Upload 38 files
Browse files- chat_template.jinja +1 -0
- checkpoint-2900/chat_template.jinja +1 -0
- checkpoint-2900/config.json +37 -0
- checkpoint-2900/generation_config.json +6 -0
- checkpoint-2900/merges.txt +0 -0
- checkpoint-2900/model.safetensors +3 -0
- checkpoint-2900/optimizer.pt +3 -0
- checkpoint-2900/rng_state.pth +3 -0
- checkpoint-2900/scheduler.pt +3 -0
- checkpoint-2900/special_tokens_map.json +24 -0
- checkpoint-2900/tokenizer.json +0 -0
- checkpoint-2900/tokenizer_config.json +23 -0
- checkpoint-2900/trainer_state.json +2064 -0
- checkpoint-2900/training_args.bin +3 -0
- checkpoint-2900/vocab.json +0 -0
- checkpoint-3000/chat_template.jinja +1 -0
- checkpoint-3000/config.json +37 -0
- checkpoint-3000/generation_config.json +6 -0
- checkpoint-3000/merges.txt +0 -0
- checkpoint-3000/model.safetensors +3 -0
- checkpoint-3000/optimizer.pt +3 -0
- checkpoint-3000/rng_state.pth +3 -0
- checkpoint-3000/scheduler.pt +3 -0
- checkpoint-3000/special_tokens_map.json +24 -0
- checkpoint-3000/tokenizer.json +0 -0
- checkpoint-3000/tokenizer_config.json +23 -0
- checkpoint-3000/trainer_state.json +2134 -0
- checkpoint-3000/training_args.bin +3 -0
- checkpoint-3000/vocab.json +0 -0
- config.json +37 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +23 -0
- training_args.bin +3 -0
- vocab.json +0 -0
chat_template.jinja
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}
|
checkpoint-2900/chat_template.jinja
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}
|
checkpoint-2900/config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 50256,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 50256,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"layer_norm_epsilon": 1e-05,
|
| 12 |
+
"model_type": "gpt2",
|
| 13 |
+
"n_ctx": 1024,
|
| 14 |
+
"n_embd": 1024,
|
| 15 |
+
"n_head": 16,
|
| 16 |
+
"n_inner": null,
|
| 17 |
+
"n_layer": 24,
|
| 18 |
+
"n_positions": 1024,
|
| 19 |
+
"reorder_and_upcast_attn": false,
|
| 20 |
+
"resid_pdrop": 0.1,
|
| 21 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 22 |
+
"scale_attn_weights": true,
|
| 23 |
+
"summary_activation": null,
|
| 24 |
+
"summary_first_dropout": 0.1,
|
| 25 |
+
"summary_proj_to_labels": true,
|
| 26 |
+
"summary_type": "cls_index",
|
| 27 |
+
"summary_use_proj": true,
|
| 28 |
+
"task_specific_params": {
|
| 29 |
+
"conversational": {
|
| 30 |
+
"max_length": 1000
|
| 31 |
+
}
|
| 32 |
+
},
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.54.1",
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"vocab_size": 50257
|
| 37 |
+
}
|
checkpoint-2900/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.54.1"
|
| 6 |
+
}
|
checkpoint-2900/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2900/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa6e5bddf134327d22632c73a7f16e23f2e97d77538112eb292cecb29975b664
|
| 3 |
+
size 1419322880
|
checkpoint-2900/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a192d1421652ff3d90b09cdf325c3a8aab319cce976fac5c9baabe23178daad
|
| 3 |
+
size 2838821579
|
checkpoint-2900/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dba4fde4ee04d2f472bb4dea96a48e8fdf7891d2b0694a8f012e8133a2e176ae
|
| 3 |
+
size 14455
|
checkpoint-2900/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37f21d971adb59ae3c37fd575c2edb5190aed6c0d57807bd46ceb2e829ad7484
|
| 3 |
+
size 1465
|
checkpoint-2900/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|endoftext|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
checkpoint-2900/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2900/tokenizer_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"50256": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
}
|
| 13 |
+
},
|
| 14 |
+
"bos_token": "<|endoftext|>",
|
| 15 |
+
"clean_up_tokenization_spaces": true,
|
| 16 |
+
"eos_token": "<|endoftext|>",
|
| 17 |
+
"errors": "replace",
|
| 18 |
+
"extra_special_tokens": {},
|
| 19 |
+
"model_max_length": 1024,
|
| 20 |
+
"pad_token": "<|endoftext|>",
|
| 21 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 22 |
+
"unk_token": "<|endoftext|>"
|
| 23 |
+
}
|
checkpoint-2900/trainer_state.json
ADDED
|
@@ -0,0 +1,2064 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.9,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2900,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.01,
|
| 14 |
+
"grad_norm": 31.807226181030273,
|
| 15 |
+
"learning_rate": 4.5e-06,
|
| 16 |
+
"loss": 10.2322,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.02,
|
| 21 |
+
"grad_norm": 14.19406795501709,
|
| 22 |
+
"learning_rate": 9.5e-06,
|
| 23 |
+
"loss": 8.6686,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.03,
|
| 28 |
+
"grad_norm": 8.947138786315918,
|
| 29 |
+
"learning_rate": 1.45e-05,
|
| 30 |
+
"loss": 6.6091,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.04,
|
| 35 |
+
"grad_norm": 7.508649826049805,
|
| 36 |
+
"learning_rate": 1.9500000000000003e-05,
|
| 37 |
+
"loss": 5.1112,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.05,
|
| 42 |
+
"grad_norm": 5.768527030944824,
|
| 43 |
+
"learning_rate": 2.45e-05,
|
| 44 |
+
"loss": 4.4247,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.06,
|
| 49 |
+
"grad_norm": 5.962294578552246,
|
| 50 |
+
"learning_rate": 2.95e-05,
|
| 51 |
+
"loss": 3.7838,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.07,
|
| 56 |
+
"grad_norm": 7.343990802764893,
|
| 57 |
+
"learning_rate": 3.45e-05,
|
| 58 |
+
"loss": 3.3172,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.08,
|
| 63 |
+
"grad_norm": 5.001032829284668,
|
| 64 |
+
"learning_rate": 3.9500000000000005e-05,
|
| 65 |
+
"loss": 3.1734,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.09,
|
| 70 |
+
"grad_norm": 3.4707157611846924,
|
| 71 |
+
"learning_rate": 4.4500000000000004e-05,
|
| 72 |
+
"loss": 2.9784,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1,
|
| 77 |
+
"grad_norm": 4.321723461151123,
|
| 78 |
+
"learning_rate": 4.9500000000000004e-05,
|
| 79 |
+
"loss": 2.6301,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.11,
|
| 84 |
+
"grad_norm": 4.037026405334473,
|
| 85 |
+
"learning_rate": 4.98448275862069e-05,
|
| 86 |
+
"loss": 2.8441,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.12,
|
| 91 |
+
"grad_norm": 6.042785167694092,
|
| 92 |
+
"learning_rate": 4.967241379310345e-05,
|
| 93 |
+
"loss": 2.5558,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.13,
|
| 98 |
+
"grad_norm": 7.331098556518555,
|
| 99 |
+
"learning_rate": 4.9500000000000004e-05,
|
| 100 |
+
"loss": 2.5997,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.14,
|
| 105 |
+
"grad_norm": 5.285608291625977,
|
| 106 |
+
"learning_rate": 4.932758620689655e-05,
|
| 107 |
+
"loss": 2.3912,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.15,
|
| 112 |
+
"grad_norm": 5.633673191070557,
|
| 113 |
+
"learning_rate": 4.915517241379311e-05,
|
| 114 |
+
"loss": 2.3576,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.16,
|
| 119 |
+
"grad_norm": 5.462876796722412,
|
| 120 |
+
"learning_rate": 4.898275862068966e-05,
|
| 121 |
+
"loss": 2.3879,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.17,
|
| 126 |
+
"grad_norm": 5.2996015548706055,
|
| 127 |
+
"learning_rate": 4.8810344827586205e-05,
|
| 128 |
+
"loss": 2.6634,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.18,
|
| 133 |
+
"grad_norm": 4.960510730743408,
|
| 134 |
+
"learning_rate": 4.863793103448276e-05,
|
| 135 |
+
"loss": 2.3228,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.19,
|
| 140 |
+
"grad_norm": 5.18018913269043,
|
| 141 |
+
"learning_rate": 4.846551724137931e-05,
|
| 142 |
+
"loss": 2.4035,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.2,
|
| 147 |
+
"grad_norm": 3.5356884002685547,
|
| 148 |
+
"learning_rate": 4.8293103448275865e-05,
|
| 149 |
+
"loss": 1.9488,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.21,
|
| 154 |
+
