm": 174.9026336669922,
|
| 113 |
+
"learning_rate": 1.152e-05,
|
| 114 |
+
"loss": 7.595,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.008462809917355372,
|
| 119 |
+
"grad_norm": 199.49935913085938,
|
| 120 |
+
"learning_rate": 1.232e-05,
|
| 121 |
+
"loss": 7.5791,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.008991735537190083,
|
| 126 |
+
"grad_norm": 557.2059936523438,
|
| 127 |
+
"learning_rate": 1.3120000000000001e-05,
|
| 128 |
+
"loss": 7.7285,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.009520661157024794,
|
| 133 |
+
"grad_norm": 333.83441162109375,
|
| 134 |
+
"learning_rate": 1.3919999999999999e-05,
|
| 135 |
+
"loss": 7.6101,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.010049586776859505,
|
| 140 |
+
"grad_norm": 213.27163696289062,
|
| 141 |
+
"learning_rate": 1.472e-05,
|
| 142 |
+
"loss": 7.6139,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.010578512396694216,
|
| 147 |
+
"grad_norm": 192.46920776367188,
|
| 148 |
+
"learning_rate": 1.552e-05,
|
| 149 |
+
"loss": 7.4358,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.011107438016528925,
|
| 154 |
+
"grad_norm": 369.1148986816406,
|
| 155 |
+
"learning_rate": 1.6320000000000003e-05,
|
| 156 |
+
"loss": 7.4565,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.011636363636363636,
|
| 161 |
+
"grad_norm": 244.7185821533203,
|
| 162 |
+
"learning_rate": 1.712e-05,
|
| 163 |
+
"loss": 7.3962,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.012165289256198347,
|
| 168 |
+
"grad_norm": 308.51544189453125,
|
| 169 |
+
"learning_rate": 1.792e-05,
|
| 170 |
+
"loss": 7.4273,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.012694214876033057,
|
| 175 |
+
"grad_norm": 208.3214569091797,
|
| 176 |
+
"learning_rate": 1.872e-05,
|
| 177 |
+
"loss": 7.3567,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.013223140495867768,
|
| 182 |
+
"grad_norm": 121.53463745117188,
|
| 183 |
+
"learning_rate": 1.9520000000000003e-05,
|
| 184 |
+
"loss": 7.4131,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.01375206611570248,
|
| 189 |
+
"grad_norm": 124.09678649902344,
|
| 190 |
+
"learning_rate": 2.032e-05,
|
| 191 |
+
"loss": 7.426,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.01428099173553719,
|
| 196 |
+
"grad_norm": 237.53346252441406,
|
| 197 |
+
"learning_rate": 2.112e-05,
|
| 198 |
+
"loss": 7.377,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.014809917355371901,
|
| 203 |
+
"grad_norm": 174.61985778808594,
|
| 204 |
+
"learning_rate": 2.192e-05,
|
| 205 |
+
"loss": 7.3773,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.015338842975206612,
|
| 210 |
+
"grad_norm": 86.74190521240234,
|
| 211 |
+
"learning_rate": 2.2720000000000003e-05,
|
| 212 |
+
"loss": 7.3686,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.015867768595041323,
|
| 217 |
+
"grad_norm": 123.0051498413086,
|
| 218 |
+
"learning_rate": 2.3520000000000002e-05,
|
| 219 |
+
"loss": 7.363,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.016396694214876033,
|
| 224 |
+
"grad_norm": 149.46461486816406,
|
| 225 |
+
"learning_rate": 2.432e-05,
|
| 226 |
+
"loss": 7.3321,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.016925619834710744,
|
| 231 |
+
"grad_norm": 129.9262237548828,
|
| 232 |
+
"learning_rate": 2.512e-05,
|
| 233 |
+
"loss": 7.3589,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.017454545454545455,
|
| 238 |
+
"grad_norm": 287.2998962402344,
|
| 239 |
+
"learning_rate": 2.592e-05,
|
| 240 |
+
"loss": 7.3022,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.017983471074380166,
|
| 245 |
+
"grad_norm": 149.36317443847656,
|
| 246 |
+
"learning_rate": 2.672e-05,
|
| 247 |
+
"loss": 7.1559,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.018512396694214877,
|
| 252 |
+
"grad_norm": 133.55393981933594,
|
| 253 |
+
"learning_rate": 2.752e-05,
|
| 254 |
+
"loss": 7.2833,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.019041322314049588,
|
| 259 |
+
"grad_norm": 111.75740814208984,
|
| 260 |
+
"learning_rate": 2.8320000000000003e-05,
|
| 261 |
+
"loss": 7.0669,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.0195702479338843,
|
| 266 |
+
"grad_norm": 108.92760467529297,
|
| 267 |
+
"learning_rate": 2.9120000000000002e-05,
|
| 268 |
+
"loss": 7.2586,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.02009917355371901,
|
| 273 |
+
"grad_norm": 160.08486938476562,
|
| 274 |
+
"learning_rate": 2.9920000000000005e-05,
|
| 275 |
+
"loss": 7.2912,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.02062809917355372,
|
| 280 |
+
"grad_norm": 115.86800384521484,
|
| 281 |
+
"learning_rate": 3.072e-05,
|
| 282 |
+
"loss": 7.1553,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.02115702479338843,
|
| 287 |
+
"grad_norm": 131.96246337890625,
|
| 288 |
+
"learning_rate": 3.1519999999999996e-05,
|
| 289 |
+
"loss": 7.0865,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.021685950413223142,
|
| 294 |
+
"grad_norm": 175.23385620117188,
|
| 295 |
+
"learning_rate": 3.232e-05,
|
| 296 |
+
"loss": 7.1718,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.02221487603305785,
|
| 301 |
+
"grad_norm": 130.51516723632812,
|
| 302 |
+
"learning_rate": 3.312e-05,
|
| 303 |
+
"loss": 7.1449,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.02274380165289256,
|
| 308 |
+
"grad_norm": 142.1250762939453,
|
| 309 |
+
"learning_rate": 3.392e-05,
|
| 310 |
+
"loss": 7.0811,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.02327272727272727,
|
| 315 |
+
"grad_norm": 93.60326385498047,
|
| 316 |
+
"learning_rate": 3.472e-05,
|
| 317 |
+
"loss": 7.0511,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.023801652892561982,
|
| 322 |
+
"grad_norm": 85.3148193359375,
|
| 323 |
+
"learning_rate": 3.5520000000000006e-05,
|
| 324 |
+
"loss": 7.057,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.024330578512396693,
|
| 329 |
+
"grad_norm": 77.96083068847656,
|
| 330 |
+
"learning_rate": 3.6320000000000005e-05,
|
| 331 |
+
"loss": 7.0768,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.024859504132231404,
|
| 336 |
+
"grad_norm": 64.50347900390625,
|
| 337 |
+
"learning_rate": 3.712e-05,
|
| 338 |
+
"loss": 7.0468,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.025388429752066115,
