Upload folder using huggingface_hub
Browse files- chat_template.jinja +1 -0
- config.json +36 -0
- generation_config.json +9 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +0 -0
- trainer_state.json +1329 -0
- training_args.bin +3 -0
chat_template.jinja
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{{ bos_token }}{% for message in messages %}{% if message['role'] == 'system' %}{{ '[INST] System: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'user' %}{% if loop.index0 == 0 or (loop.index0 == 1 and messages[0]['role'] == 'system') %}{{ message['content'] + ' [/INST]' }}{% else %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% endif %}{% elif message['role'] == 'assistant' %}{{ ' ' + message['content'] + eos_token }}{% else %}{{ raise_exception('Only system, user, and assistant roles are supported!') }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ ' ' }}{% endif %}
|
config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HybridFourierLM"
|
| 4 |
+
],
|
| 5 |
+
"auto_map": {
|
| 6 |
+
"AutoConfig": "model.HybridFourierConfig",
|
| 7 |
+
"AutoModelForCausalLM": "model.HybridFourierLM"
|
| 8 |
+
},
|
| 9 |
+
"bos_token_id": 1,
|
| 10 |
+
"dropout": 0.05,
|
| 11 |
+
"dtype": "bfloat16",
|
| 12 |
+
"eos_token_id": 2,
|
| 13 |
+
"latent_dim": 768,
|
| 14 |
+
"layer_types": [
|
| 15 |
+
"linear",
|
| 16 |
+
"linear",
|
| 17 |
+
"linear",
|
| 18 |
+
"softmax",
|
| 19 |
+
"linear",
|
| 20 |
+
"linear",
|
| 21 |
+
"linear",
|
| 22 |
+
"softmax",
|
| 23 |
+
"linear",
|
| 24 |
+
"linear",
|
| 25 |
+
"linear",
|
| 26 |
+
"softmax"
|
| 27 |
+
],
|
| 28 |
+
"model_type": "hybrid_fourier_lm",
|
| 29 |
+
"num_layers": 12,
|
| 30 |
+
"num_modes": 64,
|
| 31 |
+
"pad_token_id": 2,
|
| 32 |
+
"time_scale": 128.0,
|
| 33 |
+
"transformers_version": "4.56.0",
|
| 34 |
+
"use_cache": false,
|
| 35 |
+
"vocab_size": 32768
|
| 36 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
2
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 2,
|
| 8 |
+
"transformers_version": "4.56.0"
|
| 9 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01d6abe1f7aba6be6f3d2428cb3142a01f8544dd43320a2d9a2892488852d2ff
|
| 3 |
+
size 234683688
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54d7a0389c000c1a37878e18eec5448fd9d8a771ee35b483e2bcfca79cce09ad
|
| 3 |
+
size 469516363
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91f6ccdd0eeb88da4d8a5f4b5b0d6f584586db1f41fc805ac11822ddb4e886f8
|
| 3 |
+
size 14645
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5de482cc10086d5c1081320f7eabc0195d51d8a1561cc1d4b0b946e2773fe88a
|
| 3 |
+
size 1465
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
|
| 3 |
+
size 587404
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1329 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 929,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.005382131324004306,
|
| 14 |
+
"grad_norm": 19.25,
|
| 15 |
+
"learning_rate": 5.7142857142857145e-06,
|
| 16 |
+
"loss": 7.5826,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.010764262648008612,
|
| 21 |
+
"grad_norm": 24.125,
|
| 22 |
+
"learning_rate": 1.2857142857142857e-05,
|
| 23 |
+
"loss": 7.7389,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.016146393972012917,
|
| 28 |
+
"grad_norm": 20.375,
|
| 29 |
+
"learning_rate": 2e-05,
|
| 30 |
+
"loss": 8.0474,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.021528525296017224,
|
| 35 |
+
"grad_norm": 17.375,
|
| 36 |
+
"learning_rate": 2.714285714285714e-05,
|
| 37 |
+
"loss": 7.2989,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.02691065662002153,
|
| 42 |
+
"grad_norm": 15.0625,
|
| 43 |
+
"learning_rate": 3.428571428571429e-05,
|
| 44 |
+
"loss": 7.8579,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.03229278794402583,
|
| 49 |
+
"grad_norm": 12.875,
|
| 50 |
+
"learning_rate": 4.1428571428571437e-05,
|
| 51 |
+
"loss": 7.3271,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.03767491926803014,
|
| 56 |
+
"grad_norm": 8.5,
|
| 57 |
+
"learning_rate": 4.8571428571428576e-05,
|
| 58 |
+
"loss": 7.0945,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.04305705059203445,
|
| 63 |
+
"grad_norm": 7.46875,
|
| 64 |
+
"learning_rate": 5.571428571428572e-05,
|
| 65 |
+
"loss": 6.3577,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.04843918191603875,
|
| 70 |
+
"grad_norm": 7.40625,
|
| 71 |
+
"learning_rate": 6.285714285714286e-05,
|
| 72 |
+
"loss": 6.2656,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.05382131324004306,
|
| 77 |
+
"grad_norm": 3.53125,
|
| 78 |
+
"learning_rate": 7e-05,
|
| 79 |
+
"loss": 6.2146,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.059203444564047365,
|
| 84 |
+
"grad_norm": 3.671875,
|
| 85 |
+
"learning_rate": 7.714285714285715e-05,
|
| 86 |
+
"loss": 5.7147,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.06458557588805167,
|
| 91 |
+
"grad_norm": 2.6875,
|
| 92 |
+
"learning_rate": 8.428571428571429e-05,
|
| 93 |
+
"loss": 5.2684,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.06996770721205597,
|
| 98 |
+
"grad_norm": 2.203125,
|
| 99 |
+
"learning_rate": 9.142857142857143e-05,
|
| 100 |
+
"loss": 4.914,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.07534983853606028,
|
| 105 |
+
"grad_norm": 2.28125,
|
| 106 |
+
"learning_rate": 9.857142857142858e-05,
|
| 107 |
+