"grad_norm": 2.8790781497955322,
|
| 155 |
+
"learning_rate": 4.812068965517242e-05,
|
| 156 |
+
"loss": 2.2974,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.22,
|
| 161 |
+
"grad_norm": 3.502866506576538,
|
| 162 |
+
"learning_rate": 4.794827586206897e-05,
|
| 163 |
+
"loss": 2.1646,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.23,
|
| 168 |
+
"grad_norm": 2.9694302082061768,
|
| 169 |
+
"learning_rate": 4.777586206896552e-05,
|
| 170 |
+
"loss": 2.1186,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.24,
|
| 175 |
+
"grad_norm": 2.986870050430298,
|
| 176 |
+
"learning_rate": 4.7603448275862073e-05,
|
| 177 |
+
"loss": 2.1907,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.25,
|
| 182 |
+
"grad_norm": 7.217125415802002,
|
| 183 |
+
"learning_rate": 4.743103448275862e-05,
|
| 184 |
+
"loss": 2.0278,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.26,
|
| 189 |
+
"grad_norm": 2.887138843536377,
|
| 190 |
+
"learning_rate": 4.725862068965518e-05,
|
| 191 |
+
"loss": 2.269,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.27,
|
| 196 |
+
"grad_norm": 14.621356964111328,
|
| 197 |
+
"learning_rate": 4.7086206896551726e-05,
|
| 198 |
+
"loss": 2.0509,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.28,
|
| 203 |
+
"grad_norm": 2.5131711959838867,
|
| 204 |
+
"learning_rate": 4.6913793103448275e-05,
|
| 205 |
+
"loss": 2.2239,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.29,
|
| 210 |
+
"grad_norm": 4.753391265869141,
|
| 211 |
+
"learning_rate": 4.674137931034483e-05,
|
| 212 |
+
"loss": 2.0629,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.3,
|
| 217 |
+
"grad_norm": 4.106902599334717,
|
| 218 |
+
"learning_rate": 4.656896551724138e-05,
|
| 219 |
+
"loss": 2.0625,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.31,
|
| 224 |
+
"grad_norm": 4.522510528564453,
|
| 225 |
+
"learning_rate": 4.6396551724137935e-05,
|
| 226 |
+
"loss": 1.9146,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.32,
|
| 231 |
+
"grad_norm": 3.454258441925049,
|
| 232 |
+
"learning_rate": 4.622413793103448e-05,
|
| 233 |
+
"loss": 1.7679,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.33,
|
| 238 |
+
"grad_norm": 12.172571182250977,
|
| 239 |
+
"learning_rate": 4.605172413793103e-05,
|
| 240 |
+
"loss": 1.762,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.34,
|
| 245 |
+
"grad_norm": 5.5643630027771,
|
| 246 |
+
"learning_rate": 4.587931034482759e-05,
|
| 247 |
+
"loss": 1.9651,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.35,
|
| 252 |
+
"grad_norm": 5.371229648590088,
|
| 253 |
+
"learning_rate": 4.5706896551724136e-05,
|
| 254 |
+
"loss": 2.1326,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.36,
|
| 259 |
+
"grad_norm": 2.6412742137908936,
|
| 260 |
+
"learning_rate": 4.553448275862069e-05,
|
| 261 |
+
"loss": 1.955,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.37,
|
| 266 |
+
"grad_norm": 5.9563775062561035,
|
| 267 |
+
"learning_rate": 4.536206896551725e-05,
|
| 268 |
+
"loss": 1.8654,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.38,
|
| 273 |
+
"grad_norm": 5.498210906982422,
|
| 274 |
+
"learning_rate": 4.5189655172413796e-05,
|
| 275 |
+
"loss": 2.0221,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.39,
|
| 280 |
+
"grad_norm": 1.9855848550796509,
|
| 281 |
+
"learning_rate": 4.501724137931035e-05,
|
| 282 |
+
"loss": 1.9202,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.4,
|
| 287 |
+
"grad_norm": 6.402889728546143,
|
| 288 |
+
"learning_rate": 4.48448275862069e-05,
|
| 289 |
+
"loss": 1.6582,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.41,
|
| 294 |
+
"grad_norm": 1.9488422870635986,
|
| 295 |
+
"learning_rate": 4.467241379310345e-05,
|
| 296 |
+
"loss": 1.9576,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.42,
|
| 301 |
+
"grad_norm": 1.99562406539917,
|
| 302 |
+
"learning_rate": 4.4500000000000004e-05,
|
| 303 |
+
"loss": 1.6823,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.43,
|
| 308 |
+
"grad_norm": 3.2172203063964844,
|
| 309 |
+
"learning_rate": 4.432758620689655e-05,
|
| 310 |
+
"loss": 1.7448,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.44,
|
| 315 |
+
"grad_norm": 1.7004073858261108,
|
| 316 |
+
"learning_rate": 4.415517241379311e-05,
|
| 317 |
+
"loss": 1.687,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.45,
|
| 322 |
+
"grad_norm": 2.6527938842773438,
|
| 323 |
+
"learning_rate": 4.398275862068966e-05,
|
| 324 |
+
"loss": 1.6152,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.46,
|
| 329 |
+
"grad_norm": 2.223691463470459,
|
| 330 |
+
"learning_rate": 4.3810344827586206e-05,
|
| 331 |
+
"loss": 1.7911,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.47,
|
| 336 |
+
"grad_norm": 2.228793144226074,
|
| 337 |
+
"learning_rate": 4.363793103448276e-05,
|
| 338 |
+
"loss": 1.9451,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.48,
|
| 343 |
+
"grad_norm": 2.724231243133545,
|
| 344 |
+
"learning_rate": 4.346551724137931e-05,
|
| 345 |
+
"loss": 1.791,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.49,
|
| 350 |
+
"grad_norm": 3.219877243041992,
|
| 351 |
+
"learning_rate": 4.3293103448275865e-05,
|
| 352 |
+
"loss": 1.692,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.5,
|
| 357 |
+
"grad_norm": 2.977465867996216,
|
| 358 |
+
"learning_rate": 4.3120689655172414e-05,
|
| 359 |
+
"loss": 1.886,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.51,
|
| 364 |
+
"grad_norm": 2.566962242126465,
|
| 365 |
+
"learning_rate": 4.294827586206896e-05,
|
| 366 |
+
"loss": 1.802,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.52,
|
| 371 |
+
"grad_norm": 3.129835844039917,
|
| 372 |
+
"learning_rate": 4.2775862068965525e-05,
|
| 373 |
+
"loss": 1.659,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.53,
|
| 378 |
+
"grad_norm": 3.913256883621216,
|
| 379 |
+
"learning_rate": 4.2603448275862074e-05,
|
| 380 |
+
"loss": 1.5919,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.54,
|
| 385 |
+
"grad_norm": 1.7998114824295044,
|
| 386 |
+
"learning_rate": 4.243103448275862e-05,
|
| 387 |
+
"loss": 1.7564,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.55,
|
| 392 |
+
"grad_norm": 2.310154676437378,
|
| 393 |
+
"learning_rate": 4.225862068965518e-05,
|
| 394 |
+
"loss": 1.7347,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.56,
|
| 399 |
+
"grad_norm": 1.835707426071167,
|
| 400 |
+
"learning_rate": 4.208620689655173e-05,
|
| 401 |
+
"loss": 1.802,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.57,
|
| 406 |
+
"grad_norm": 1.9488534927368164,
|
| 407 |
+
"learning_rate": 4.191379310344828e-05,
|
| 408 |
+
"loss": 1.9981,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.58,
|
| 413 |
+
"grad_norm": 5.861155986785889,
|
| 414 |
+
"learning_rate": 4.174137931034483e-05,
|
| 415 |
+
"loss": 1.9519,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.59,
|
| 420 |
+
"grad_norm": 2.403691053390503,
|
| 421 |
+
"learning_rate": 4.156896551724138e-05,
|
| 422 |
+
"loss": 1.6711,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.6,
|
| 427 |
+
"grad_norm": 1.9013047218322754,
|
| 428 |
+
"learning_rate": 4.1396551724137935e-05,
|
| 429 |
+
"loss": 1.6679,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.61,
|
| 434 |
+
"grad_norm": 2.6646413803100586,
|
| 435 |
+
"learning_rate": 4.1224137931034484e-05,
|
| 436 |
+
"loss": 1.7117,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.62,
|
| 441 |
+
"grad_norm": 2.6011579036712646,
|
| 442 |
+
"learning_rate": 4.105172413793103e-05,
|
| 443 |
+
"loss": 1.6351,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.63,
|
| 448 |
+
"grad_norm": 1.9296406507492065,
|
| 449 |
+
"learning_rate": 4.087931034482759e-05,
|
| 450 |
+
"loss": 1.8179,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.64,
|
| 455 |
+
"grad_norm": 2.2965588569641113,
|
| 456 |
+