|
| 343 |
+
"grad_norm": 89.8930892944336,
|
| 344 |
+
"learning_rate": 3.792e-05,
|
| 345 |
+
"loss": 6.9279,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.025917355371900826,
|
| 350 |
+
"grad_norm": 103.4708251953125,
|
| 351 |
+
"learning_rate": 3.872e-05,
|
| 352 |
+
"loss": 6.8665,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.026446280991735537,
|
| 357 |
+
"grad_norm": 96.82048034667969,
|
| 358 |
+
"learning_rate": 3.952e-05,
|
| 359 |
+
"loss": 6.9254,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.026975206611570247,
|
| 364 |
+
"grad_norm": 127.65508270263672,
|
| 365 |
+
"learning_rate": 4.032e-05,
|
| 366 |
+
"loss": 6.9533,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.02750413223140496,
|
| 371 |
+
"grad_norm": 123.8250503540039,
|
| 372 |
+
"learning_rate": 4.1120000000000006e-05,
|
| 373 |
+
"loss": 6.8762,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.02803305785123967,
|
| 378 |
+
"grad_norm": 80.71707153320312,
|
| 379 |
+
"learning_rate": 4.1920000000000005e-05,
|
| 380 |
+
"loss": 6.9264,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.02856198347107438,
|
| 385 |
+
"grad_norm": 76.69340515136719,
|
| 386 |
+
"learning_rate": 4.2720000000000004e-05,
|
| 387 |
+
"loss": 6.8932,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.02909090909090909,
|
| 392 |
+
"grad_norm": 64.87788391113281,
|
| 393 |
+
"learning_rate": 4.352e-05,
|
| 394 |
+
"loss": 6.8852,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.029619834710743802,
|
| 399 |
+
"grad_norm": 55.4420280456543,
|
| 400 |
+
"learning_rate": 4.432e-05,
|
| 401 |
+
"loss": 6.8624,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.030148760330578513,
|
| 406 |
+
"grad_norm": 83.48722076416016,
|
| 407 |
+
"learning_rate": 4.512e-05,
|
| 408 |
+
"loss": 6.791,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.030677685950413223,
|
| 413 |
+
"grad_norm": 67.83543395996094,
|
| 414 |
+
"learning_rate": 4.592e-05,
|
| 415 |
+
"loss": 6.78,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.031206611570247934,
|
| 420 |
+
"grad_norm": 75.6465072631836,
|
| 421 |
+
"learning_rate": 4.672e-05,
|
| 422 |
+
"loss": 6.7436,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.031735537190082645,
|
| 427 |
+
"grad_norm": 57.24126434326172,
|
| 428 |
+
"learning_rate": 4.7520000000000006e-05,
|
| 429 |
+
"loss": 6.6183,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.032264462809917356,
|
| 434 |
+
"grad_norm": 53.670318603515625,
|
| 435 |
+
"learning_rate": 4.8320000000000005e-05,
|
| 436 |
+
"loss": 6.7423,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.03279338842975207,
|
| 441 |
+
"grad_norm": 90.657958984375,
|
| 442 |
+
"learning_rate": 4.9120000000000004e-05,
|
| 443 |
+
"loss": 6.796,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.03332231404958678,
|
| 448 |
+
"grad_norm": 59.86640167236328,
|
| 449 |
+
"learning_rate": 4.992e-05,
|
| 450 |
+
"loss": 6.6875,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.03385123966942149,
|
| 455 |
+
"grad_norm": 82.00715637207031,
|
| 456 |
+
"learning_rate": 5.072e-05,
|
| 457 |
+
"loss": 6.8297,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.0343801652892562,
|
| 462 |
+
"grad_norm": 77.67565155029297,
|
| 463 |
+
"learning_rate": 5.152e-05,
|
| 464 |
+
"loss": 6.6996,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.03490909090909091,
|
| 469 |
+
"grad_norm": 76.80774688720703,
|
| 470 |
+
"learning_rate": 5.232e-05,
|
| 471 |
+
"loss": 6.6164,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.03543801652892562,
|
| 476 |
+
"grad_norm": 90.92999267578125,
|
| 477 |
+
"learning_rate": 5.3120000000000006e-05,
|
| 478 |
+
"loss": 6.6109,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.03596694214876033,
|
| 483 |
+
"grad_norm": 60.101036071777344,
|
| 484 |
+
"learning_rate": 5.3920000000000006e-05,
|
| 485 |
+
"loss": 6.6207,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.03649586776859504,
|
| 490 |
+
"grad_norm": 71.14286804199219,
|
| 491 |
+
"learning_rate": 5.4720000000000005e-05,
|
| 492 |
+
"loss": 6.6988,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.037024793388429754,
|
| 497 |
+
"grad_norm": 79.58287048339844,
|
| 498 |
+
"learning_rate": 5.5520000000000004e-05,
|
| 499 |
+
"loss": 6.6793,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.037553719008264465,
|
| 504 |
+
"grad_norm": 57.14976119995117,
|
| 505 |
+
"learning_rate": 5.632e-05,
|
| 506 |
+
"loss": 6.5679,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.038082644628099176,
|
| 511 |
+
"grad_norm": 48.05242919921875,
|
| 512 |
+
"learning_rate": 5.712000000000001e-05,
|
| 513 |
+
"loss": 6.6146,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.03861157024793389,
|
| 518 |
+
"grad_norm": 44.47470474243164,
|
| 519 |
+
"learning_rate": 5.792000000000001e-05,
|
| 520 |
+
"loss": 6.5374,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.0391404958677686,
|
| 525 |
+
"grad_norm": 51.66844177246094,
|
| 526 |
+
"learning_rate": 5.872000000000001e-05,
|
| 527 |
+
"loss": 6.4478,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.03966942148760331,
|
| 532 |
+
"grad_norm": 54.69235610961914,
|
| 533 |
+
"learning_rate": 5.952e-05,
|
| 534 |
+
"loss": 6.4556,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.04019834710743802,
|
| 539 |
+
"grad_norm": 62.92082214355469,
|
| 540 |
+
"learning_rate": 6.032e-05,
|
| 541 |
+
"loss": 6.494,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.04072727272727273,
|
| 546 |
+
"grad_norm": 59.18268585205078,
|
| 547 |
+
"learning_rate": 6.112e-05,
|
| 548 |
+
"loss": 6.4632,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.04125619834710744,
|
| 553 |
+
"grad_norm": 43.41447448730469,
|
| 554 |
+
"learning_rate": 6.192e-05,
|
| 555 |
+
"loss": 6.4568,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.04178512396694215,
|
| 560 |
+
"grad_norm": 68.496337890625,
|
| 561 |
+
"learning_rate": 6.272e-05,
|
| 562 |
+
"loss": 6.3378,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.04231404958677686,
|
| 567 |
+
"grad_norm": 55.83193588256836,
|
| 568 |
+
"learning_rate": 6.352e-05,
|
| 569 |
+
"loss": 6.5272,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.042842975206611573,