"loss": 5.5474,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.08073196986006459,
|
| 112 |
+
"grad_norm": 3.03125,
|
| 113 |
+
"learning_rate": 0.00010571428571428572,
|
| 114 |
+
"loss": 4.0901,
|
| 115 |
+
"step": 75
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.0861141011840689,
|
| 119 |
+
"grad_norm": 2.40625,
|
| 120 |
+
"learning_rate": 0.00011285714285714286,
|
| 121 |
+
"loss": 4.1259,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.09149623250807319,
|
| 126 |
+
"grad_norm": 2.328125,
|
| 127 |
+
"learning_rate": 0.00012,
|
| 128 |
+
"loss": 3.7235,
|
| 129 |
+
"step": 85
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.0968783638320775,
|
| 133 |
+
"grad_norm": 2.46875,
|
| 134 |
+
"learning_rate": 0.00012714285714285714,
|
| 135 |
+
"loss": 3.1657,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.10226049515608181,
|
| 140 |
+
"grad_norm": 3.171875,
|
| 141 |
+
"learning_rate": 0.00013428571428571428,
|
| 142 |
+
"loss": 3.4388,
|
| 143 |
+
"step": 95
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.10764262648008611,
|
| 147 |
+
"grad_norm": 2.34375,
|
| 148 |
+
"learning_rate": 0.00014142857142857145,
|
| 149 |
+
"loss": 3.637,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.11302475780409042,
|
| 154 |
+
"grad_norm": 1.9375,
|
| 155 |
+
"learning_rate": 0.00014857142857142857,
|
| 156 |
+
"loss": 2.8895,
|
| 157 |
+
"step": 105
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.11840688912809473,
|
| 161 |
+
"grad_norm": 2.40625,
|
| 162 |
+
"learning_rate": 0.00015571428571428572,
|
| 163 |
+
"loss": 3.011,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.12378902045209902,
|
| 168 |
+
"grad_norm": 1.6796875,
|
| 169 |
+
"learning_rate": 0.00016285714285714287,
|
| 170 |
+
"loss": 2.5217,
|
| 171 |
+
"step": 115
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.12917115177610333,
|
| 175 |
+
"grad_norm": 1.609375,
|
| 176 |
+
"learning_rate": 0.00017,
|
| 177 |
+
"loss": 2.3684,
|
| 178 |
+
"step": 120
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.13455328310010764,
|
| 182 |
+
"grad_norm": 1.3203125,
|
| 183 |
+
"learning_rate": 0.00017714285714285713,
|
| 184 |
+
"loss": 2.6268,
|
| 185 |
+
"step": 125
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.13993541442411195,
|
| 189 |
+
"grad_norm": 1.6953125,
|
| 190 |
+
"learning_rate": 0.00018428571428571428,
|
| 191 |
+
"loss": 2.2101,
|
| 192 |
+
"step": 130
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.14531754574811626,
|
| 196 |
+
"grad_norm": 1.71875,
|
| 197 |
+
"learning_rate": 0.00019142857142857145,
|
| 198 |
+
"loss": 2.1823,
|
| 199 |
+
"step": 135
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.15069967707212056,
|
| 203 |
+
"grad_norm": 0.9375,
|
| 204 |
+
"learning_rate": 0.0001985714285714286,
|
| 205 |
+
"loss": 1.8939,
|
| 206 |
+
"step": 140
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.15608180839612487,
|
| 210 |
+
"grad_norm": 1.3125,
|
| 211 |
+
"learning_rate": 0.00019999887311127372,
|
| 212 |
+
"loss": 2.6186,
|
| 213 |
+
"step": 145
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.16146393972012918,
|
| 217 |
+
"grad_norm": 1.15625,
|
| 218 |
+
"learning_rate": 0.0001999942951693512,
|
| 219 |
+
"loss": 2.3448,
|
| 220 |
+
"step": 150
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.1668460710441335,
|
| 224 |
+
"grad_norm": 1.53125,
|
| 225 |
+
"learning_rate": 0.00019998619590477638,
|
| 226 |
+
"loss": 2.0453,
|
| 227 |
+
"step": 155
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.1722282023681378,
|
| 231 |
+
"grad_norm": 1.1328125,
|
| 232 |
+
"learning_rate": 0.00019997457560276666,
|
| 233 |
+
"loss": 1.9159,
|
| 234 |
+
"step": 160
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.17761033369214208,
|
| 238 |
+
"grad_norm": 1.3359375,
|
| 239 |
+
"learning_rate": 0.00019995943467253385,
|
| 240 |
+
"loss": 2.2564,
|
| 241 |
+
"step": 165
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.18299246501614638,
|
| 245 |
+
"grad_norm": 1.453125,
|
| 246 |
+
"learning_rate": 0.00019994077364726925,
|
| 247 |
+
"loss": 2.1459,
|
| 248 |
+
"step": 170
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.1883745963401507,
|
| 252 |
+
"grad_norm": 1.15625,
|
| 253 |
+
"learning_rate": 0.00019991859318412537,
|
| 254 |
+
"loss": 2.3652,
|
| 255 |
+
"step": 175
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.193756727664155,
|
| 259 |
+
"grad_norm": 1.703125,
|
| 260 |
+
"learning_rate": 0.00019989289406419238,
|
| 261 |
+
"loss": 2.0883,
|
| 262 |
+
"step": 180
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.1991388589881593,
|
| 266 |
+
"grad_norm": 1.046875,
|
| 267 |
+
"learning_rate": 0.00019986367719247082,
|
| 268 |
+
"loss": 2.0466,
|
| 269 |
+
"step": 185
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.20452099031216361,
|
| 273 |
+
"grad_norm": 1.9765625,
|
| 274 |
+
"learning_rate": 0.00019983094359783977,
|
| 275 |
+
"loss": 2.0306,
|
| 276 |
+
"step": 190
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.20990312163616792,
|
| 280 |
+
"grad_norm": 0.93359375,
|
| 281 |
+
"learning_rate": 0.00019979469443302046,
|
| 282 |
+
"loss": 1.73,
|
| 283 |
+
"step": 195
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.21528525296017223,
|
| 287 |
+
"grad_norm": 1.203125,
|
| 288 |
+