"learning_rate": 4.070689655172414e-05,
|
| 457 |
+
"loss": 1.7164,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.65,
|
| 462 |
+
"grad_norm": 1.7480602264404297,
|
| 463 |
+
"learning_rate": 4.053448275862069e-05,
|
| 464 |
+
"loss": 1.5552,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.66,
|
| 469 |
+
"grad_norm": 2.9659781455993652,
|
| 470 |
+
"learning_rate": 4.036206896551724e-05,
|
| 471 |
+
"loss": 1.79,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.67,
|
| 476 |
+
"grad_norm": 1.5911238193511963,
|
| 477 |
+
"learning_rate": 4.018965517241379e-05,
|
| 478 |
+
"loss": 1.7139,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.68,
|
| 483 |
+
"grad_norm": 1.8339680433273315,
|
| 484 |
+
"learning_rate": 4.0017241379310345e-05,
|
| 485 |
+
"loss": 1.6479,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.69,
|
| 490 |
+
"grad_norm": 1.8804699182510376,
|
| 491 |
+
"learning_rate": 3.98448275862069e-05,
|
| 492 |
+
"loss": 1.6501,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.7,
|
| 497 |
+
"grad_norm": 5.505954742431641,
|
| 498 |
+
"learning_rate": 3.967241379310345e-05,
|
| 499 |
+
"loss": 1.549,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.71,
|
| 504 |
+
"grad_norm": 3.225405693054199,
|
| 505 |
+
"learning_rate": 3.9500000000000005e-05,
|
| 506 |
+
"loss": 1.5231,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.72,
|
| 511 |
+
"grad_norm": 2.4233756065368652,
|
| 512 |
+
"learning_rate": 3.932758620689655e-05,
|
| 513 |
+
"loss": 1.5577,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.73,
|
| 518 |
+
"grad_norm": 1.9218379259109497,
|
| 519 |
+
"learning_rate": 3.915517241379311e-05,
|
| 520 |
+
"loss": 1.8394,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.74,
|
| 525 |
+
"grad_norm": 1.7937753200531006,
|
| 526 |
+
"learning_rate": 3.898275862068966e-05,
|
| 527 |
+
"loss": 1.4735,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.75,
|
| 532 |
+
"grad_norm": 2.696561336517334,
|
| 533 |
+
"learning_rate": 3.8810344827586206e-05,
|
| 534 |
+
"loss": 1.7371,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.76,
|
| 539 |
+
"grad_norm": 1.6280263662338257,
|
| 540 |
+
"learning_rate": 3.863793103448276e-05,
|
| 541 |
+
"loss": 1.6161,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.77,
|
| 546 |
+
"grad_norm": 1.7006651163101196,
|
| 547 |
+
"learning_rate": 3.846551724137931e-05,
|
| 548 |
+
"loss": 1.4593,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.78,
|
| 553 |
+
"grad_norm": 3.765646457672119,
|
| 554 |
+
"learning_rate": 3.8293103448275866e-05,
|
| 555 |
+
"loss": 1.5506,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.79,
|
| 560 |
+
"grad_norm": 2.9314448833465576,
|
| 561 |
+
"learning_rate": 3.8120689655172415e-05,
|
| 562 |
+
"loss": 1.5805,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.8,
|
| 567 |
+
"grad_norm": 1.736654281616211,
|
| 568 |
+
"learning_rate": 3.794827586206896e-05,
|
| 569 |
+
"loss": 1.5675,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.81,
|
| 574 |
+
"grad_norm": 2.3542542457580566,
|
| 575 |
+
"learning_rate": 3.777586206896552e-05,
|
| 576 |
+
"loss": 1.5955,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.82,
|
| 581 |
+
"grad_norm": 2.1898491382598877,
|
| 582 |
+
"learning_rate": 3.760344827586207e-05,
|
| 583 |
+
"loss": 1.3708,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.83,
|
| 588 |
+
"grad_norm": 2.2105820178985596,
|
| 589 |
+
"learning_rate": 3.743103448275862e-05,
|
| 590 |
+
"loss": 1.6554,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.84,
|
| 595 |
+
"grad_norm": 4.901267051696777,
|
| 596 |
+
"learning_rate": 3.725862068965517e-05,
|
| 597 |
+
"loss": 1.3071,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.85,
|
| 602 |
+
"grad_norm": 1.991741418838501,
|
| 603 |
+
"learning_rate": 3.708620689655173e-05,
|
| 604 |
+
"loss": 1.3876,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.86,
|
| 609 |
+
"grad_norm": 2.1567299365997314,
|
| 610 |
+
"learning_rate": 3.691379310344828e-05,
|
| 611 |
+
"loss": 1.5718,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.87,
|
| 616 |
+
"grad_norm": 1.741442084312439,
|
| 617 |
+
"learning_rate": 3.674137931034483e-05,
|
| 618 |
+
"loss": 1.3982,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.88,
|
| 623 |
+
"grad_norm": 2.704728364944458,
|
| 624 |
+
"learning_rate": 3.656896551724138e-05,
|
| 625 |
+
"loss": 1.3117,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.89,
|
| 630 |
+
"grad_norm": 1.5768979787826538,
|
| 631 |
+
"learning_rate": 3.6396551724137936e-05,
|
| 632 |
+
"loss": 1.6102,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.9,
|
| 637 |
+
"grad_norm": 1.6916723251342773,
|
| 638 |
+
"learning_rate": 3.6224137931034484e-05,
|
| 639 |
+
"loss": 1.6576,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.91,
|
| 644 |
+
"grad_norm": 2.1157259941101074,
|
| 645 |
+
"learning_rate": 3.605172413793104e-05,
|
| 646 |
+
"loss": 1.4144,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.92,
|
| 651 |
+
"grad_norm": 1.7090058326721191,
|
| 652 |
+
"learning_rate": 3.587931034482759e-05,
|
| 653 |
+
"loss": 1.3267,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.93,
|
| 658 |
+
"grad_norm": 2.5148727893829346,
|
| 659 |
+
"learning_rate": 3.570689655172414e-05,
|
| 660 |
+
"loss": 1.7362,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.94,
|
| 665 |
+
"grad_norm": 2.4861910343170166,
|
| 666 |
+
"learning_rate": 3.553448275862069e-05,
|
| 667 |
+
"loss": 1.4764,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.95,
|
| 672 |
+
"grad_norm": 1.909857988357544,
|
| 673 |
+
"learning_rate": 3.536206896551724e-05,
|
| 674 |
+
"loss": 1.8828,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.96,
|
| 679 |
+
"grad_norm": 1.5957543849945068,
|
| 680 |
+
"learning_rate": 3.51896551724138e-05,
|
| 681 |
+
"loss": 1.4019,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.97,
|
| 686 |
+
"grad_norm": 2.6423611640930176,
|
| 687 |
+
"learning_rate": 3.5017241379310345e-05,
|
| 688 |
+
"loss": 1.2464,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.98,
|
| 693 |
+
"grad_norm": 1.7054439783096313,
|
| 694 |
+
"learning_rate": 3.4844827586206894e-05,
|
| 695 |
+
"loss": 1.3908,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.99,
|
| 700 |
+
"grad_norm": 1.5509027242660522,
|
| 701 |
+
"learning_rate": 3.467241379310345e-05,
|
| 702 |
+
"loss": 1.6855,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.0,
|
| 707 |
+
"grad_norm": 2.0527048110961914,
|
| 708 |
+
"learning_rate": 3.45e-05,
|
| 709 |
+
"loss": 1.41,
|
| 710 |
+
"step": 1000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.01,
|
| 714 |
+
"grad_norm": 1.912597417831421,
|
| 715 |
+
"learning_rate": 3.4327586206896554e-05,
|
| 716 |
+
"loss": 1.696,
|
| 717 |
+
"step": 1010
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.02,
|
| 721 |
+
"grad_norm": 2.4118075370788574,
|
| 722 |
+
"learning_rate": 3.415517241379311e-05,
|
| 723 |
+
"loss": 1.4162,
|
| 724 |
+
"step": 1020
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.03,
|
| 728 |
+
"grad_norm": 1.8533530235290527,
|
| 729 |
+
"learning_rate": 3.398275862068966e-05,
|
| 730 |
+
"loss": 1.3809,
|
| 731 |
+
"step": 1030
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.04,
|
| 735 |
+
"grad_norm": 1.950042724609375,
|
| 736 |
+
"learning_rate": 3.381034482758621e-05,
|
| 737 |
+
"loss": 1.3845,
|
| 738 |
+
"step": 1040
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.05,
|
| 742 |
+
"grad_norm": 2.852569341659546,
|
| 743 |
+
"learning_rate": 3.363793103448276e-05,
|
| 744 |
+
"loss": 1.3189,
|
| 745 |
+
"step": 1050
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.06,
|
| 749 |
+
"grad_norm": 1.6454888582229614,
|
| 750 |
+
"learning_rate": 3.346551724137931e-05,
|
| 751 |
+
"loss": 1.4498,
|
| 752 |