|
| 574 |
+
"grad_norm": 52.77011489868164,
|
| 575 |
+
"learning_rate": 6.432000000000001e-05,
|
| 576 |
+
"loss": 6.3882,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.043371900826446284,
|
| 581 |
+
"grad_norm": 47.83772659301758,
|
| 582 |
+
"learning_rate": 6.512e-05,
|
| 583 |
+
"loss": 6.3745,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.04390082644628099,
|
| 588 |
+
"grad_norm": 64.70166015625,
|
| 589 |
+
"learning_rate": 6.592e-05,
|
| 590 |
+
"loss": 6.3783,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.0444297520661157,
|
| 595 |
+
"grad_norm": 69.14620208740234,
|
| 596 |
+
"learning_rate": 6.672e-05,
|
| 597 |
+
"loss": 6.403,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.04495867768595041,
|
| 602 |
+
"grad_norm": 41.3566780090332,
|
| 603 |
+
"learning_rate": 6.752e-05,
|
| 604 |
+
"loss": 6.273,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.04548760330578512,
|
| 609 |
+
"grad_norm": 57.124813079833984,
|
| 610 |
+
"learning_rate": 6.832000000000001e-05,
|
| 611 |
+
"loss": 6.3434,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.04601652892561983,
|
| 616 |
+
"grad_norm": 47.598854064941406,
|
| 617 |
+
"learning_rate": 6.912e-05,
|
| 618 |
+
"loss": 6.2613,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.04654545454545454,
|
| 623 |
+
"grad_norm": 63.111759185791016,
|
| 624 |
+
"learning_rate": 6.992000000000001e-05,
|
| 625 |
+
"loss": 6.2488,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.047074380165289254,
|
| 630 |
+
"grad_norm": 53.83757781982422,
|
| 631 |
+
"learning_rate": 7.072000000000001e-05,
|
| 632 |
+
"loss": 6.1787,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.047603305785123964,
|
| 637 |
+
"grad_norm": 42.92972946166992,
|
| 638 |
+
"learning_rate": 7.151999999999999e-05,
|
| 639 |
+
"loss": 6.2455,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.048132231404958675,
|
| 644 |
+
"grad_norm": 40.897098541259766,
|
| 645 |
+
"learning_rate": 7.232e-05,
|
| 646 |
+
"loss": 6.1776,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.048661157024793386,
|
| 651 |
+
"grad_norm": 67.57796478271484,
|
| 652 |
+
"learning_rate": 7.312e-05,
|
| 653 |
+
"loss": 6.0933,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.0491900826446281,
|
| 658 |
+
"grad_norm": 54.34871292114258,
|
| 659 |
+
"learning_rate": 7.392e-05,
|
| 660 |
+
"loss": 6.1669,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.04971900826446281,
|
| 665 |
+
"grad_norm": 46.664188385009766,
|
| 666 |
+
"learning_rate": 7.472e-05,
|
| 667 |
+
"loss": 6.0994,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.05024793388429752,
|
| 672 |
+
"grad_norm": 40.62440490722656,
|
| 673 |
+
"learning_rate": 7.552e-05,
|
| 674 |
+
"loss": 6.1375,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.05077685950413223,
|
| 679 |
+
"grad_norm": 40.99917221069336,
|
| 680 |
+
"learning_rate": 7.632e-05,
|
| 681 |
+
"loss": 6.0468,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.05130578512396694,
|
| 686 |
+
"grad_norm": 41.27398681640625,
|
| 687 |
+
"learning_rate": 7.712000000000001e-05,
|
| 688 |
+
"loss": 6.0949,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.05183471074380165,
|
| 693 |
+
"grad_norm": 40.87042236328125,
|
| 694 |
+
"learning_rate": 7.792e-05,
|
| 695 |
+
"loss": 6.0498,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.05236363636363636,
|
| 700 |
+
"grad_norm": 41.66493606567383,
|
| 701 |
+
"learning_rate": 7.872e-05,
|
| 702 |
+
"loss": 6.0707,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.05289256198347107,
|
| 707 |
+
"grad_norm": 36.58250427246094,
|
| 708 |
+
"learning_rate": 7.952000000000001e-05,
|
| 709 |
+
"loss": 6.0559,
|
| 710 |
+
"step": 1000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.053421487603305784,
|
| 714 |
+
"grad_norm": 34.69593048095703,
|
| 715 |
+
"learning_rate": 8.032e-05,
|
| 716 |
+
"loss": 6.0294,
|
| 717 |
+
"step": 1010
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.053950413223140495,
|
| 721 |
+
"grad_norm": 36.51956558227539,
|
| 722 |
+
"learning_rate": 8.112000000000001e-05,
|
| 723 |
+
"loss": 6.008,
|
| 724 |
+
"step": 1020
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.054479338842975206,
|
| 728 |
+
"grad_norm": 38.489219665527344,
|
| 729 |
+
"learning_rate": 8.192e-05,
|
| 730 |
+
"loss": 5.9906,
|
| 731 |
+
"step": 1030
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.05500826446280992,
|
| 735 |
+
"grad_norm": 35.57550048828125,
|
| 736 |
+
"learning_rate": 8.272000000000001e-05,
|
| 737 |
+
"loss": 5.9222,
|
| 738 |
+
"step": 1040
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.05553719008264463,
|
| 742 |
+
"grad_norm": 36.05617904663086,
|
| 743 |
+
"learning_rate": 8.352000000000001e-05,
|
| 744 |
+
"loss": 6.0426,
|
| 745 |
+
"step": 1050
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.05606611570247934,
|
| 749 |
+
"grad_norm": 31.7716121673584,
|
| 750 |
+
"learning_rate": 8.431999999999999e-05,
|
| 751 |
+
"loss": 5.9889,
|
| 752 |
+
"step": 1060
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.05659504132231405,
|
| 756 |
+
"grad_norm": 34.74286651611328,
|
| 757 |
+
"learning_rate": 8.512e-05,
|
| 758 |
+
"loss": 5.8873,
|
| 759 |
+
"step": 1070
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.05712396694214876,
|
| 763 |
+
"grad_norm": 45.21353530883789,
|
| 764 |
+
"learning_rate": 8.592e-05,
|
| 765 |
+
"loss": 5.9505,
|
| 766 |
+
"step": 1080
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.05765289256198347,
|
| 770 |
+
"grad_norm": 30.405447006225586,
|
| 771 |
+
"learning_rate": 8.672e-05,
|
| 772 |
+
"loss": 5.8087,
|
| 773 |
+
"step": 1090
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.05818181818181818,
|
| 777 |
+
"grad_norm": 30.943218231201172,
|
| 778 |
+
"learning_rate": 8.752e-05,
|
| 779 |
+
"loss": 5.7337,
|
| 780 |
+
"step": 1100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.05871074380165289,
|
| 784 |
+
"grad_norm": 32.396610260009766,
|
| 785 |
+
"learning_rate": 8.832000000000001e-05,
|
| 786 |
+
"loss": 5.7989,
|
| 787 |
+
"step": 1110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.059239669421487604,
|
| 791 |
+