"learning_rate": 0.0001997549309745357,
|
| 289 |
+
"loss": 2.1835,
|
| 290 |
+
"step": 200
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.22066738428417654,
|
| 294 |
+
"grad_norm": 0.80859375,
|
| 295 |
+
"learning_rate": 0.00019971165462266512,
|
| 296 |
+
"loss": 1.8594,
|
| 297 |
+
"step": 205
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.22604951560818085,
|
| 301 |
+
"grad_norm": 0.98828125,
|
| 302 |
+
"learning_rate": 0.00019966486690139564,
|
| 303 |
+
"loss": 1.8338,
|
| 304 |
+
"step": 210
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.23143164693218515,
|
| 308 |
+
"grad_norm": 1.15625,
|
| 309 |
+
"learning_rate": 0.0001996145694583678,
|
| 310 |
+
"loss": 2.0899,
|
| 311 |
+
"step": 215
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.23681377825618946,
|
| 315 |
+
"grad_norm": 1.296875,
|
| 316 |
+
"learning_rate": 0.000199560764064818,
|
| 317 |
+
"loss": 2.0116,
|
| 318 |
+
"step": 220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.24219590958019377,
|
| 322 |
+
"grad_norm": 1.4375,
|
| 323 |
+
"learning_rate": 0.00019950345261551583,
|
| 324 |
+
"loss": 1.9816,
|
| 325 |
+
"step": 225
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.24757804090419805,
|
| 329 |
+
"grad_norm": 0.89453125,
|
| 330 |
+
"learning_rate": 0.0001994426371286974,
|
| 331 |
+
"loss": 1.4429,
|
| 332 |
+
"step": 230
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.2529601722282024,
|
| 336 |
+
"grad_norm": 1.171875,
|
| 337 |
+
"learning_rate": 0.00019937831974599447,
|
| 338 |
+
"loss": 1.8191,
|
| 339 |
+
"step": 235
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.25834230355220666,
|
| 343 |
+
"grad_norm": 1.0625,
|
| 344 |
+
"learning_rate": 0.0001993105027323588,
|
| 345 |
+
"loss": 2.0092,
|
| 346 |
+
"step": 240
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.263724434876211,
|
| 350 |
+
"grad_norm": 0.95703125,
|
| 351 |
+
"learning_rate": 0.00019923918847598247,
|
| 352 |
+
"loss": 1.6442,
|
| 353 |
+
"step": 245
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.2691065662002153,
|
| 357 |
+
"grad_norm": 1.1953125,
|
| 358 |
+
"learning_rate": 0.00019916437948821382,
|
| 359 |
+
"loss": 2.29,
|
| 360 |
+
"step": 250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.2744886975242196,
|
| 364 |
+
"grad_norm": 1.2734375,
|
| 365 |
+
"learning_rate": 0.00019908607840346903,
|
| 366 |
+
"loss": 1.7178,
|
| 367 |
+
"step": 255
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.2798708288482239,
|
| 371 |
+
"grad_norm": 0.91015625,
|
| 372 |
+
"learning_rate": 0.00019900428797913915,
|
| 373 |
+
"loss": 1.8539,
|
| 374 |
+
"step": 260
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.2852529601722282,
|
| 378 |
+
"grad_norm": 1.21875,
|
| 379 |
+
"learning_rate": 0.0001989190110954933,
|
| 380 |
+
"loss": 1.9345,
|
| 381 |
+
"step": 265
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.2906350914962325,
|
| 385 |
+
"grad_norm": 1.3515625,
|
| 386 |
+
"learning_rate": 0.000198830250755577,
|
| 387 |
+
"loss": 2.1381,
|
| 388 |
+
"step": 270
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.2960172228202368,
|
| 392 |
+
"grad_norm": 1.015625,
|
| 393 |
+
"learning_rate": 0.0001987380100851065,
|
| 394 |
+
"loss": 2.0466,
|
| 395 |
+
"step": 275
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.3013993541442411,
|
| 399 |
+
"grad_norm": 0.953125,
|
| 400 |
+
"learning_rate": 0.00019864229233235875,
|
| 401 |
+
"loss": 2.1104,
|
| 402 |
+
"step": 280
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.3067814854682454,
|
| 406 |
+
"grad_norm": 0.984375,
|
| 407 |
+
"learning_rate": 0.000198543100868057,
|
| 408 |
+
"loss": 2.0808,
|
| 409 |
+
"step": 285
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.31216361679224974,
|
| 413 |
+
"grad_norm": 1.390625,
|
| 414 |
+
"learning_rate": 0.00019844043918525195,
|
| 415 |
+
"loss": 1.9378,
|
| 416 |
+
"step": 290
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.317545748116254,
|
| 420 |
+
"grad_norm": 0.78515625,
|
| 421 |
+
"learning_rate": 0.00019833431089919898,
|
| 422 |
+
"loss": 1.565,
|
| 423 |
+
"step": 295
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.32292787944025836,
|
| 427 |
+
"grad_norm": 1.7109375,
|
| 428 |
+
"learning_rate": 0.00019822471974723064,
|
| 429 |
+
"loss": 1.8316,
|
| 430 |
+
"step": 300
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.32831001076426264,
|
| 434 |
+
"grad_norm": 1.0234375,
|
| 435 |
+
"learning_rate": 0.0001981116695886252,
|
| 436 |
+
"loss": 1.9357,
|
| 437 |
+
"step": 305
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.333692142088267,
|
| 441 |
+
"grad_norm": 0.99609375,
|
| 442 |
+
"learning_rate": 0.00019799516440447058,
|
| 443 |
+
"loss": 1.7745,
|
| 444 |
+
"step": 310
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.33907427341227125,
|
| 448 |
+
"grad_norm": 0.97265625,
|
| 449 |
+
"learning_rate": 0.00019787520829752427,
|
| 450 |
+
"loss": 1.8947,
|
| 451 |
+
"step": 315
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.3444564047362756,
|
| 455 |
+
"grad_norm": 0.8046875,
|
| 456 |
+
"learning_rate": 0.00019775180549206888,
|
| 457 |
+
"loss": 1.6128,
|
| 458 |
+
"step": 320
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.34983853606027987,
|
| 462 |
+
"grad_norm": 0.921875,
|
| 463 |
+
"learning_rate": 0.0001976249603337632,