+
"step": 1060
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.07,
|
| 756 |
+
"grad_norm": 2.481353759765625,
|
| 757 |
+
"learning_rate": 3.3293103448275866e-05,
|
| 758 |
+
"loss": 1.4578,
|
| 759 |
+
"step": 1070
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.08,
|
| 763 |
+
"grad_norm": 2.739814519882202,
|
| 764 |
+
"learning_rate": 3.3120689655172415e-05,
|
| 765 |
+
"loss": 1.4949,
|
| 766 |
+
"step": 1080
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.09,
|
| 770 |
+
"grad_norm": 2.799699068069458,
|
| 771 |
+
"learning_rate": 3.2948275862068964e-05,
|
| 772 |
+
"loss": 1.1835,
|
| 773 |
+
"step": 1090
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.1,
|
| 777 |
+
"grad_norm": 1.6168289184570312,
|
| 778 |
+
"learning_rate": 3.277586206896552e-05,
|
| 779 |
+
"loss": 1.4057,
|
| 780 |
+
"step": 1100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.11,
|
| 784 |
+
"grad_norm": 3.1404354572296143,
|
| 785 |
+
"learning_rate": 3.260344827586207e-05,
|
| 786 |
+
"loss": 1.2438,
|
| 787 |
+
"step": 1110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.12,
|
| 791 |
+
"grad_norm": 2.4057466983795166,
|
| 792 |
+
"learning_rate": 3.2431034482758623e-05,
|
| 793 |
+
"loss": 1.5332,
|
| 794 |
+
"step": 1120
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.13,
|
| 798 |
+
"grad_norm": 1.1605113744735718,
|
| 799 |
+
"learning_rate": 3.225862068965517e-05,
|
| 800 |
+
"loss": 1.3803,
|
| 801 |
+
"step": 1130
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.1400000000000001,
|
| 805 |
+
"grad_norm": 2.467651605606079,
|
| 806 |
+
"learning_rate": 3.208620689655172e-05,
|
| 807 |
+
"loss": 1.3769,
|
| 808 |
+
"step": 1140
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.15,
|
| 812 |
+
"grad_norm": 2.0736987590789795,
|
| 813 |
+
"learning_rate": 3.1913793103448276e-05,
|
| 814 |
+
"loss": 1.4032,
|
| 815 |
+
"step": 1150
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.16,
|
| 819 |
+
"grad_norm": 2.9988651275634766,
|
| 820 |
+
"learning_rate": 3.1741379310344825e-05,
|
| 821 |
+
"loss": 1.4226,
|
| 822 |
+
"step": 1160
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.17,
|
| 826 |
+
"grad_norm": 2.2302157878875732,
|
| 827 |
+
"learning_rate": 3.156896551724138e-05,
|
| 828 |
+
"loss": 1.5159,
|
| 829 |
+
"step": 1170
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.18,
|
| 833 |
+
"grad_norm": 1.2775397300720215,
|
| 834 |
+
"learning_rate": 3.1396551724137936e-05,
|
| 835 |
+
"loss": 1.2539,
|
| 836 |
+
"step": 1180
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.19,
|
| 840 |
+
"grad_norm": 3.2107908725738525,
|
| 841 |
+
"learning_rate": 3.1224137931034485e-05,
|
| 842 |
+
"loss": 1.3425,
|
| 843 |
+
"step": 1190
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.2,
|
| 847 |
+
"grad_norm": 1.783532977104187,
|
| 848 |
+
"learning_rate": 3.105172413793104e-05,
|
| 849 |
+
"loss": 1.2874,
|
| 850 |
+
"step": 1200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.21,
|
| 854 |
+
"grad_norm": 2.1126065254211426,
|
| 855 |
+
"learning_rate": 3.087931034482759e-05,
|
| 856 |
+
"loss": 1.5065,
|
| 857 |
+
"step": 1210
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.22,
|
| 861 |
+
"grad_norm": 2.010965347290039,
|
| 862 |
+
"learning_rate": 3.070689655172414e-05,
|
| 863 |
+
"loss": 1.3932,
|
| 864 |
+
"step": 1220
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.23,
|
| 868 |
+
"grad_norm": 5.611945152282715,
|
| 869 |
+
"learning_rate": 3.053448275862069e-05,
|
| 870 |
+
"loss": 1.4646,
|
| 871 |
+
"step": 1230
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.24,
|
| 875 |
+
"grad_norm": 1.9755380153656006,
|
| 876 |
+
"learning_rate": 3.0362068965517242e-05,
|
| 877 |
+
"loss": 1.1764,
|
| 878 |
+
"step": 1240
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.25,
|
| 882 |
+
"grad_norm": 2.106905221939087,
|
| 883 |
+
"learning_rate": 3.0189655172413794e-05,
|
| 884 |
+
"loss": 1.3547,
|
| 885 |
+
"step": 1250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.26,
|
| 889 |
+
"grad_norm": 1.7636513710021973,
|
| 890 |
+
"learning_rate": 3.0017241379310346e-05,
|
| 891 |
+
"loss": 1.2024,
|
| 892 |
+
"step": 1260
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.27,
|
| 896 |
+
"grad_norm": 2.3909709453582764,
|
| 897 |
+
"learning_rate": 2.9844827586206898e-05,
|
| 898 |
+
"loss": 1.2256,
|
| 899 |
+
"step": 1270
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.28,
|
| 903 |
+
"grad_norm": 1.8174681663513184,
|
| 904 |
+
"learning_rate": 2.967241379310345e-05,
|
| 905 |
+
"loss": 1.4106,
|
| 906 |
+
"step": 1280
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.29,
|
| 910 |
+
"grad_norm": 1.857674241065979,
|
| 911 |
+
"learning_rate": 2.95e-05,
|
| 912 |
+
"loss": 1.1851,
|
| 913 |
+
"step": 1290
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.3,
|
| 917 |
+
"grad_norm": 1.9900033473968506,
|
| 918 |
+
"learning_rate": 2.932758620689655e-05,
|
| 919 |
+
"loss": 1.2333,
|
| 920 |
+
"step": 1300
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.31,
|
| 924 |
+
"grad_norm": 1.5615085363388062,
|
| 925 |
+
"learning_rate": 2.9155172413793103e-05,
|
| 926 |
+
"loss": 1.3969,
|
| 927 |
+
"step": 1310
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.32,
|
| 931 |
+
"grad_norm": 1.7219326496124268,
|
| 932 |
+
"learning_rate": 2.8982758620689655e-05,
|
| 933 |
+
"loss": 1.2629,
|
| 934 |
+
"step": 1320
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.33,
|
| 938 |
+
"grad_norm": 1.7303168773651123,
|
| 939 |
+
"learning_rate": 2.881034482758621e-05,
|
| 940 |
+
"loss": 1.4391,
|
| 941 |
+
"step": 1330
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.34,
|
| 945 |
+
"grad_norm": 1.7237037420272827,
|
| 946 |
+
"learning_rate": 2.8637931034482763e-05,
|
| 947 |
+
"loss": 1.3606,
|
| 948 |
+
"step": 1340
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.35,
|
| 952 |
+
"grad_norm": 1.575646162033081,
|
| 953 |
+
"learning_rate": 2.8465517241379315e-05,
|
| 954 |
+
"loss": 1.1907,
|
| 955 |
+
"step": 1350
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.3599999999999999,
|
| 959 |
+
"grad_norm": 2.1866729259490967,
|
| 960 |
+
"learning_rate": 2.8293103448275863e-05,
|
| 961 |
+
"loss": 1.3406,
|
| 962 |
+
"step": 1360
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.37,
|
| 966 |
+
"grad_norm": 1.5900951623916626,
|
| 967 |
+
"learning_rate": 2.8120689655172415e-05,
|
| 968 |
+
"loss": 1.3234,
|
| 969 |
+
"step": 1370
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.38,
|
| 973 |
+
"grad_norm": 2.729886293411255,
|
| 974 |
+
"learning_rate": 2.7948275862068968e-05,
|
| 975 |
+
"loss": 1.3068,
|
| 976 |
+
"step": 1380
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.3900000000000001,
|
| 980 |
+
"grad_norm": 7.489139556884766,
|
| 981 |
+
"learning_rate": 2.777586206896552e-05,
|
| 982 |
+
"loss": 1.2874,
|
| 983 |
+
"step": 1390
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.4,
|
| 987 |
+
"grad_norm": 1.6766670942306519,
|
| 988 |
+
"learning_rate": 2.7603448275862072e-05,
|
| 989 |
+
"loss": 1.369,
|
| 990 |
+
"step": 1400
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.41,
|
| 994 |
+
"grad_norm": 1.6040589809417725,
|
| 995 |
+
"learning_rate": 2.743103448275862e-05,
|
| 996 |
+
"loss": 1.4296,
|
| 997 |
+
"step": 1410
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.42,
|
| 1001 |
+
"grad_norm": 2.0411570072174072,
|
| 1002 |
+
"learning_rate": 2.7258620689655173e-05,
|
| 1003 |
+
"loss": 1.2803,
|
| 1004 |
+
"step": 1420
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.43,
|
| 1008 |
+
"grad_norm": 2.604081869125366,
|
| 1009 |
+
"learning_rate": 2.7086206896551725e-05,
|
| 1010 |
+
"loss": 1.2784,
|
| 1011 |
+
"step": 1430
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.44,
|
| 1015 |
+
"grad_norm": 1.4787765741348267,