"grad_norm": 31.198833465576172,
|
| 792 |
+
"learning_rate": 8.912e-05,
|
| 793 |
+
"loss": 5.8181,
|
| 794 |
+
"step": 1120
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.059768595041322314,
|
| 798 |
+
"grad_norm": 40.59803009033203,
|
| 799 |
+
"learning_rate": 8.992e-05,
|
| 800 |
+
"loss": 5.8761,
|
| 801 |
+
"step": 1130
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.060297520661157025,
|
| 805 |
+
"grad_norm": 43.126766204833984,
|
| 806 |
+
"learning_rate": 9.072e-05,
|
| 807 |
+
"loss": 5.8239,
|
| 808 |
+
"step": 1140
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.060826446280991736,
|
| 812 |
+
"grad_norm": 39.69029998779297,
|
| 813 |
+
"learning_rate": 9.152e-05,
|
| 814 |
+
"loss": 5.7444,
|
| 815 |
+
"step": 1150
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.06135537190082645,
|
| 819 |
+
"grad_norm": 28.941499710083008,
|
| 820 |
+
"learning_rate": 9.232000000000001e-05,
|
| 821 |
+
"loss": 5.8256,
|
| 822 |
+
"step": 1160
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.06188429752066116,
|
| 826 |
+
"grad_norm": 46.216552734375,
|
| 827 |
+
"learning_rate": 9.312e-05,
|
| 828 |
+
"loss": 5.8361,
|
| 829 |
+
"step": 1170
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.06241322314049587,
|
| 833 |
+
"grad_norm": 42.1989860534668,
|
| 834 |
+
"learning_rate": 9.392000000000001e-05,
|
| 835 |
+
"loss": 5.7034,
|
| 836 |
+
"step": 1180
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.06294214876033058,
|
| 840 |
+
"grad_norm": 36.610836029052734,
|
| 841 |
+
"learning_rate": 9.472000000000001e-05,
|
| 842 |
+
"loss": 5.7089,
|
| 843 |
+
"step": 1190
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.06347107438016529,
|
| 847 |
+
"grad_norm": 38.280452728271484,
|
| 848 |
+
"learning_rate": 9.552000000000001e-05,
|
| 849 |
+
"loss": 5.8296,
|
| 850 |
+
"step": 1200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.064,
|
| 854 |
+
"grad_norm": 42.162864685058594,
|
| 855 |
+
"learning_rate": 9.632e-05,
|
| 856 |
+
"loss": 5.833,
|
| 857 |
+
"step": 1210
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.06452892561983471,
|
| 861 |
+
"grad_norm": 58.0146369934082,
|
| 862 |
+
"learning_rate": 9.712e-05,
|
| 863 |
+
"loss": 5.6257,
|
| 864 |
+
"step": 1220
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.06505785123966942,
|
| 868 |
+
"grad_norm": 72.400634765625,
|
| 869 |
+
"learning_rate": 9.792e-05,
|
| 870 |
+
"loss": 5.6169,
|
| 871 |
+
"step": 1230
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.06558677685950413,
|
| 875 |
+
"grad_norm": 41.95994186401367,
|
| 876 |
+
"learning_rate": 9.872e-05,
|
| 877 |
+
"loss": 5.6194,
|
| 878 |
+
"step": 1240
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.06611570247933884,
|
| 882 |
+
"grad_norm": 38.22507858276367,
|
| 883 |
+
"learning_rate": 9.952e-05,
|
| 884 |
+
"loss": 5.5854,
|
| 885 |
+
"step": 1250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.06664462809917356,
|
| 889 |
+
"grad_norm": 36.9998664855957,
|
| 890 |
+
"learning_rate": 0.00010032000000000002,
|
| 891 |
+
"loss": 5.5598,
|
| 892 |
+
"step": 1260
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.06717355371900827,
|
| 896 |
+
"grad_norm": 30.84783363342285,
|
| 897 |
+
"learning_rate": 0.00010112000000000002,
|
| 898 |
+
"loss": 5.4868,
|
| 899 |
+
"step": 1270
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.06770247933884298,
|
| 903 |
+
"grad_norm": 35.899383544921875,
|
| 904 |
+
"learning_rate": 0.00010192000000000001,
|
| 905 |
+
"loss": 5.4559,
|
| 906 |
+
"step": 1280
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.06823140495867769,
|
| 910 |
+
"grad_norm": 32.75505828857422,
|
| 911 |
+
"learning_rate": 0.00010271999999999999,
|
| 912 |
+
"loss": 5.6184,
|
| 913 |
+
"step": 1290
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.0687603305785124,
|
| 917 |
+
"grad_norm": 40.69361877441406,
|
| 918 |
+
"learning_rate": 0.00010352,
|
| 919 |
+
"loss": 5.5495,
|
| 920 |
+
"step": 1300
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.06928925619834711,
|
| 924 |
+
"grad_norm": 43.96121597290039,
|
| 925 |
+
"learning_rate": 0.00010431999999999999,
|
| 926 |
+
"loss": 5.585,
|
| 927 |
+
"step": 1310
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.06981818181818182,
|
| 931 |
+
"grad_norm": 34.5072021484375,
|
| 932 |
+
"learning_rate": 0.00010512,
|
| 933 |
+
"loss": 5.518,
|
| 934 |
+
"step": 1320
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.07034710743801653,
|
| 938 |
+
"grad_norm": 46.74812698364258,
|
| 939 |
+
"learning_rate": 0.00010592,
|
| 940 |
+
"loss": 5.4283,
|
| 941 |
+
"step": 1330
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.07087603305785124,
|
| 945 |
+
"grad_norm": 48.960025787353516,
|
| 946 |
+
"learning_rate": 0.00010672,
|
| 947 |
+
"loss": 5.4234,
|
| 948 |
+
"step": 1340
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.07140495867768595,
|
| 952 |
+
"grad_norm": 47.75209045410156,
|
| 953 |
+
"learning_rate": 0.00010752,
|
| 954 |
+
"loss": 5.4553,
|
| 955 |
+
"step": 1350
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.07193388429752066,
|
| 959 |
+
"grad_norm": 43.6797981262207,
|
| 960 |
+
"learning_rate": 0.00010831999999999999,
|
| 961 |
+
"loss": 5.3252,
|
| 962 |
+
"step": 1360
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.07246280991735538,
|
| 966 |
+
"grad_norm": 48.113887786865234,
|
| 967 |
+
"learning_rate": 0.00010912,
|
| 968 |
+
"loss": 5.4867,
|
| 969 |
+
"step": 1370
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.07299173553719009,
|
| 973 |
+
"grad_norm": 42.719642639160156,
|
| 974 |
+
"learning_rate": 0.00010992,
|
| 975 |
+
"loss": 5.3672,
|
| 976 |
+
"step": 1380
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.0735206611570248,
|
| 980 |
+
"grad_norm": 51.8200798034668,
|
| 981 |
+
"learning_rate": 0.00011072,
|
| 982 |
+
"loss": 5.2117,
|
| 983 |
+
"step": 1390
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.07404958677685951,
|
| 987 |
+
"grad_norm": 72.69532012939453,
|
| 988 |
+
"learning_rate": 0.00011152,
|
| 989 |
+
"loss": 5.3722,
|
| 990 |
+
"step": 1400
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.07457851239669422,
|
| 994 |
+
"grad_norm": 56.0296745300293,