|
| 464 |
+
"loss": 1.6003,
|
| 465 |
+
"step": 325
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.35522066738428415,
|
| 469 |
+
"grad_norm": 0.7421875,
|
| 470 |
+
"learning_rate": 0.00019749467728948943,
|
| 471 |
+
"loss": 1.7543,
|
| 472 |
+
"step": 330
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.3606027987082885,
|
| 476 |
+
"grad_norm": 1.46875,
|
| 477 |
+
"learning_rate": 0.0001973609609471956,
|
| 478 |
+
"loss": 1.8543,
|
| 479 |
+
"step": 335
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.36598493003229277,
|
| 483 |
+
"grad_norm": 0.953125,
|
| 484 |
+
"learning_rate": 0.00019722381601573413,
|
| 485 |
+
"loss": 1.7436,
|
| 486 |
+
"step": 340
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.3713670613562971,
|
| 490 |
+
"grad_norm": 0.9765625,
|
| 491 |
+
"learning_rate": 0.0001970832473246962,
|
| 492 |
+
"loss": 2.1039,
|
| 493 |
+
"step": 345
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.3767491926803014,
|
| 497 |
+
"grad_norm": 0.76171875,
|
| 498 |
+
"learning_rate": 0.0001969392598242413,
|
| 499 |
+
"loss": 1.9624,
|
| 500 |
+
"step": 350
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.3821313240043057,
|
| 504 |
+
"grad_norm": 0.6796875,
|
| 505 |
+
"learning_rate": 0.0001967918585849232,
|
| 506 |
+
"loss": 1.4343,
|
| 507 |
+
"step": 355
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.38751345532831,
|
| 511 |
+
"grad_norm": 1.2421875,
|
| 512 |
+
"learning_rate": 0.00019664104879751123,
|
| 513 |
+
"loss": 1.5505,
|
| 514 |
+
"step": 360
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.39289558665231433,
|
| 518 |
+
"grad_norm": 0.86328125,
|
| 519 |
+
"learning_rate": 0.00019648683577280757,
|
| 520 |
+
"loss": 1.6731,
|
| 521 |
+
"step": 365
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.3982777179763186,
|
| 525 |
+
"grad_norm": 0.90234375,
|
| 526 |
+
"learning_rate": 0.0001963292249414602,
|
| 527 |
+
"loss": 1.6294,
|
| 528 |
+
"step": 370
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.40365984930032295,
|
| 532 |
+
"grad_norm": 0.80859375,
|
| 533 |
+
"learning_rate": 0.0001961682218537717,
|
| 534 |
+
"loss": 1.7152,
|
| 535 |
+
"step": 375
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.40904198062432723,
|
| 539 |
+
"grad_norm": 1.2890625,
|
| 540 |
+
"learning_rate": 0.00019600383217950365,
|
| 541 |
+
"loss": 2.0493,
|
| 542 |
+
"step": 380
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.41442411194833156,
|
| 546 |
+
"grad_norm": 1.2890625,
|
| 547 |
+
"learning_rate": 0.00019583606170767718,
|
| 548 |
+
"loss": 1.809,
|
| 549 |
+
"step": 385
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.41980624327233584,
|
| 553 |
+
"grad_norm": 0.93359375,
|
| 554 |
+
"learning_rate": 0.00019566491634636897,
|
| 555 |
+
"loss": 2.0224,
|
| 556 |
+
"step": 390
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.4251883745963401,
|
| 560 |
+
"grad_norm": 1.1484375,
|
| 561 |
+
"learning_rate": 0.0001954904021225032,
|
| 562 |
+
"loss": 1.8455,
|
| 563 |
+
"step": 395
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.43057050592034446,
|
| 567 |
+
"grad_norm": 0.83984375,
|
| 568 |
+
"learning_rate": 0.0001953125251816394,
|
| 569 |
+
"loss": 1.5119,
|
| 570 |
+
"step": 400
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.43595263724434874,
|
| 574 |
+
"grad_norm": 0.95703125,
|
| 575 |
+
"learning_rate": 0.00019513129178775588,
|
| 576 |
+
"loss": 1.6183,
|
| 577 |
+
"step": 405
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.4413347685683531,
|
| 581 |
+
"grad_norm": 0.97265625,
|
| 582 |
+
"learning_rate": 0.0001949467083230293,
|
| 583 |
+
"loss": 1.5994,
|
| 584 |
+
"step": 410
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.44671689989235736,
|
| 588 |
+
"grad_norm": 0.92578125,
|
| 589 |
+
"learning_rate": 0.0001947587812876099,
|
| 590 |
+
"loss": 1.9839,
|
| 591 |
+
"step": 415
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.4520990312163617,
|
| 595 |
+
"grad_norm": 0.95703125,
|
| 596 |
+
"learning_rate": 0.00019456751729939238,
|
| 597 |
+
"loss": 1.7201,
|
| 598 |
+
"step": 420
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.45748116254036597,
|
| 602 |
+
"grad_norm": 0.74609375,
|
| 603 |
+
"learning_rate": 0.00019437292309378324,
|
| 604 |
+
"loss": 1.8024,
|
| 605 |
+
"step": 425
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.4628632938643703,
|
| 609 |
+
"grad_norm": 1.609375,
|
| 610 |
+
"learning_rate": 0.00019417500552346316,
|
| 611 |
+
"loss": 1.421,
|
| 612 |
+
"step": 430
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.4682454251883746,
|
| 616 |
+
"grad_norm": 0.98046875,
|
| 617 |
+
"learning_rate": 0.000193973771558146,
|
| 618 |
+
"loss": 1.5199,
|
| 619 |
+
"step": 435
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.4736275565123789,
|
| 623 |
+
"grad_norm": 0.97265625,
|
| 624 |
+
"learning_rate": 0.0001937692282843333,
|
| 625 |
+
"loss": 1.8052,
|
| 626 |
+
"step": 440
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.4790096878363832,
|
| 630 |
+
"grad_norm": 1.078125,
|
| 631 |
+
"learning_rate": 0.00019356138290506461,
|
| 632 |
+
"loss": 2.0869,
|
| 633 |
+
"step": 445
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.48439181916038754,
|
| 637 |
+
"grad_norm": 0.99609375,
|
| 638 |
+