|
| 1016 |
+
"learning_rate": 2.6913793103448277e-05,
|
| 1017 |
+
"loss": 1.3021,
|
| 1018 |
+
"step": 1440
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.45,
|
| 1022 |
+
"grad_norm": 1.665315866470337,
|
| 1023 |
+
"learning_rate": 2.674137931034483e-05,
|
| 1024 |
+
"loss": 1.1502,
|
| 1025 |
+
"step": 1450
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.46,
|
| 1029 |
+
"grad_norm": 2.4420969486236572,
|
| 1030 |
+
"learning_rate": 2.6568965517241378e-05,
|
| 1031 |
+
"loss": 1.3531,
|
| 1032 |
+
"step": 1460
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.47,
|
| 1036 |
+
"grad_norm": 1.961679220199585,
|
| 1037 |
+
"learning_rate": 2.639655172413793e-05,
|
| 1038 |
+
"loss": 1.413,
|
| 1039 |
+
"step": 1470
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.48,
|
| 1043 |
+
"grad_norm": 1.6548084020614624,
|
| 1044 |
+
"learning_rate": 2.6224137931034482e-05,
|
| 1045 |
+
"loss": 1.2579,
|
| 1046 |
+
"step": 1480
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.49,
|
| 1050 |
+
"grad_norm": 1.22232985496521,
|
| 1051 |
+
"learning_rate": 2.6051724137931037e-05,
|
| 1052 |
+
"loss": 1.4794,
|
| 1053 |
+
"step": 1490
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.5,
|
| 1057 |
+
"grad_norm": 2.133786916732788,
|
| 1058 |
+
"learning_rate": 2.587931034482759e-05,
|
| 1059 |
+
"loss": 1.4226,
|
| 1060 |
+
"step": 1500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.51,
|
| 1064 |
+
"grad_norm": 1.7223315238952637,
|
| 1065 |
+
"learning_rate": 2.570689655172414e-05,
|
| 1066 |
+
"loss": 1.3799,
|
| 1067 |
+
"step": 1510
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.52,
|
| 1071 |
+
"grad_norm": 2.187749147415161,
|
| 1072 |
+
"learning_rate": 2.5534482758620693e-05,
|
| 1073 |
+
"loss": 1.3415,
|
| 1074 |
+
"step": 1520
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.53,
|
| 1078 |
+
"grad_norm": 1.8895548582077026,
|
| 1079 |
+
"learning_rate": 2.5362068965517246e-05,
|
| 1080 |
+
"loss": 1.2736,
|
| 1081 |
+
"step": 1530
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.54,
|
| 1085 |
+
"grad_norm": 2.2825796604156494,
|
| 1086 |
+
"learning_rate": 2.5189655172413794e-05,
|
| 1087 |
+
"loss": 1.4374,
|
| 1088 |
+
"step": 1540
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.55,
|
| 1092 |
+
"grad_norm": 1.5137097835540771,
|
| 1093 |
+
"learning_rate": 2.5017241379310346e-05,
|
| 1094 |
+
"loss": 1.1751,
|
| 1095 |
+
"step": 1550
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.56,
|
| 1099 |
+
"grad_norm": 1.8762792348861694,
|
| 1100 |
+
"learning_rate": 2.48448275862069e-05,
|
| 1101 |
+
"loss": 1.2994,
|
| 1102 |
+
"step": 1560
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.5699999999999998,
|
| 1106 |
+
"grad_norm": 1.4601935148239136,
|
| 1107 |
+
"learning_rate": 2.467241379310345e-05,
|
| 1108 |
+
"loss": 1.6414,
|
| 1109 |
+
"step": 1570
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.58,
|
| 1113 |
+
"grad_norm": 1.7618972063064575,
|
| 1114 |
+
"learning_rate": 2.45e-05,
|
| 1115 |
+
"loss": 1.3107,
|
| 1116 |
+
"step": 1580
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.5899999999999999,
|
| 1120 |
+
"grad_norm": 3.77205753326416,
|
| 1121 |
+
"learning_rate": 2.432758620689655e-05,
|
| 1122 |
+
"loss": 1.4596,
|
| 1123 |
+
"step": 1590
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.6,
|
| 1127 |
+
"grad_norm": 1.3197537660598755,
|
| 1128 |
+
"learning_rate": 2.4155172413793103e-05,
|
| 1129 |
+
"loss": 1.2752,
|
| 1130 |
+
"step": 1600
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.6099999999999999,
|
| 1134 |
+
"grad_norm": 1.2479321956634521,
|
| 1135 |
+
"learning_rate": 2.398275862068966e-05,
|
| 1136 |
+
"loss": 1.2671,
|
| 1137 |
+
"step": 1610
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.62,
|
| 1141 |
+
"grad_norm": 1.6044553518295288,
|
| 1142 |
+
"learning_rate": 2.3810344827586208e-05,
|
| 1143 |
+
"loss": 1.4017,
|
| 1144 |
+
"step": 1620
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.63,
|
| 1148 |
+
"grad_norm": 1.746628999710083,
|
| 1149 |
+
"learning_rate": 2.363793103448276e-05,
|
| 1150 |
+
"loss": 1.1989,
|
| 1151 |
+
"step": 1630
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.6400000000000001,
|
| 1155 |
+
"grad_norm": 1.4533942937850952,
|
| 1156 |
+
"learning_rate": 2.3465517241379312e-05,
|
| 1157 |
+
"loss": 1.3846,
|
| 1158 |
+
"step": 1640
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.65,
|
| 1162 |
+
"grad_norm": 1.4432073831558228,
|
| 1163 |
+
"learning_rate": 2.3293103448275864e-05,
|
| 1164 |
+
"loss": 1.385,
|
| 1165 |
+
"step": 1650
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.6600000000000001,
|
| 1169 |
+
"grad_norm": 1.7605477571487427,
|
| 1170 |
+
"learning_rate": 2.3120689655172416e-05,
|
| 1171 |
+
"loss": 1.3516,
|
| 1172 |
+
"step": 1660
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.67,
|
| 1176 |
+
"grad_norm": 2.024019718170166,
|
| 1177 |
+
"learning_rate": 2.2948275862068965e-05,
|
| 1178 |
+
"loss": 1.2414,
|
| 1179 |
+
"step": 1670
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.6800000000000002,
|
| 1183 |
+
"grad_norm": 1.9421080350875854,
|
| 1184 |
+
"learning_rate": 2.2775862068965517e-05,
|
| 1185 |
+
"loss": 1.3778,
|
| 1186 |
+
"step": 1680
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.69,
|
| 1190 |
+
"grad_norm": 2.7231059074401855,
|
| 1191 |
+
"learning_rate": 2.2603448275862072e-05,
|
| 1192 |
+
"loss": 1.3709,
|
| 1193 |
+
"step": 1690
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.7,
|
| 1197 |
+
"grad_norm": 4.394734859466553,
|
| 1198 |
+
"learning_rate": 2.2431034482758624e-05,
|
| 1199 |
+
"loss": 1.0418,
|
| 1200 |
+
"step": 1700
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.71,
|
| 1204 |
+
"grad_norm": 1.7055786848068237,
|
| 1205 |
+
"learning_rate": 2.2258620689655173e-05,
|
| 1206 |
+
"loss": 1.3787,
|
| 1207 |
+
"step": 1710
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.72,
|
| 1211 |
+
"grad_norm": 2.871880292892456,
|
| 1212 |
+
"learning_rate": 2.2086206896551725e-05,
|
| 1213 |
+
"loss": 1.2104,
|
| 1214 |
+
"step": 1720
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.73,
|
| 1218 |
+
"grad_norm": 1.9549953937530518,
|
| 1219 |
+
"learning_rate": 2.1913793103448277e-05,
|
| 1220 |
+
"loss": 1.3271,
|
| 1221 |
+
"step": 1730
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.74,
|
| 1225 |
+
"grad_norm": 1.724934458732605,
|
| 1226 |
+
"learning_rate": 2.174137931034483e-05,
|
| 1227 |
+
"loss": 1.1641,
|
| 1228 |
+
"step": 1740
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.75,
|
| 1232 |
+
"grad_norm": 1.8861603736877441,
|
| 1233 |
+
"learning_rate": 2.1568965517241378e-05,
|
| 1234 |
+
"loss": 1.3302,
|
| 1235 |
+
"step": 1750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.76,
|
| 1239 |
+
"grad_norm": 1.9307113885879517,
|
| 1240 |
+
"learning_rate": 2.139655172413793e-05,
|
| 1241 |
+
"loss": 1.4253,
|
| 1242 |
+
"step": 1760
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.77,
|
| 1246 |
+
"grad_norm": 1.860857605934143,
|
| 1247 |
+
"learning_rate": 2.1224137931034486e-05,
|
| 1248 |
+
"loss": 1.4241,
|
| 1249 |
+
"step": 1770
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.78,
|
| 1253 |
+
"grad_norm": 2.8345351219177246,
|
| 1254 |
+
"learning_rate": 2.1051724137931038e-05,
|
| 1255 |
+
"loss": 1.2214,
|
| 1256 |
+
"step": 1780
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.79,
|
| 1260 |
+
"grad_norm": 1.1715213060379028,
|
| 1261 |
+
"learning_rate": 2.0879310344827586e-05,
|
| 1262 |
+
"loss": 1.3256,
|
| 1263 |
+
"step": 1790
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.8,
|
| 1267 |
+
"grad_norm": 1.8184287548065186,
|
| 1268 |
+
"learning_rate": 2.070689655172414e-05,
|
| 1269 |
+
"loss": 1.1173,
|
| 1270 |
+
"step": 1800