|
| 995 |
+
"learning_rate": 0.00011232000000000001,
|
| 996 |
+
"loss": 5.2986,
|
| 997 |
+
"step": 1410
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.07510743801652893,
|
| 1001 |
+
"grad_norm": 48.64356994628906,
|
| 1002 |
+
"learning_rate": 0.00011312,
|
| 1003 |
+
"loss": 5.3451,
|
| 1004 |
+
"step": 1420
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.07563636363636364,
|
| 1008 |
+
"grad_norm": 62.179046630859375,
|
| 1009 |
+
"learning_rate": 0.00011392000000000001,
|
| 1010 |
+
"loss": 5.3301,
|
| 1011 |
+
"step": 1430
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.07616528925619835,
|
| 1015 |
+
"grad_norm": 95.21004486083984,
|
| 1016 |
+
"learning_rate": 0.00011472,
|
| 1017 |
+
"loss": 5.2516,
|
| 1018 |
+
"step": 1440
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.07669421487603306,
|
| 1022 |
+
"grad_norm": 76.14125061035156,
|
| 1023 |
+
"learning_rate": 0.00011552,
|
| 1024 |
+
"loss": 5.1788,
|
| 1025 |
+
"step": 1450
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.07722314049586777,
|
| 1029 |
+
"grad_norm": 79.47603607177734,
|
| 1030 |
+
"learning_rate": 0.00011632000000000001,
|
| 1031 |
+
"loss": 5.2876,
|
| 1032 |
+
"step": 1460
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.07775206611570248,
|
| 1036 |
+
"grad_norm": 101.11727142333984,
|
| 1037 |
+
"learning_rate": 0.00011712,
|
| 1038 |
+
"loss": 5.1364,
|
| 1039 |
+
"step": 1470
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.0782809917355372,
|
| 1043 |
+
"grad_norm": 82.6675796508789,
|
| 1044 |
+
"learning_rate": 0.00011792000000000001,
|
| 1045 |
+
"loss": 5.2109,
|
| 1046 |
+
"step": 1480
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.0788099173553719,
|
| 1050 |
+
"grad_norm": 82.03048706054688,
|
| 1051 |
+
"learning_rate": 0.00011872000000000002,
|
| 1052 |
+
"loss": 5.2076,
|
| 1053 |
+
"step": 1490
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.07933884297520662,
|
| 1057 |
+
"grad_norm": 56.5334358215332,
|
| 1058 |
+
"learning_rate": 0.00011952000000000001,
|
| 1059 |
+
"loss": 5.2379,
|
| 1060 |
+
"step": 1500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.07986776859504133,
|
| 1064 |
+
"grad_norm": 77.19476318359375,
|
| 1065 |
+
"learning_rate": 0.00012032000000000001,
|
| 1066 |
+
"loss": 5.2414,
|
| 1067 |
+
"step": 1510
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.08039669421487604,
|
| 1071 |
+
"grad_norm": 76.6305160522461,
|
| 1072 |
+
"learning_rate": 0.00012112,
|
| 1073 |
+
"loss": 5.1135,
|
| 1074 |
+
"step": 1520
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.08092561983471075,
|
| 1078 |
+
"grad_norm": 183.71173095703125,
|
| 1079 |
+
"learning_rate": 0.00012192000000000001,
|
| 1080 |
+
"loss": 5.1305,
|
| 1081 |
+
"step": 1530
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.08145454545454546,
|
| 1085 |
+
"grad_norm": 103.42782592773438,
|
| 1086 |
+
"learning_rate": 0.00012272000000000002,
|
| 1087 |
+
"loss": 5.0707,
|
| 1088 |
+
"step": 1540
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.08198347107438017,
|
| 1092 |
+
"grad_norm": 89.39161682128906,
|
| 1093 |
+
"learning_rate": 0.00012352,
|
| 1094 |
+
"loss": 5.0448,
|
| 1095 |
+
"step": 1550
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.08251239669421488,
|
| 1099 |
+
"grad_norm": 128.94386291503906,
|
| 1100 |
+
"learning_rate": 0.00012432,
|
| 1101 |
+
"loss": 5.0627,
|
| 1102 |
+
"step": 1560
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.08304132231404959,
|
| 1106 |
+
"grad_norm": 114.81316375732422,
|
| 1107 |
+
"learning_rate": 0.00012512000000000002,
|
| 1108 |
+
"loss": 5.0173,
|
| 1109 |
+
"step": 1570
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.0835702479338843,
|
| 1113 |
+
"grad_norm": 85.47364807128906,
|
| 1114 |
+
"learning_rate": 0.00012592000000000001,
|
| 1115 |
+
"loss": 5.0522,
|
| 1116 |
+
"step": 1580
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.08409917355371901,
|
| 1120 |
+
"grad_norm": 97.26194763183594,
|
| 1121 |
+
"learning_rate": 0.00012672,
|
| 1122 |
+
"loss": 5.0868,
|
| 1123 |
+
"step": 1590
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.08462809917355373,
|
| 1127 |
+
"grad_norm": 186.6729278564453,
|
| 1128 |
+
"learning_rate": 0.00012752,
|
| 1129 |
+
"loss": 5.0442,
|
| 1130 |
+
"step": 1600
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.08515702479338844,
|
| 1134 |
+
"grad_norm": 79.75817108154297,
|
| 1135 |
+
"learning_rate": 0.00012832,
|
| 1136 |
+
"loss": 4.9309,
|
| 1137 |
+
"step": 1610
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.08568595041322315,
|
| 1141 |
+
"grad_norm": 98.72312927246094,
|
| 1142 |
+
"learning_rate": 0.00012911999999999998,
|
| 1143 |
+
"loss": 4.9763,
|
| 1144 |
+
"step": 1620
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.08621487603305786,
|
| 1148 |
+
"grad_norm": 99.25630950927734,
|
| 1149 |
+
"learning_rate": 0.00012992,
|
| 1150 |
+
"loss": 5.0555,
|
| 1151 |
+
"step": 1630
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.08674380165289257,
|
| 1155 |
+
"grad_norm": 113.07233428955078,
|
| 1156 |
+
"learning_rate": 0.00013072,
|
| 1157 |
+
"loss": 4.9236,
|
| 1158 |
+
"step": 1640
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.08727272727272728,
|
| 1162 |
+
"grad_norm": 116.71514892578125,
|
| 1163 |
+
"learning_rate": 0.00013152,
|
| 1164 |
+
"loss": 4.8469,
|
| 1165 |
+
"step": 1650
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.08780165289256198,
|
| 1169 |
+
"grad_norm": 183.65267944335938,
|
| 1170 |
+
"learning_rate": 0.00013224000000000002,
|
| 1171 |
+
"loss": 4.922,
|
| 1172 |
+
"step": 1660
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.08833057851239669,
|
| 1176 |
+
"grad_norm": 134.0264892578125,
|
| 1177 |
+
"learning_rate": 0.00013304000000000001,
|
| 1178 |
+
"loss": 4.8469,
|
| 1179 |
+
"step": 1670
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.0888595041322314,
|
| 1183 |
+
"grad_norm": 114.74702453613281,
|
| 1184 |
+
"learning_rate": 0.00013384,
|
| 1185 |
+
"loss": 4.891,
|
| 1186 |
+
"step": 1680
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.08938842975206611,
|
| 1190 |
+
"grad_norm": 124.9133529663086,
|
| 1191 |
+
"learning_rate": 0.00013464,