"learning_rate": 0.00019335024273966383,
|
| 639 |
+
"loss": 1.5393,
|
| 640 |
+
"step": 450
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.4897739504843918,
|
| 644 |
+
"grad_norm": 1.171875,
|
| 645 |
+
"learning_rate": 0.00019313581522348164,
|
| 646 |
+
"loss": 1.6464,
|
| 647 |
+
"step": 455
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.4951560818083961,
|
| 651 |
+
"grad_norm": 0.83203125,
|
| 652 |
+
"learning_rate": 0.00019291810790763355,
|
| 653 |
+
"loss": 1.8133,
|
| 654 |
+
"step": 460
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.5005382131324004,
|
| 658 |
+
"grad_norm": 1.453125,
|
| 659 |
+
"learning_rate": 0.00019269712845873397,
|
| 660 |
+
"loss": 2.0506,
|
| 661 |
+
"step": 465
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.5059203444564048,
|
| 665 |
+
"grad_norm": 0.84375,
|
| 666 |
+
"learning_rate": 0.00019247288465862615,
|
| 667 |
+
"loss": 1.95,
|
| 668 |
+
"step": 470
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.511302475780409,
|
| 672 |
+
"grad_norm": 0.91015625,
|
| 673 |
+
"learning_rate": 0.0001922453844041084,
|
| 674 |
+
"loss": 1.565,
|
| 675 |
+
"step": 475
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.5166846071044133,
|
| 679 |
+
"grad_norm": 0.71875,
|
| 680 |
+
"learning_rate": 0.00019201463570665573,
|
| 681 |
+
"loss": 1.7664,
|
| 682 |
+
"step": 480
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.5220667384284177,
|
| 686 |
+
"grad_norm": 0.6015625,
|
| 687 |
+
"learning_rate": 0.0001917806466921378,
|
| 688 |
+
"loss": 1.6515,
|
| 689 |
+
"step": 485
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.527448869752422,
|
| 693 |
+
"grad_norm": 0.69140625,
|
| 694 |
+
"learning_rate": 0.00019154342560053297,
|
| 695 |
+
"loss": 1.654,
|
| 696 |
+
"step": 490
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.5328310010764262,
|
| 700 |
+
"grad_norm": 0.62109375,
|
| 701 |
+
"learning_rate": 0.0001913029807856378,
|
| 702 |
+
"loss": 1.5976,
|
| 703 |
+
"step": 495
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.5382131324004306,
|
| 707 |
+
"grad_norm": 1.0859375,
|
| 708 |
+
"learning_rate": 0.00019105932071477303,
|
| 709 |
+
"loss": 1.497,
|
| 710 |
+
"step": 500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.5435952637244349,
|
| 714 |
+
"grad_norm": 0.87890625,
|
| 715 |
+
"learning_rate": 0.00019081245396848547,
|
| 716 |
+
"loss": 1.6065,
|
| 717 |
+
"step": 505
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.5489773950484392,
|
| 721 |
+
"grad_norm": 0.78125,
|
| 722 |
+
"learning_rate": 0.00019056238924024574,
|
| 723 |
+
"loss": 1.3089,
|
| 724 |
+
"step": 510
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.5543595263724435,
|
| 728 |
+
"grad_norm": 1.0546875,
|
| 729 |
+
"learning_rate": 0.00019030913533614208,
|
| 730 |
+
"loss": 1.8274,
|
| 731 |
+
"step": 515
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.5597416576964478,
|
| 735 |
+
"grad_norm": 1.1953125,
|
| 736 |
+
"learning_rate": 0.00019005270117457043,
|
| 737 |
+
"loss": 1.6165,
|
| 738 |
+
"step": 520
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.5651237890204521,
|
| 742 |
+
"grad_norm": 1.0625,
|
| 743 |
+
"learning_rate": 0.00018979309578592016,
|
| 744 |
+
"loss": 1.578,
|
| 745 |
+
"step": 525
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.5705059203444564,
|
| 749 |
+
"grad_norm": 1.7109375,
|
| 750 |
+
"learning_rate": 0.0001895303283122561,
|
| 751 |
+
"loss": 1.7197,
|
| 752 |
+
"step": 530
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.5758880516684607,
|
| 756 |
+
"grad_norm": 1.0390625,
|
| 757 |
+
"learning_rate": 0.00018926440800699678,
|
| 758 |
+
"loss": 1.7235,
|
| 759 |
+
"step": 535
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.581270182992465,
|
| 763 |
+
"grad_norm": 0.92578125,
|
| 764 |
+
"learning_rate": 0.0001889953442345884,
|
| 765 |
+
"loss": 1.536,
|
| 766 |
+
"step": 540
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.5866523143164694,
|
| 770 |
+
"grad_norm": 0.8125,
|
| 771 |
+
"learning_rate": 0.000188723146470175,
|
| 772 |
+
"loss": 1.8374,
|
| 773 |
+
"step": 545
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.5920344456404736,
|
| 777 |
+
"grad_norm": 0.96484375,
|
| 778 |
+
"learning_rate": 0.00018844782429926495,
|
| 779 |
+
"loss": 1.4953,
|
| 780 |
+
"step": 550
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.5974165769644779,
|
| 784 |
+
"grad_norm": 0.7734375,
|
| 785 |
+
"learning_rate": 0.0001881693874173934,
|
| 786 |
+
"loss": 1.3424,
|
| 787 |
+
"step": 555
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.6027987082884823,
|
| 791 |
+
"grad_norm": 0.7890625,
|
| 792 |
+
"learning_rate": 0.0001878878456297807,
|
| 793 |
+
"loss": 1.4368,
|
| 794 |
+
"step": 560
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.6081808396124866,
|
| 798 |
+
"grad_norm": 1.09375,
|
| 799 |
+
"learning_rate": 0.00018760320885098715,
|
| 800 |
+
"loss": 1.7983,
|
| 801 |
+
"step": 565
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.6135629709364908,
|
| 805 |
+
"grad_norm": 1.1015625,
|
| 806 |
+
"learning_rate": 0.00018731548710456398,
|
| 807 |
+
"loss": 1.8513,
|
| 808 |
+
"step": 570
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.6189451022604952,
|
| 812 |
+
"grad_norm": 2.125,
|
| 813 |
+
"learning_rate": 0.00018702469052270023,