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.81,
|
| 1274 |
+
"grad_norm": 1.9528814554214478,
|
| 1275 |
+
"learning_rate": 2.053448275862069e-05,
|
| 1276 |
+
"loss": 1.1872,
|
| 1277 |
+
"step": 1810
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.8199999999999998,
|
| 1281 |
+
"grad_norm": 2.1913580894470215,
|
| 1282 |
+
"learning_rate": 2.0362068965517243e-05,
|
| 1283 |
+
"loss": 1.2677,
|
| 1284 |
+
"step": 1820
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.83,
|
| 1288 |
+
"grad_norm": 1.9390571117401123,
|
| 1289 |
+
"learning_rate": 2.0189655172413795e-05,
|
| 1290 |
+
"loss": 1.2469,
|
| 1291 |
+
"step": 1830
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 1.8399999999999999,
|
| 1295 |
+
"grad_norm": 1.8685649633407593,
|
| 1296 |
+
"learning_rate": 2.0017241379310343e-05,
|
| 1297 |
+
"loss": 1.2809,
|
| 1298 |
+
"step": 1840
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.85,
|
| 1302 |
+
"grad_norm": 2.4311530590057373,
|
| 1303 |
+
"learning_rate": 1.98448275862069e-05,
|
| 1304 |
+
"loss": 1.2982,
|
| 1305 |
+
"step": 1850
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.8599999999999999,
|
| 1309 |
+
"grad_norm": 1.5639426708221436,
|
| 1310 |
+
"learning_rate": 1.967241379310345e-05,
|
| 1311 |
+
"loss": 1.2996,
|
| 1312 |
+
"step": 1860
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.87,
|
| 1316 |
+
"grad_norm": 1.2009373903274536,
|
| 1317 |
+
"learning_rate": 1.9500000000000003e-05,
|
| 1318 |
+
"loss": 1.2812,
|
| 1319 |
+
"step": 1870
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.88,
|
| 1323 |
+
"grad_norm": 1.017490267753601,
|
| 1324 |
+
"learning_rate": 1.9327586206896552e-05,
|
| 1325 |
+
"loss": 1.1055,
|
| 1326 |
+
"step": 1880
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 1.8900000000000001,
|
| 1330 |
+
"grad_norm": 2.3106815814971924,
|
| 1331 |
+
"learning_rate": 1.9155172413793104e-05,
|
| 1332 |
+
"loss": 1.2474,
|
| 1333 |
+
"step": 1890
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 1.9,
|
| 1337 |
+
"grad_norm": 1.609084129333496,
|
| 1338 |
+
"learning_rate": 1.8982758620689656e-05,
|
| 1339 |
+
"loss": 1.1917,
|
| 1340 |
+
"step": 1900
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.9100000000000001,
|
| 1344 |
+
"grad_norm": 1.7436444759368896,
|
| 1345 |
+
"learning_rate": 1.8810344827586208e-05,
|
| 1346 |
+
"loss": 1.3704,
|
| 1347 |
+
"step": 1910
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 1.92,
|
| 1351 |
+
"grad_norm": 1.7709165811538696,
|
| 1352 |
+
"learning_rate": 1.863793103448276e-05,
|
| 1353 |
+
"loss": 1.3904,
|
| 1354 |
+
"step": 1920
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.9300000000000002,
|
| 1358 |
+
"grad_norm": 1.775133490562439,
|
| 1359 |
+
"learning_rate": 1.8465517241379312e-05,
|
| 1360 |
+
"loss": 1.2368,
|
| 1361 |
+
"step": 1930
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 1.94,
|
| 1365 |
+
"grad_norm": 2.224012613296509,
|
| 1366 |
+
"learning_rate": 1.8293103448275864e-05,
|
| 1367 |
+
"loss": 1.1834,
|
| 1368 |
+
"step": 1940
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.95,
|
| 1372 |
+
"grad_norm": 1.8021095991134644,
|
| 1373 |
+
"learning_rate": 1.8120689655172416e-05,
|
| 1374 |
+
"loss": 1.2385,
|
| 1375 |
+
"step": 1950
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 1.96,
|
| 1379 |
+
"grad_norm": 2.179215431213379,
|
| 1380 |
+
"learning_rate": 1.7948275862068965e-05,
|
| 1381 |
+
"loss": 1.4039,
|
| 1382 |
+
"step": 1960
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.97,
|
| 1386 |
+
"grad_norm": 1.850145697593689,
|
| 1387 |
+
"learning_rate": 1.7775862068965517e-05,
|
| 1388 |
+
"loss": 1.1953,
|
| 1389 |
+
"step": 1970
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.98,
|
| 1393 |
+
"grad_norm": 1.6872076988220215,
|
| 1394 |
+
"learning_rate": 1.760344827586207e-05,
|
| 1395 |
+
"loss": 1.2247,
|
| 1396 |
+
"step": 1980
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 1.99,
|
| 1400 |
+
"grad_norm": 2.2350351810455322,
|
| 1401 |
+
"learning_rate": 1.743103448275862e-05,
|
| 1402 |
+
"loss": 1.0938,
|
| 1403 |
+
"step": 1990
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 2.0,
|
| 1407 |
+
"grad_norm": 1.5278306007385254,
|
| 1408 |
+
"learning_rate": 1.7258620689655173e-05,
|
| 1409 |
+
"loss": 1.216,
|
| 1410 |
+
"step": 2000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 2.01,
|
| 1414 |
+
"grad_norm": 1.9336029291152954,
|
| 1415 |
+
"learning_rate": 1.7086206896551722e-05,
|
| 1416 |
+
"loss": 1.1958,
|
| 1417 |
+
"step": 2010
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 2.02,
|
| 1421 |
+
"grad_norm": 1.2718322277069092,
|
| 1422 |
+
"learning_rate": 1.6913793103448278e-05,
|
| 1423 |
+
"loss": 1.047,
|
| 1424 |
+
"step": 2020
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 2.03,
|
| 1428 |
+
"grad_norm": 1.8943592309951782,
|
| 1429 |
+
"learning_rate": 1.674137931034483e-05,
|
| 1430 |
+
"loss": 1.3197,
|
| 1431 |
+
"step": 2030
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 2.04,
|
| 1435 |
+
"grad_norm": 1.7184983491897583,
|
| 1436 |
+
"learning_rate": 1.6568965517241382e-05,
|
| 1437 |
+
"loss": 1.1611,
|
| 1438 |
+
"step": 2040
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 2.05,
|
| 1442 |
+
"grad_norm": 2.1850178241729736,
|
| 1443 |
+
"learning_rate": 1.639655172413793e-05,
|
| 1444 |
+
"loss": 1.2405,
|
| 1445 |
+
"step": 2050
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 2.06,
|
| 1449 |
+
"grad_norm": 1.6850008964538574,
|
| 1450 |
+
"learning_rate": 1.6224137931034483e-05,
|
| 1451 |
+
"loss": 1.119,
|
| 1452 |
+
"step": 2060
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 2.07,
|
| 1456 |
+
"grad_norm": 1.895009160041809,
|
| 1457 |
+
"learning_rate": 1.6051724137931035e-05,
|
| 1458 |
+
"loss": 1.3074,
|
| 1459 |
+
"step": 2070
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 2.08,
|
| 1463 |
+
"grad_norm": 2.0490798950195312,
|
| 1464 |
+
"learning_rate": 1.5879310344827587e-05,
|
| 1465 |
+
"loss": 1.0361,
|
| 1466 |
+
"step": 2080
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 2.09,
|
| 1470 |
+
"grad_norm": 2.465575695037842,
|
| 1471 |
+
"learning_rate": 1.570689655172414e-05,
|
| 1472 |
+
"loss": 1.1015,
|
| 1473 |
+
"step": 2090
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 2.1,
|
| 1477 |
+
"grad_norm": 1.3066885471343994,
|
| 1478 |
+
"learning_rate": 1.553448275862069e-05,
|
| 1479 |
+
"loss": 1.1267,
|
| 1480 |
+
"step": 2100
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 2.11,
|
| 1484 |
+
"grad_norm": 1.7399309873580933,
|
| 1485 |
+
"learning_rate": 1.5362068965517243e-05,
|
| 1486 |
+
"loss": 1.203,
|
| 1487 |
+
"step": 2110
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 2.12,
|
| 1491 |
+
"grad_norm": 2.804007053375244,
|
| 1492 |
+
"learning_rate": 1.5189655172413793e-05,
|
| 1493 |
+
"loss": 1.0919,
|
| 1494 |
+
"step": 2120
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 2.13,
|
| 1498 |
+
"grad_norm": 1.44864022731781,
|
| 1499 |
+
"learning_rate": 1.5017241379310346e-05,
|
| 1500 |
+
"loss": 1.4365,
|
| 1501 |
+
"step": 2130
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 2.14,
|
| 1505 |
+
"grad_norm": 1.5640863180160522,
|
| 1506 |
+
"learning_rate": 1.4844827586206898e-05,
|
| 1507 |
+
"loss": 1.1694,
|
| 1508 |
+
"step": 2140
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 2.15,
|
| 1512 |
+
"grad_norm": 1.847272276878357,
|
| 1513 |
+
"learning_rate": 1.4672413793103448e-05,
|
| 1514 |
+
"loss": 1.1713,
|
| 1515 |
+
"step": 2150
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 2.16,
|
| 1519 |
+
"grad_norm": 1.4313805103302002,
|
| 1520 |
+
"learning_rate": 1.45e-05,
|
| 1521 |
+
"loss": 1.108,
|
| 1522 |
+
"step": 2160
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 2.17,
|
| 1526 |
+
"grad_norm": 1.906491994857788,
|
| 1527 |