|
| 1192 |
+
"loss": 4.7879,
|
| 1193 |
+
"step": 1690
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.08991735537190082,
|
| 1197 |
+
"grad_norm": 141.5299530029297,
|
| 1198 |
+
"learning_rate": 0.00013544000000000002,
|
| 1199 |
+
"loss": 4.7898,
|
| 1200 |
+
"step": 1700
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.09044628099173553,
|
| 1204 |
+
"grad_norm": 93.27886962890625,
|
| 1205 |
+
"learning_rate": 0.00013624,
|
| 1206 |
+
"loss": 4.8604,
|
| 1207 |
+
"step": 1710
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.09097520661157024,
|
| 1211 |
+
"grad_norm": 194.52664184570312,
|
| 1212 |
+
"learning_rate": 0.00013704,
|
| 1213 |
+
"loss": 4.7352,
|
| 1214 |
+
"step": 1720
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.09150413223140495,
|
| 1218 |
+
"grad_norm": 118.92210388183594,
|
| 1219 |
+
"learning_rate": 0.00013784000000000002,
|
| 1220 |
+
"loss": 4.7951,
|
| 1221 |
+
"step": 1730
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.09203305785123966,
|
| 1225 |
+
"grad_norm": 167.02508544921875,
|
| 1226 |
+
"learning_rate": 0.00013864000000000001,
|
| 1227 |
+
"loss": 4.7964,
|
| 1228 |
+
"step": 1740
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.09256198347107437,
|
| 1232 |
+
"grad_norm": 105.10356903076172,
|
| 1233 |
+
"learning_rate": 0.00013944,
|
| 1234 |
+
"loss": 4.7212,
|
| 1235 |
+
"step": 1750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.09309090909090909,
|
| 1239 |
+
"grad_norm": 91.76654052734375,
|
| 1240 |
+
"learning_rate": 0.00014024000000000003,
|
| 1241 |
+
"loss": 4.7349,
|
| 1242 |
+
"step": 1760
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.0936198347107438,
|
| 1246 |
+
"grad_norm": 102.53783416748047,
|
| 1247 |
+
"learning_rate": 0.00014104000000000002,
|
| 1248 |
+
"loss": 4.6718,
|
| 1249 |
+
"step": 1770
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.09414876033057851,
|
| 1253 |
+
"grad_norm": 129.4251251220703,
|
| 1254 |
+
"learning_rate": 0.00014184,
|
| 1255 |
+
"loss": 4.7727,
|
| 1256 |
+
"step": 1780
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.09467768595041322,
|
| 1260 |
+
"grad_norm": 243.75103759765625,
|
| 1261 |
+
"learning_rate": 0.00014264,
|
| 1262 |
+
"loss": 4.6279,
|
| 1263 |
+
"step": 1790
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.09520661157024793,
|
| 1267 |
+
"grad_norm": 119.21356964111328,
|
| 1268 |
+
"learning_rate": 0.00014344,
|
| 1269 |
+
"loss": 4.6609,
|
| 1270 |
+
"step": 1800
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.09573553719008264,
|
| 1274 |
+
"grad_norm": 178.49330139160156,
|
| 1275 |
+
"learning_rate": 0.00014424,
|
| 1276 |
+
"loss": 4.642,
|
| 1277 |
+
"step": 1810
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.09626446280991735,
|
| 1281 |
+
"grad_norm": 152.4857940673828,
|
| 1282 |
+
"learning_rate": 0.00014504,
|
| 1283 |
+
"loss": 4.6757,
|
| 1284 |
+
"step": 1820
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.09679338842975206,
|
| 1288 |
+
"grad_norm": 141.40493774414062,
|
| 1289 |
+
"learning_rate": 0.00014584,
|
| 1290 |
+
"loss": 4.6543,
|
| 1291 |
+
"step": 1830
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.09732231404958677,
|
| 1295 |
+
"grad_norm": 155.3096923828125,
|
| 1296 |
+
"learning_rate": 0.00014664,
|
| 1297 |
+
"loss": 4.5327,
|
| 1298 |
+
"step": 1840
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.09785123966942148,
|
| 1302 |
+
"grad_norm": 150.15298461914062,
|
| 1303 |
+
"learning_rate": 0.00014744,
|
| 1304 |
+
"loss": 4.6052,
|
| 1305 |
+
"step": 1850
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.0983801652892562,
|
| 1309 |
+
"grad_norm": 187.1421356201172,
|
| 1310 |
+
"learning_rate": 0.00014824,
|
| 1311 |
+
"loss": 4.4834,
|
| 1312 |
+
"step": 1860
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.0989090909090909,
|
| 1316 |
+
"grad_norm": 150.79815673828125,
|
| 1317 |
+
"learning_rate": 0.00014904,
|
| 1318 |
+
"loss": 4.5097,
|
| 1319 |
+
"step": 1870
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.09943801652892562,
|
| 1323 |
+
"grad_norm": 147.16586303710938,
|
| 1324 |
+
"learning_rate": 0.00014984000000000002,
|
| 1325 |
+
"loss": 4.5149,
|
| 1326 |
+
"step": 1880
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.09996694214876033,
|
| 1330 |
+
"grad_norm": 129.7955322265625,
|
| 1331 |
+
"learning_rate": 0.00015064,
|
| 1332 |
+
"loss": 4.5588,
|
| 1333 |
+
"step": 1890
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.10049586776859504,
|
| 1337 |
+
"grad_norm": 249.13198852539062,
|
| 1338 |
+
"learning_rate": 0.00015144,
|
| 1339 |
+
"loss": 4.5071,
|
| 1340 |
+
"step": 1900
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.10102479338842975,
|
| 1344 |
+
"grad_norm": 119.97147369384766,
|
| 1345 |
+
"learning_rate": 0.00015224,
|
| 1346 |
+
"loss": 4.5246,
|
| 1347 |
+
"step": 1910
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.10155371900826446,
|
| 1351 |
+
"grad_norm": 131.48204040527344,
|
| 1352 |
+
"learning_rate": 0.00015304,
|
| 1353 |
+
"loss": 4.3402,
|
| 1354 |
+
"step": 1920
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.10208264462809917,
|
| 1358 |
+
"grad_norm": 186.90174865722656,
|
| 1359 |
+
"learning_rate": 0.00015384,
|
| 1360 |
+
"loss": 4.403,
|
| 1361 |
+
"step": 1930
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.10261157024793388,
|
| 1365 |
+
"grad_norm": 146.8113250732422,
|
| 1366 |
+
"learning_rate": 0.00015464,
|
| 1367 |
+
"loss": 4.4193,
|
| 1368 |
+
"step": 1940
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.10314049586776859,
|
| 1372 |
+
"grad_norm": 150.3628387451172,
|
| 1373 |
+
"learning_rate": 0.00015544000000000002,
|
| 1374 |
+
"loss": 4.4478,
|
| 1375 |
+
"step": 1950
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.1036694214876033,
|
| 1379 |
+
"grad_norm": 112.74451446533203,
|
| 1380 |
+
"learning_rate": 0.00015624,
|
| 1381 |
+
"loss": 4.3628,
|
| 1382 |
+
"step": 1960
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.10419834710743801,
|
| 1386 |
+
"grad_norm": 239.00863647460938,
|
| 1387 |
+
"learning_rate": 0.00015704,
|
| 1388 |
+
"loss": 4.3369,
|
| 1389 |
+
"step": 1970
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.10472727272727272,