|
| 814 |
+
"loss": 2.1254,
|
| 815 |
+
"step": 575
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.6243272335844995,
|
| 819 |
+
"grad_norm": 0.7421875,
|
| 820 |
+
"learning_rate": 0.00018673082934586607,
|
| 821 |
+
"loss": 1.6763,
|
| 822 |
+
"step": 580
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.6297093649085038,
|
| 826 |
+
"grad_norm": 1.140625,
|
| 827 |
+
"learning_rate": 0.00018643391392245197,
|
| 828 |
+
"loss": 1.6641,
|
| 829 |
+
"step": 585
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.635091496232508,
|
| 833 |
+
"grad_norm": 0.890625,
|
| 834 |
+
"learning_rate": 0.00018613395470840454,
|
| 835 |
+
"loss": 2.0576,
|
| 836 |
+
"step": 590
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.6404736275565124,
|
| 840 |
+
"grad_norm": 0.74609375,
|
| 841 |
+
"learning_rate": 0.0001858309622668581,
|
| 842 |
+
"loss": 1.643,
|
| 843 |
+
"step": 595
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.6458557588805167,
|
| 847 |
+
"grad_norm": 1.3671875,
|
| 848 |
+
"learning_rate": 0.00018552494726776283,
|
| 849 |
+
"loss": 1.8816,
|
| 850 |
+
"step": 600
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.6512378902045209,
|
| 854 |
+
"grad_norm": 0.8515625,
|
| 855 |
+
"learning_rate": 0.00018521592048750907,
|
| 856 |
+
"loss": 1.4728,
|
| 857 |
+
"step": 605
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.6566200215285253,
|
| 861 |
+
"grad_norm": 0.94921875,
|
| 862 |
+
"learning_rate": 0.00018490389280854754,
|
| 863 |
+
"loss": 1.6078,
|
| 864 |
+
"step": 610
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.6620021528525296,
|
| 868 |
+
"grad_norm": 0.96484375,
|
| 869 |
+
"learning_rate": 0.0001845888752190065,
|
| 870 |
+
"loss": 1.6509,
|
| 871 |
+
"step": 615
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.667384284176534,
|
| 875 |
+
"grad_norm": 0.73046875,
|
| 876 |
+
"learning_rate": 0.00018427087881230455,
|
| 877 |
+
"loss": 1.1777,
|
| 878 |
+
"step": 620
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.6727664155005382,
|
| 882 |
+
"grad_norm": 1.09375,
|
| 883 |
+
"learning_rate": 0.00018394991478676005,
|
| 884 |
+
"loss": 1.4283,
|
| 885 |
+
"step": 625
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.6781485468245425,
|
| 889 |
+
"grad_norm": 0.859375,
|
| 890 |
+
"learning_rate": 0.0001836259944451967,
|
| 891 |
+
"loss": 1.6932,
|
| 892 |
+
"step": 630
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.6835306781485468,
|
| 896 |
+
"grad_norm": 1.03125,
|
| 897 |
+
"learning_rate": 0.00018329912919454565,
|
| 898 |
+
"loss": 1.4168,
|
| 899 |
+
"step": 635
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.6889128094725512,
|
| 903 |
+
"grad_norm": 0.77734375,
|
| 904 |
+
"learning_rate": 0.00018296933054544367,
|
| 905 |
+
"loss": 1.7149,
|
| 906 |
+
"step": 640
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.6942949407965554,
|
| 910 |
+
"grad_norm": 0.921875,
|
| 911 |
+
"learning_rate": 0.00018263661011182783,
|
| 912 |
+
"loss": 1.5492,
|
| 913 |
+
"step": 645
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.6996770721205597,
|
| 917 |
+
"grad_norm": 0.8828125,
|
| 918 |
+
"learning_rate": 0.00018230097961052658,
|
| 919 |
+
"loss": 1.8432,
|
| 920 |
+
"step": 650
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.7050592034445641,
|
| 924 |
+
"grad_norm": 0.8359375,
|
| 925 |
+
"learning_rate": 0.00018196245086084703,
|
| 926 |
+
"loss": 1.5463,
|
| 927 |
+
"step": 655
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.7104413347685683,
|
| 931 |
+
"grad_norm": 1.03125,
|
| 932 |
+
"learning_rate": 0.00018162103578415884,
|
| 933 |
+
"loss": 1.6883,
|
| 934 |
+
"step": 660
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.7158234660925726,
|
| 938 |
+
"grad_norm": 0.8515625,
|
| 939 |
+
"learning_rate": 0.0001812767464034743,
|
| 940 |
+
"loss": 1.5512,
|
| 941 |
+
"step": 665
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.721205597416577,
|
| 945 |
+
"grad_norm": 0.91796875,
|
| 946 |
+
"learning_rate": 0.00018092959484302515,
|
| 947 |
+
"loss": 1.387,
|
| 948 |
+
"step": 670
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.7265877287405813,
|
| 952 |
+
"grad_norm": 0.7421875,
|
| 953 |
+
"learning_rate": 0.00018057959332783518,
|
| 954 |
+
"loss": 1.2412,
|
| 955 |
+
"step": 675
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.7319698600645855,
|
| 959 |
+
"grad_norm": 0.6875,
|
| 960 |
+
"learning_rate": 0.0001802267541832903,
|
| 961 |
+
"loss": 1.4303,
|
| 962 |
+
"step": 680
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.7373519913885899,
|
| 966 |
+
"grad_norm": 1.359375,
|
| 967 |
+
"learning_rate": 0.00017987108983470403,
|
| 968 |
+
"loss": 1.9346,
|
| 969 |
+
"step": 685
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.7427341227125942,
|
| 973 |
+
"grad_norm": 1.890625,
|
| 974 |
+
"learning_rate": 0.0001795126128068801,
|
| 975 |
+
"loss": 1.5194,
|
| 976 |
+
"step": 690
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.7481162540365985,
|
| 980 |
+
"grad_norm": 1.1796875,
|
| 981 |
+
"learning_rate": 0.00017915133572367155,
|
| 982 |
+
"loss": 1.9612,
|
| 983 |
+
"step": 695
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.7534983853606028,
|
| 987 |
+
"grad_norm": 1.15625,
|
| 988 |
+
"learning_rate": 0.00017878727130753592,
|