+
"learning_rate": 1.432758620689655e-05,
|
| 1528 |
+
"loss": 1.2404,
|
| 1529 |
+
"step": 2170
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 2.18,
|
| 1533 |
+
"grad_norm": 2.265270948410034,
|
| 1534 |
+
"learning_rate": 1.4155172413793106e-05,
|
| 1535 |
+
"loss": 1.1744,
|
| 1536 |
+
"step": 2180
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 2.19,
|
| 1540 |
+
"grad_norm": 1.927332878112793,
|
| 1541 |
+
"learning_rate": 1.3982758620689656e-05,
|
| 1542 |
+
"loss": 1.1907,
|
| 1543 |
+
"step": 2190
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 2.2,
|
| 1547 |
+
"grad_norm": 1.7866955995559692,
|
| 1548 |
+
"learning_rate": 1.3810344827586208e-05,
|
| 1549 |
+
"loss": 1.1983,
|
| 1550 |
+
"step": 2200
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 2.21,
|
| 1554 |
+
"grad_norm": 1.738226056098938,
|
| 1555 |
+
"learning_rate": 1.3637931034482759e-05,
|
| 1556 |
+
"loss": 1.2034,
|
| 1557 |
+
"step": 2210
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.22,
|
| 1561 |
+
"grad_norm": 1.8509528636932373,
|
| 1562 |
+
"learning_rate": 1.3465517241379311e-05,
|
| 1563 |
+
"loss": 1.2246,
|
| 1564 |
+
"step": 2220
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 2.23,
|
| 1568 |
+
"grad_norm": 2.776275634765625,
|
| 1569 |
+
"learning_rate": 1.3293103448275861e-05,
|
| 1570 |
+
"loss": 1.0615,
|
| 1571 |
+
"step": 2230
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 2.24,
|
| 1575 |
+
"grad_norm": 1.994899868965149,
|
| 1576 |
+
"learning_rate": 1.3120689655172413e-05,
|
| 1577 |
+
"loss": 1.0704,
|
| 1578 |
+
"step": 2240
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 2.25,
|
| 1582 |
+
"grad_norm": 1.3992385864257812,
|
| 1583 |
+
"learning_rate": 1.2948275862068966e-05,
|
| 1584 |
+
"loss": 1.1459,
|
| 1585 |
+
"step": 2250
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 2.26,
|
| 1589 |
+
"grad_norm": 1.4067262411117554,
|
| 1590 |
+
"learning_rate": 1.277586206896552e-05,
|
| 1591 |
+
"loss": 1.104,
|
| 1592 |
+
"step": 2260
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 2.27,
|
| 1596 |
+
"grad_norm": 2.0203895568847656,
|
| 1597 |
+
"learning_rate": 1.260344827586207e-05,
|
| 1598 |
+
"loss": 1.2588,
|
| 1599 |
+
"step": 2270
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 2.2800000000000002,
|
| 1603 |
+
"grad_norm": 2.0324246883392334,
|
| 1604 |
+
"learning_rate": 1.2431034482758622e-05,
|
| 1605 |
+
"loss": 1.2133,
|
| 1606 |
+
"step": 2280
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 2.29,
|
| 1610 |
+
"grad_norm": 1.5362598896026611,
|
| 1611 |
+
"learning_rate": 1.2258620689655174e-05,
|
| 1612 |
+
"loss": 1.2062,
|
| 1613 |
+
"step": 2290
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 2.3,
|
| 1617 |
+
"grad_norm": 1.9725372791290283,
|
| 1618 |
+
"learning_rate": 1.2086206896551724e-05,
|
| 1619 |
+
"loss": 1.2211,
|
| 1620 |
+
"step": 2300
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 2.31,
|
| 1624 |
+
"grad_norm": 2.6382522583007812,
|
| 1625 |
+
"learning_rate": 1.1913793103448276e-05,
|
| 1626 |
+
"loss": 1.3856,
|
| 1627 |
+
"step": 2310
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 2.32,
|
| 1631 |
+
"grad_norm": 0.9707180857658386,
|
| 1632 |
+
"learning_rate": 1.1741379310344828e-05,
|
| 1633 |
+
"loss": 1.1416,
|
| 1634 |
+
"step": 2320
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 2.33,
|
| 1638 |
+
"grad_norm": 2.1676788330078125,
|
| 1639 |
+
"learning_rate": 1.156896551724138e-05,
|
| 1640 |
+
"loss": 1.2297,
|
| 1641 |
+
"step": 2330
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 2.34,
|
| 1645 |
+
"grad_norm": 1.6406278610229492,
|
| 1646 |
+
"learning_rate": 1.1396551724137931e-05,
|
| 1647 |
+
"loss": 0.9923,
|
| 1648 |
+
"step": 2340
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 2.35,
|
| 1652 |
+
"grad_norm": 1.8479793071746826,
|
| 1653 |
+
"learning_rate": 1.1224137931034483e-05,
|
| 1654 |
+
"loss": 1.0925,
|
| 1655 |
+
"step": 2350
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 2.36,
|
| 1659 |
+
"grad_norm": 1.7905402183532715,
|
| 1660 |
+
"learning_rate": 1.1051724137931035e-05,
|
| 1661 |
+
"loss": 1.2361,
|
| 1662 |
+
"step": 2360
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 2.37,
|
| 1666 |
+
"grad_norm": 2.006901979446411,
|
| 1667 |
+
"learning_rate": 1.0879310344827587e-05,
|
| 1668 |
+
"loss": 1.144,
|
| 1669 |
+
"step": 2370
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 2.38,
|
| 1673 |
+
"grad_norm": 1.4485629796981812,
|
| 1674 |
+
"learning_rate": 1.0706896551724138e-05,
|
| 1675 |
+
"loss": 1.1374,
|
| 1676 |
+
"step": 2380
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 2.39,
|
| 1680 |
+
"grad_norm": 1.953250765800476,
|
| 1681 |
+
"learning_rate": 1.053448275862069e-05,
|
| 1682 |
+
"loss": 1.222,
|
| 1683 |
+
"step": 2390
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 2.4,
|
| 1687 |
+
"grad_norm": 1.4904489517211914,
|
| 1688 |
+
"learning_rate": 1.0362068965517242e-05,
|
| 1689 |
+
"loss": 1.1942,
|
| 1690 |
+
"step": 2400
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 2.41,
|
| 1694 |
+
"grad_norm": 1.9679901599884033,
|
| 1695 |
+
"learning_rate": 1.0189655172413794e-05,
|
| 1696 |
+
"loss": 1.2024,
|
| 1697 |
+
"step": 2410
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 2.42,
|
| 1701 |
+
"grad_norm": 1.6501275300979614,
|
| 1702 |
+
"learning_rate": 1.0017241379310344e-05,
|
| 1703 |
+
"loss": 1.2754,
|
| 1704 |
+
"step": 2420
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 2.43,
|
| 1708 |
+
"grad_norm": 1.617769479751587,
|
| 1709 |
+
"learning_rate": 9.844827586206896e-06,
|
| 1710 |
+
"loss": 1.2086,
|
| 1711 |
+
"step": 2430
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 2.44,
|
| 1715 |
+
"grad_norm": 1.9600815773010254,
|
| 1716 |
+
"learning_rate": 9.672413793103448e-06,
|
| 1717 |
+
"loss": 1.1549,
|
| 1718 |
+
"step": 2440
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 2.45,
|
| 1722 |
+
"grad_norm": 1.5949968099594116,
|
| 1723 |
+
"learning_rate": 9.5e-06,
|
| 1724 |
+
"loss": 1.2698,
|
| 1725 |
+
"step": 2450
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 2.46,
|
| 1729 |
+
"grad_norm": 1.2073543071746826,
|
| 1730 |
+
"learning_rate": 9.327586206896553e-06,
|
| 1731 |
+
"loss": 1.1885,
|
| 1732 |
+
"step": 2460
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 2.4699999999999998,
|
| 1736 |
+
"grad_norm": 1.0354326963424683,
|
| 1737 |
+
"learning_rate": 9.155172413793103e-06,
|
| 1738 |
+
"loss": 1.2975,
|
| 1739 |
+
"step": 2470
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 2.48,
|
| 1743 |
+
"grad_norm": 4.918059825897217,
|
| 1744 |
+
"learning_rate": 8.982758620689657e-06,
|
| 1745 |
+
"loss": 1.161,
|
| 1746 |
+
"step": 2480
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 2.49,
|
| 1750 |
+
"grad_norm": 2.176772117614746,
|
| 1751 |
+
"learning_rate": 8.810344827586207e-06,
|
| 1752 |
+
"loss": 1.1096,
|
| 1753 |
+
"step": 2490
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 2.5,
|
| 1757 |
+
"grad_norm": 1.9638526439666748,
|
| 1758 |
+
"learning_rate": 8.63793103448276e-06,
|
| 1759 |
+
"loss": 1.1893,
|
| 1760 |
+
"step": 2500
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 2.51,
|
| 1764 |
+
"grad_norm": 1.3812869787216187,
|
| 1765 |
+
"learning_rate": 8.46551724137931e-06,
|
| 1766 |
+
"loss": 1.1958,
|
| 1767 |
+
"step": 2510
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 2.52,
|
| 1771 |
+
"grad_norm": 2.1832292079925537,
|
| 1772 |
+
"learning_rate": 8.293103448275863e-06,
|
| 1773 |
+
"loss": 1.1582,
|
| 1774 |
+
"step": 2520
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 2.5300000000000002,
|
| 1778 |
+
"grad_norm": 1.416548728942871,
|
| 1779 |
+
"learning_rate": 8.120689655172414e-06,
|
| 1780 |
+
"loss": 0.9992,
|
| 1781 |
+
"step": 2530