|
| 1393 |
+
"grad_norm": 126.43092346191406,
|
| 1394 |
+
"learning_rate": 0.00015784000000000002,
|
| 1395 |
+
"loss": 4.3286,
|
| 1396 |
+
"step": 1980
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.10525619834710744,
|
| 1400 |
+
"grad_norm": 185.16238403320312,
|
| 1401 |
+
"learning_rate": 0.00015864,
|
| 1402 |
+
"loss": 4.2692,
|
| 1403 |
+
"step": 1990
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.10578512396694215,
|
| 1407 |
+
"grad_norm": 128.131103515625,
|
| 1408 |
+
"learning_rate": 0.00015944,
|
| 1409 |
+
"loss": 4.2632,
|
| 1410 |
+
"step": 2000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.10631404958677686,
|
| 1414 |
+
"grad_norm": 158.20382690429688,
|
| 1415 |
+
"learning_rate": 0.00016024000000000002,
|
| 1416 |
+
"loss": 4.2025,
|
| 1417 |
+
"step": 2010
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.10684297520661157,
|
| 1421 |
+
"grad_norm": 129.88511657714844,
|
| 1422 |
+
"learning_rate": 0.00016104000000000002,
|
| 1423 |
+
"loss": 4.3182,
|
| 1424 |
+
"step": 2020
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.10737190082644628,
|
| 1428 |
+
"grad_norm": 99.9822006225586,
|
| 1429 |
+
"learning_rate": 0.00016184,
|
| 1430 |
+
"loss": 4.2665,
|
| 1431 |
+
"step": 2030
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.10790082644628099,
|
| 1435 |
+
"grad_norm": 109.63304138183594,
|
| 1436 |
+
"learning_rate": 0.00016264,
|
| 1437 |
+
"loss": 4.1677,
|
| 1438 |
+
"step": 2040
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.1084297520661157,
|
| 1442 |
+
"grad_norm": 129.84288024902344,
|
| 1443 |
+
"learning_rate": 0.00016344000000000002,
|
| 1444 |
+
"loss": 4.2211,
|
| 1445 |
+
"step": 2050
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.10895867768595041,
|
| 1449 |
+
"grad_norm": 173.83929443359375,
|
| 1450 |
+
"learning_rate": 0.00016424,
|
| 1451 |
+
"loss": 4.177,
|
| 1452 |
+
"step": 2060
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.10948760330578512,
|
| 1456 |
+
"grad_norm": 152.7726287841797,
|
| 1457 |
+
"learning_rate": 0.00016504,
|
| 1458 |
+
"loss": 4.0519,
|
| 1459 |
+
"step": 2070
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.11001652892561983,
|
| 1463 |
+
"grad_norm": 99.01861572265625,
|
| 1464 |
+
"learning_rate": 0.00016584000000000002,
|
| 1465 |
+
"loss": 4.1148,
|
| 1466 |
+
"step": 2080
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.11054545454545454,
|
| 1470 |
+
"grad_norm": 149.03744506835938,
|
| 1471 |
+
"learning_rate": 0.00016664000000000002,
|
| 1472 |
+
"loss": 4.1625,
|
| 1473 |
+
"step": 2090
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.11107438016528925,
|
| 1477 |
+
"grad_norm": 76.12191009521484,
|
| 1478 |
+
"learning_rate": 0.00016744,
|
| 1479 |
+
"loss": 4.145,
|
| 1480 |
+
"step": 2100
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.11160330578512397,
|
| 1484 |
+
"grad_norm": 105.04821014404297,
|
| 1485 |
+
"learning_rate": 0.00016824,
|
| 1486 |
+
"loss": 4.0494,
|
| 1487 |
+
"step": 2110
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.11213223140495868,
|
| 1491 |
+
"grad_norm": 98.34203338623047,
|
| 1492 |
+
"learning_rate": 0.00016904,
|
| 1493 |
+
"loss": 4.0551,
|
| 1494 |
+
"step": 2120
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.11266115702479339,
|
| 1498 |
+
"grad_norm": 138.1121063232422,
|
| 1499 |
+
"learning_rate": 0.00016984,
|
| 1500 |
+
"loss": 3.9701,
|
| 1501 |
+
"step": 2130
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.1131900826446281,
|
| 1505 |
+
"grad_norm": 140.3077392578125,
|
| 1506 |
+
"learning_rate": 0.00017064,
|
| 1507 |
+
"loss": 4.0075,
|
| 1508 |
+
"step": 2140
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.11371900826446281,
|
| 1512 |
+
"grad_norm": 154.5470428466797,
|
| 1513 |
+
"learning_rate": 0.00017144,
|
| 1514 |
+
"loss": 4.1154,
|
| 1515 |
+
"step": 2150
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.11424793388429752,
|
| 1519 |
+
"grad_norm": 131.924072265625,
|
| 1520 |
+
"learning_rate": 0.00017224,
|
| 1521 |
+
"loss": 4.0457,
|
| 1522 |
+
"step": 2160
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.11477685950413223,
|
| 1526 |
+
"grad_norm": 77.7768325805664,
|
| 1527 |
+
"learning_rate": 0.00017304,
|
| 1528 |
+
"loss": 3.8566,
|
| 1529 |
+
"step": 2170
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.11530578512396694,
|
| 1533 |
+
"grad_norm": 164.1995086669922,
|
| 1534 |
+
"learning_rate": 0.00017384,
|
| 1535 |
+
"loss": 3.9619,
|
| 1536 |
+
"step": 2180
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.11583471074380165,
|
| 1540 |
+
"grad_norm": 81.0079345703125,
|
| 1541 |
+
"learning_rate": 0.00017464,
|
| 1542 |
+
"loss": 4.0439,
|
| 1543 |
+
"step": 2190
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.11636363636363636,
|
| 1547 |
+
"grad_norm": 120.98047637939453,
|
| 1548 |
+
"learning_rate": 0.00017544000000000001,
|
| 1549 |
+
"loss": 3.9237,
|
| 1550 |
+
"step": 2200
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.11689256198347107,
|
| 1554 |
+
"grad_norm": 114.70262145996094,
|
| 1555 |
+
"learning_rate": 0.00017624,
|
| 1556 |
+
"loss": 3.9856,
|
| 1557 |
+
"step": 2210
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.11742148760330579,
|
| 1561 |
+
"grad_norm": 161.363525390625,
|
| 1562 |
+
"learning_rate": 0.00017704,
|
| 1563 |
+
"loss": 3.8999,
|
| 1564 |
+
"step": 2220
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.1179504132231405,
|
| 1568 |
+
"grad_norm": 123.91844177246094,
|
| 1569 |
+
"learning_rate": 0.00017784000000000002,
|
| 1570 |
+
"loss": 3.9258,
|
| 1571 |
+
"step": 2230
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.11847933884297521,
|
| 1575 |
+
"grad_norm": 144.61944580078125,
|
| 1576 |
+
"learning_rate": 0.00017864,
|
| 1577 |
+
"loss": 3.9065,
|
| 1578 |
+
"step": 2240
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.11900826446280992,
|
| 1582 |
+
"grad_norm": 121.40870666503906,
|
| 1583 |
+
"learning_rate": 0.00017944,
|
| 1584 |
+
"loss": 3.858,
|
| 1585 |
+
"step": 2250
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.11953719008264463,
|
| 1589 |
+
"grad_norm": 76.07757568359375,
|
| 1590 |
+
"learning_rate": 0.00018024,