| 989 |
+
"loss": 1.8595,
|
| 990 |
+
"step": 700
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.7588805166846071,
|
| 994 |
+
"grad_norm": 1.1640625,
|
| 995 |
+
"learning_rate": 0.00017842043237908733,
|
| 996 |
+
"loss": 1.4777,
|
| 997 |
+
"step": 705
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.7642626480086114,
|
| 1001 |
+
"grad_norm": 1.1171875,
|
| 1002 |
+
"learning_rate": 0.00017805083185664508,
|
| 1003 |
+
"loss": 1.6248,
|
| 1004 |
+
"step": 710
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.7696447793326158,
|
| 1008 |
+
"grad_norm": 0.82421875,
|
| 1009 |
+
"learning_rate": 0.00017767848275577856,
|
| 1010 |
+
"loss": 1.7387,
|
| 1011 |
+
"step": 715
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.77502691065662,
|
| 1015 |
+
"grad_norm": 0.83984375,
|
| 1016 |
+
"learning_rate": 0.0001773033981888491,
|
| 1017 |
+
"loss": 1.7641,
|
| 1018 |
+
"step": 720
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.7804090419806243,
|
| 1022 |
+
"grad_norm": 0.8359375,
|
| 1023 |
+
"learning_rate": 0.000176925591364548,
|
| 1024 |
+
"loss": 1.853,
|
| 1025 |
+
"step": 725
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.7857911733046287,
|
| 1029 |
+
"grad_norm": 1.046875,
|
| 1030 |
+
"learning_rate": 0.00017654507558743153,
|
| 1031 |
+
"loss": 1.3802,
|
| 1032 |
+
"step": 730
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.7911733046286329,
|
| 1036 |
+
"grad_norm": 0.87890625,
|
| 1037 |
+
"learning_rate": 0.00017616186425745248,
|
| 1038 |
+
"loss": 1.8941,
|
| 1039 |
+
"step": 735
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.7965554359526372,
|
| 1043 |
+
"grad_norm": 0.80078125,
|
| 1044 |
+
"learning_rate": 0.00017577597086948797,
|
| 1045 |
+
"loss": 1.6458,
|
| 1046 |
+
"step": 740
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.8019375672766416,
|
| 1050 |
+
"grad_norm": 1.0078125,
|
| 1051 |
+
"learning_rate": 0.00017538740901286464,
|
| 1052 |
+
"loss": 1.6792,
|
| 1053 |
+
"step": 745
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.8073196986006459,
|
| 1057 |
+
"grad_norm": 0.640625,
|
| 1058 |
+
"learning_rate": 0.00017499619237087969,
|
| 1059 |
+
"loss": 1.389,
|
| 1060 |
+
"step": 750
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.8127018299246501,
|
| 1064 |
+
"grad_norm": 1.015625,
|
| 1065 |
+
"learning_rate": 0.00017460233472031935,
|
| 1066 |
+
"loss": 2.0551,
|
| 1067 |
+
"step": 755
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.8180839612486545,
|
| 1071 |
+
"grad_norm": 1.0625,
|
| 1072 |
+
"learning_rate": 0.0001742058499309735,
|
| 1073 |
+
"loss": 1.6721,
|
| 1074 |
+
"step": 760
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.8234660925726588,
|
| 1078 |
+
"grad_norm": 0.83203125,
|
| 1079 |
+
"learning_rate": 0.00017380675196514739,
|
| 1080 |
+
"loss": 1.3685,
|
| 1081 |
+
"step": 765
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.8288482238966631,
|
| 1085 |
+
"grad_norm": 1.09375,
|
| 1086 |
+
"learning_rate": 0.00017340505487716985,
|
| 1087 |
+
"loss": 1.7255,
|
| 1088 |
+
"step": 770
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.8342303552206674,
|
| 1092 |
+
"grad_norm": 1.0546875,
|
| 1093 |
+
"learning_rate": 0.00017300077281289845,
|
| 1094 |
+
"loss": 1.5643,
|
| 1095 |
+
"step": 775
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.8396124865446717,
|
| 1099 |
+
"grad_norm": 0.8203125,
|
| 1100 |
+
"learning_rate": 0.00017259392000922125,
|
| 1101 |
+
"loss": 1.516,
|
| 1102 |
+
"step": 780
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.844994617868676,
|
| 1106 |
+
"grad_norm": 1.1328125,
|
| 1107 |
+
"learning_rate": 0.0001721845107935556,
|
| 1108 |
+
"loss": 1.6089,
|
| 1109 |
+
"step": 785
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.8503767491926802,
|
| 1113 |
+
"grad_norm": 0.67578125,
|
| 1114 |
+
"learning_rate": 0.00017177255958334342,
|
| 1115 |
+
"loss": 1.5203,
|
| 1116 |
+
"step": 790
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.8557588805166846,
|
| 1120 |
+
"grad_norm": 0.796875,
|
| 1121 |
+
"learning_rate": 0.00017135808088554358,
|
| 1122 |
+
"loss": 2.1079,
|
| 1123 |
+
"step": 795
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.8611410118406889,
|
| 1127 |
+
"grad_norm": 0.87890625,
|
| 1128 |
+
"learning_rate": 0.000170941089296121,
|
| 1129 |
+
"loss": 1.8979,
|
| 1130 |
+
"step": 800
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.8665231431646933,
|
| 1134 |
+
"grad_norm": 0.90625,
|
| 1135 |
+
"learning_rate": 0.00017052159949953278,
|
| 1136 |
+
"loss": 1.4225,
|
| 1137 |
+
"step": 805
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.8719052744886975,
|
| 1141 |
+
"grad_norm": 1.03125,
|
| 1142 |
+
"learning_rate": 0.00017009962626821082,
|
| 1143 |
+
"loss": 1.7616,
|
| 1144 |
+
"step": 810
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.8772874058127018,
|
| 1148 |
+
"grad_norm": 0.87890625,
|
| 1149 |
+
"learning_rate": 0.0001696751844620419,
|
| 1150 |
+
"loss": 1.8864,
|
| 1151 |
+
"step": 815
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.8826695371367062,
|
| 1155 |
+
"grad_norm": 1.234375,
|
| 1156 |
+
"learning_rate": 0.00016924828902784407,
|
| 1157 |
+
"loss": 1.6568,
|
| 1158 |
+
"step": 820
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.8880516684607105,
|
| 1162 |