|
| 1591 |
+
"loss": 3.8494,
|
| 1592 |
+
"step": 2260
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.12006611570247934,
|
| 1596 |
+
"grad_norm": 99.82099914550781,
|
| 1597 |
+
"learning_rate": 0.00018104000000000001,
|
| 1598 |
+
"loss": 3.8841,
|
| 1599 |
+
"step": 2270
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.12059504132231405,
|
| 1603 |
+
"grad_norm": 121.70137786865234,
|
| 1604 |
+
"learning_rate": 0.00018184,
|
| 1605 |
+
"loss": 3.8417,
|
| 1606 |
+
"step": 2280
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.12112396694214876,
|
| 1610 |
+
"grad_norm": 152.82870483398438,
|
| 1611 |
+
"learning_rate": 0.00018264,
|
| 1612 |
+
"loss": 3.8361,
|
| 1613 |
+
"step": 2290
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.12165289256198347,
|
| 1617 |
+
"grad_norm": 117.6900405883789,
|
| 1618 |
+
"learning_rate": 0.00018344000000000002,
|
| 1619 |
+
"loss": 3.8021,
|
| 1620 |
+
"step": 2300
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.12218181818181818,
|
| 1624 |
+
"grad_norm": 103.37924194335938,
|
| 1625 |
+
"learning_rate": 0.00018424,
|
| 1626 |
+
"loss": 3.7797,
|
| 1627 |
+
"step": 2310
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.1227107438016529,
|
| 1631 |
+
"grad_norm": 102.50745391845703,
|
| 1632 |
+
"learning_rate": 0.00018504,
|
| 1633 |
+
"loss": 3.7944,
|
| 1634 |
+
"step": 2320
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.1232396694214876,
|
| 1638 |
+
"grad_norm": 120.54622650146484,
|
| 1639 |
+
"learning_rate": 0.00018584000000000002,
|
| 1640 |
+
"loss": 3.7223,
|
| 1641 |
+
"step": 2330
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.12376859504132232,
|
| 1645 |
+
"grad_norm": 105.47157287597656,
|
| 1646 |
+
"learning_rate": 0.00018664000000000002,
|
| 1647 |
+
"loss": 3.8349,
|
| 1648 |
+
"step": 2340
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.12429752066115703,
|
| 1652 |
+
"grad_norm": 96.26775360107422,
|
| 1653 |
+
"learning_rate": 0.00018744,
|
| 1654 |
+
"loss": 3.7478,
|
| 1655 |
+
"step": 2350
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.12482644628099174,
|
| 1659 |
+
"grad_norm": 94.46358489990234,
|
| 1660 |
+
"learning_rate": 0.00018824000000000003,
|
| 1661 |
+
"loss": 3.8027,
|
| 1662 |
+
"step": 2360
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.12535537190082643,
|
| 1666 |
+
"grad_norm": 78.01036071777344,
|
| 1667 |
+
"learning_rate": 0.00018904000000000002,
|
| 1668 |
+
"loss": 3.7505,
|
| 1669 |
+
"step": 2370
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.12588429752066116,
|
| 1673 |
+
"grad_norm": 143.33291625976562,
|
| 1674 |
+
"learning_rate": 0.00018984,
|
| 1675 |
+
"loss": 3.6221,
|
| 1676 |
+
"step": 2380
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.12641322314049586,
|
| 1680 |
+
"grad_norm": 89.04401397705078,
|
| 1681 |
+
"learning_rate": 0.00019064000000000003,
|
| 1682 |
+
"loss": 3.7705,
|
| 1683 |
+
"step": 2390
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.12694214876033058,
|
| 1687 |
+
"grad_norm": 111.32374572753906,
|
| 1688 |
+
"learning_rate": 0.00019144000000000002,
|
| 1689 |
+
"loss": 3.6446,
|
| 1690 |
+
"step": 2400
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.12747107438016528,
|
| 1694 |
+
"grad_norm": 98.54373168945312,
|
| 1695 |
+
"learning_rate": 0.00019224000000000002,
|
| 1696 |
+
"loss": 3.6462,
|
| 1697 |
+
"step": 2410
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.128,
|
| 1701 |
+
"grad_norm": 97.3410415649414,
|
| 1702 |
+
"learning_rate": 0.00019304,
|
| 1703 |
+
"loss": 3.6436,
|
| 1704 |
+
"step": 2420
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.1285289256198347,
|
| 1708 |
+
"grad_norm": 109.594482421875,
|
| 1709 |
+
"learning_rate": 0.00019384,
|
| 1710 |
+
"loss": 3.5529,
|
| 1711 |
+
"step": 2430
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.12905785123966942,
|
| 1715 |
+
"grad_norm": 70.01071166992188,
|
| 1716 |
+
"learning_rate": 0.00019464,
|
| 1717 |
+
"loss": 3.5879,
|
| 1718 |
+
"step": 2440
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.12958677685950412,
|
| 1722 |
+
"grad_norm": 69.51897430419922,
|
| 1723 |
+
"learning_rate": 0.00019544,
|
| 1724 |
+
"loss": 3.6464,
|
| 1725 |
+
"step": 2450
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.13011570247933885,
|
| 1729 |
+
"grad_norm": 120.34490966796875,
|
| 1730 |
+
"learning_rate": 0.00019624,
|
| 1731 |
+
"loss": 3.484,
|
| 1732 |
+
"step": 2460
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 0.13064462809917354,
|
| 1736 |
+
"grad_norm": 118.81869506835938,
|
| 1737 |
+
"learning_rate": 0.00019704,
|
| 1738 |
+
"loss": 3.6032,
|
| 1739 |
+
"step": 2470
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 0.13117355371900827,
|
| 1743 |
+
"grad_norm": 67.180419921875,
|
| 1744 |
+
"learning_rate": 0.00019784,
|
| 1745 |
+
"loss": 3.6563,
|
| 1746 |
+
"step": 2480
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.13170247933884296,
|
| 1750 |
+
"grad_norm": 125.26102447509766,
|
| 1751 |
+
"learning_rate": 0.00019864,
|
| 1752 |
+
"loss": 3.5318,
|
| 1753 |
+
"step": 2490
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.1322314049586777,
|
| 1757 |
+
"grad_norm": 59.11252975463867,
|
| 1758 |
+
"learning_rate": 0.00019944,
|
| 1759 |
+
"loss": 3.4811,
|
| 1760 |
+
"step": 2500
|
| 1761 |
+
}
|
| 1762 |
+
],
|
| 1763 |
+
"logging_steps": 10,
|
| 1764 |
+
"max_steps": 10000000,
|
| 1765 |
+
"num_input_tokens_seen": 0,
|
| 1766 |
+
"num_train_epochs": 529,
|
| 1767 |
+
"save_steps": 100,
|
| 1768 |
+
"stateful_callbacks": {
|
| 1769 |
+
"TrainerControl": {
|
| 1770 |
+
"args": {
|
| 1771 |
+
"should_epoch_stop": false,
|
| 1772 |
+
"should_evaluate": false,
|
| 1773 |
+
"should_log": false,
|
| 1774 |
+
"should_save": true,
|
| 1775 |
+
"should_training_stop": false
|
| 1776 |
+
},
|
| 1777 |
+
"attributes": {}
|
| 1778 |
+
}
|
| 1779 |
+
},
|
| 1780 |
+
"total_flos": 4.35712750559232e+16,
|
| 1781 |
+
"train_batch_size": 8,
|
| 1782 |
+
"trial_name": null,
|
| 1783 |
+
"trial_params": null
|
| 1784 |
+
}
|
checkpoint-2500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15fcfa1bbe0f7d96538cf17908c1e0f3298cf826d4ee288e67e22815d92829e3
|
| 3 |
+
size 5137
|