+
"grad_norm": 0.8046875,
|
| 1163 |
+
"learning_rate": 0.00016881895499884072,
|
| 1164 |
+
"loss": 1.6826,
|
| 1165 |
+
"step": 825
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.8934337997847147,
|
| 1169 |
+
"grad_norm": 0.95703125,
|
| 1170 |
+
"learning_rate": 0.00016838719749413063,
|
| 1171 |
+
"loss": 1.3967,
|
| 1172 |
+
"step": 830
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.898815931108719,
|
| 1176 |
+
"grad_norm": 1.1953125,
|
| 1177 |
+
"learning_rate": 0.00016795303171815616,
|
| 1178 |
+
"loss": 1.7213,
|
| 1179 |
+
"step": 835
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.9041980624327234,
|
| 1183 |
+
"grad_norm": 0.8125,
|
| 1184 |
+
"learning_rate": 0.00016751647296016725,
|
| 1185 |
+
"loss": 1.6946,
|
| 1186 |
+
"step": 840
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.9095801937567277,
|
| 1190 |
+
"grad_norm": 0.71484375,
|
| 1191 |
+
"learning_rate": 0.00016707753659368337,
|
| 1192 |
+
"loss": 1.8869,
|
| 1193 |
+
"step": 845
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.9149623250807319,
|
| 1197 |
+
"grad_norm": 1.0,
|
| 1198 |
+
"learning_rate": 0.0001666362380759521,
|
| 1199 |
+
"loss": 1.5258,
|
| 1200 |
+
"step": 850
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.9203444564047363,
|
| 1204 |
+
"grad_norm": 1.28125,
|
| 1205 |
+
"learning_rate": 0.0001661925929474046,
|
| 1206 |
+
"loss": 1.8925,
|
| 1207 |
+
"step": 855
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.9257265877287406,
|
| 1211 |
+
"grad_norm": 0.84765625,
|
| 1212 |
+
"learning_rate": 0.00016574661683110858,
|
| 1213 |
+
"loss": 1.7461,
|
| 1214 |
+
"step": 860
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.9311087190527448,
|
| 1218 |
+
"grad_norm": 1.0546875,
|
| 1219 |
+
"learning_rate": 0.00016529832543221796,
|
| 1220 |
+
"loss": 1.6321,
|
| 1221 |
+
"step": 865
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.9364908503767492,
|
| 1225 |
+
"grad_norm": 0.83203125,
|
| 1226 |
+
"learning_rate": 0.00016484773453741999,
|
| 1227 |
+
"loss": 1.4394,
|
| 1228 |
+
"step": 870
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.9418729817007535,
|
| 1232 |
+
"grad_norm": 0.84375,
|
| 1233 |
+
"learning_rate": 0.0001643948600143791,
|
| 1234 |
+
"loss": 1.7612,
|
| 1235 |
+
"step": 875
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.9472551130247578,
|
| 1239 |
+
"grad_norm": 1.2890625,
|
| 1240 |
+
"learning_rate": 0.00016393971781117827,
|
| 1241 |
+
"loss": 1.5663,
|
| 1242 |
+
"step": 880
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.9526372443487621,
|
| 1246 |
+
"grad_norm": 0.9375,
|
| 1247 |
+
"learning_rate": 0.00016348232395575738,
|
| 1248 |
+
"loss": 1.6009,
|
| 1249 |
+
"step": 885
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.9580193756727664,
|
| 1253 |
+
"grad_norm": 0.796875,
|
| 1254 |
+
"learning_rate": 0.0001630226945553487,
|
| 1255 |
+
"loss": 1.5051,
|
| 1256 |
+
"step": 890
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.9634015069967707,
|
| 1260 |
+
"grad_norm": 0.58984375,
|
| 1261 |
+
"learning_rate": 0.00016256084579590991,
|
| 1262 |
+
"loss": 1.3798,
|
| 1263 |
+
"step": 895
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.9687836383207751,
|
| 1267 |
+
"grad_norm": 1.1328125,
|
| 1268 |
+
"learning_rate": 0.00016209679394155378,
|
| 1269 |
+
"loss": 1.542,
|
| 1270 |
+
"step": 900
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.9741657696447793,
|
| 1274 |
+
"grad_norm": 0.875,
|
| 1275 |
+
"learning_rate": 0.0001616305553339756,
|
| 1276 |
+
"loss": 1.7239,
|
| 1277 |
+
"step": 905
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.9795479009687836,
|
| 1281 |
+
"grad_norm": 1.0078125,
|
| 1282 |
+
"learning_rate": 0.0001611621463918778,
|
| 1283 |
+
"loss": 1.6649,
|
| 1284 |
+
"step": 910
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.984930032292788,
|
| 1288 |
+
"grad_norm": 0.91796875,
|
| 1289 |
+
"learning_rate": 0.0001606915836103916,
|
| 1290 |
+
"loss": 1.5315,
|
| 1291 |
+
"step": 915
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.9903121636167922,
|
| 1295 |
+
"grad_norm": 0.7734375,
|
| 1296 |
+
"learning_rate": 0.00016021888356049607,
|
| 1297 |
+
"loss": 1.6008,
|
| 1298 |
+
"step": 920
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.9956942949407965,
|
| 1302 |
+
"grad_norm": 0.875,
|
| 1303 |
+
"learning_rate": 0.00015974406288843485,
|
| 1304 |
+
"loss": 1.4304,
|
| 1305 |
+
"step": 925
|
| 1306 |
+
}
|
| 1307 |
+
],
|
| 1308 |
+
"logging_steps": 5,
|
| 1309 |
+
"max_steps": 2787,
|
| 1310 |
+
"num_input_tokens_seen": 0,
|
| 1311 |
+
"num_train_epochs": 3,
|
| 1312 |
+
"save_steps": 500,
|
| 1313 |
+
"stateful_callbacks": {
|
| 1314 |
+
"TrainerControl": {
|
| 1315 |
+
"args": {
|
| 1316 |
+
"should_epoch_stop": false,
|
| 1317 |
+
"should_evaluate": false,
|
| 1318 |
+
"should_log": false,
|
| 1319 |
+
"should_save": true,
|
| 1320 |
+
"should_training_stop": false
|
| 1321 |
+
},
|
| 1322 |
+
"attributes": {}
|
| 1323 |
+
}
|
| 1324 |
+
},
|
| 1325 |
+
"total_flos": 1.6830365703340032e+16,
|
| 1326 |
+
"train_batch_size": 16,
|
| 1327 |
+
"trial_name": null,
|
| 1328 |
+
"trial_params": null
|
| 1329 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f45de8282b4fbca08865798d8c57261d6ab5fc74da594198e13f7f4a749e00e2
|
| 3 |
+
size 5777
|