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 2.54,
|
| 1785 |
+
"grad_norm": 1.465884804725647,
|
| 1786 |
+
"learning_rate": 7.948275862068966e-06,
|
| 1787 |
+
"loss": 1.1773,
|
| 1788 |
+
"step": 2540
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 2.55,
|
| 1792 |
+
"grad_norm": 1.754629373550415,
|
| 1793 |
+
"learning_rate": 7.775862068965516e-06,
|
| 1794 |
+
"loss": 1.2893,
|
| 1795 |
+
"step": 2550
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 2.56,
|
| 1799 |
+
"grad_norm": 1.3299590349197388,
|
| 1800 |
+
"learning_rate": 7.60344827586207e-06,
|
| 1801 |
+
"loss": 1.1175,
|
| 1802 |
+
"step": 2560
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 2.57,
|
| 1806 |
+
"grad_norm": 1.6379165649414062,
|
| 1807 |
+
"learning_rate": 7.431034482758621e-06,
|
| 1808 |
+
"loss": 1.1522,
|
| 1809 |
+
"step": 2570
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 2.58,
|
| 1813 |
+
"grad_norm": 1.038396954536438,
|
| 1814 |
+
"learning_rate": 7.258620689655173e-06,
|
| 1815 |
+
"loss": 1.1105,
|
| 1816 |
+
"step": 2580
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 2.59,
|
| 1820 |
+
"grad_norm": 3.7200427055358887,
|
| 1821 |
+
"learning_rate": 7.086206896551724e-06,
|
| 1822 |
+
"loss": 1.2392,
|
| 1823 |
+
"step": 2590
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 2.6,
|
| 1827 |
+
"grad_norm": 1.996336817741394,
|
| 1828 |
+
"learning_rate": 6.913793103448277e-06,
|
| 1829 |
+
"loss": 1.2586,
|
| 1830 |
+
"step": 2600
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 2.61,
|
| 1834 |
+
"grad_norm": 2.2930266857147217,
|
| 1835 |
+
"learning_rate": 6.741379310344828e-06,
|
| 1836 |
+
"loss": 1.2299,
|
| 1837 |
+
"step": 2610
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 2.62,
|
| 1841 |
+
"grad_norm": 1.5807350873947144,
|
| 1842 |
+
"learning_rate": 6.568965517241379e-06,
|
| 1843 |
+
"loss": 1.1705,
|
| 1844 |
+
"step": 2620
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 2.63,
|
| 1848 |
+
"grad_norm": 2.1657156944274902,
|
| 1849 |
+
"learning_rate": 6.3965517241379305e-06,
|
| 1850 |
+
"loss": 1.008,
|
| 1851 |
+
"step": 2630
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 2.64,
|
| 1855 |
+
"grad_norm": 2.036822557449341,
|
| 1856 |
+
"learning_rate": 6.224137931034483e-06,
|
| 1857 |
+
"loss": 1.36,
|
| 1858 |
+
"step": 2640
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 2.65,
|
| 1862 |
+
"grad_norm": 1.8225266933441162,
|
| 1863 |
+
"learning_rate": 6.051724137931035e-06,
|
| 1864 |
+
"loss": 1.0531,
|
| 1865 |
+
"step": 2650
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 2.66,
|
| 1869 |
+
"grad_norm": 1.9631621837615967,
|
| 1870 |
+
"learning_rate": 5.879310344827586e-06,
|
| 1871 |
+
"loss": 1.1185,
|
| 1872 |
+
"step": 2660
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 2.67,
|
| 1876 |
+
"grad_norm": 1.3313068151474,
|
| 1877 |
+
"learning_rate": 5.706896551724138e-06,
|
| 1878 |
+
"loss": 1.0997,
|
| 1879 |
+
"step": 2670
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 2.68,
|
| 1883 |
+
"grad_norm": 1.7591108083724976,
|
| 1884 |
+
"learning_rate": 5.53448275862069e-06,
|
| 1885 |
+
"loss": 1.2264,
|
| 1886 |
+
"step": 2680
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 2.69,
|
| 1890 |
+
"grad_norm": 1.669311761856079,
|
| 1891 |
+
"learning_rate": 5.362068965517242e-06,
|
| 1892 |
+
"loss": 1.0538,
|
| 1893 |
+
"step": 2690
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 2.7,
|
| 1897 |
+
"grad_norm": 1.9697110652923584,
|
| 1898 |
+
"learning_rate": 5.1896551724137934e-06,
|
| 1899 |
+
"loss": 1.2217,
|
| 1900 |
+
"step": 2700
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 2.71,
|
| 1904 |
+
"grad_norm": 1.5783755779266357,
|
| 1905 |
+
"learning_rate": 5.0172413793103455e-06,
|
| 1906 |
+
"loss": 1.1666,
|
| 1907 |
+
"step": 2710
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 2.7199999999999998,
|
| 1911 |
+
"grad_norm": 2.451660394668579,
|
| 1912 |
+
"learning_rate": 4.844827586206897e-06,
|
| 1913 |
+
"loss": 1.2254,
|
| 1914 |
+
"step": 2720
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 2.73,
|
| 1918 |
+
"grad_norm": 1.6855318546295166,
|
| 1919 |
+
"learning_rate": 4.672413793103449e-06,
|
| 1920 |
+
"loss": 1.1644,
|
| 1921 |
+
"step": 2730
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 2.74,
|
| 1925 |
+
"grad_norm": 1.955734372138977,
|
| 1926 |
+
"learning_rate": 4.5e-06,
|
| 1927 |
+
"loss": 1.2558,
|
| 1928 |
+
"step": 2740
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 2.75,
|
| 1932 |
+
"grad_norm": 1.5705198049545288,
|
| 1933 |
+
"learning_rate": 4.327586206896552e-06,
|
| 1934 |
+
"loss": 1.3614,
|
| 1935 |
+
"step": 2750
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 2.76,
|
| 1939 |
+
"grad_norm": 1.878604769706726,
|
| 1940 |
+
"learning_rate": 4.1551724137931034e-06,
|
| 1941 |
+
"loss": 1.1227,
|
| 1942 |
+
"step": 2760
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 2.77,
|
| 1946 |
+
"grad_norm": 1.3818405866622925,
|
| 1947 |
+
"learning_rate": 3.9827586206896555e-06,
|
| 1948 |
+
"loss": 1.0261,
|
| 1949 |
+
"step": 2770
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 2.7800000000000002,
|
| 1953 |
+
"grad_norm": 1.960067629814148,
|
| 1954 |
+
"learning_rate": 3.8103448275862068e-06,
|
| 1955 |
+
"loss": 1.2194,
|
| 1956 |
+
"step": 2780
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 2.79,
|
| 1960 |
+
"grad_norm": 1.6252312660217285,
|
| 1961 |
+
"learning_rate": 3.637931034482759e-06,
|
| 1962 |
+
"loss": 1.0916,
|
| 1963 |
+
"step": 2790
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 2.8,
|
| 1967 |
+
"grad_norm": 2.1915979385375977,
|
| 1968 |
+
"learning_rate": 3.4655172413793105e-06,
|
| 1969 |
+
"loss": 0.9632,
|
| 1970 |
+
"step": 2800
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 2.81,
|
| 1974 |
+
"grad_norm": 1.7106447219848633,
|
| 1975 |
+
"learning_rate": 3.2931034482758626e-06,
|
| 1976 |
+
"loss": 1.1671,
|
| 1977 |
+
"step": 2810
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 2.82,
|
| 1981 |
+
"grad_norm": 1.840908169746399,
|
| 1982 |
+
"learning_rate": 3.120689655172414e-06,
|
| 1983 |
+
"loss": 1.1216,
|
| 1984 |
+
"step": 2820
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 2.83,
|
| 1988 |
+
"grad_norm": 1.71086585521698,
|
| 1989 |
+
"learning_rate": 2.9482758620689655e-06,
|
| 1990 |
+
"loss": 1.1521,
|
| 1991 |
+
"step": 2830
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 2.84,
|
| 1995 |
+
"grad_norm": 1.500496745109558,
|
| 1996 |
+
"learning_rate": 2.775862068965517e-06,
|
| 1997 |
+
"loss": 1.1021,
|
| 1998 |
+
"step": 2840
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 2.85,
|
| 2002 |
+
"grad_norm": 2.563215494155884,
|
| 2003 |
+
"learning_rate": 2.603448275862069e-06,
|
| 2004 |
+
"loss": 1.0535,
|
| 2005 |
+
"step": 2850
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 2.86,
|
| 2009 |
+
"grad_norm": 1.2782319784164429,
|
| 2010 |
+
"learning_rate": 2.4310344827586205e-06,
|
| 2011 |
+
"loss": 1.1942,
|
| 2012 |
+
"step": 2860
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 2.87,
|
| 2016 |
+
"grad_norm": 1.2960996627807617,
|
| 2017 |
+
"learning_rate": 2.258620689655172e-06,
|
| 2018 |
+
"loss": 1.1178,
|
| 2019 |
+
"step": 2870
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 2.88,
|
| 2023 |
+
"grad_norm": 1.6457912921905518,
|
| 2024 |
+
"learning_rate": 2.0862068965517243e-06,
|
| 2025 |
+
"loss": 1.0038,
|
| 2026 |
+
"step": 2880
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 2.89,
|
| 2030 |
+
"grad_norm": 1.8096386194229126,
|
| 2031 |
+
"learning_rate": 1.913793103448276e-06,
|
| 2032 |
+
"loss": 1.142,
|
| 2033 |
+
"step": 2890
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 2.9,
|
| 2037 |
+
"grad_norm": 1.7525629997253418,
|
| 2038 |
+
"learning_rate": 1.7413793103448276e-06,
|
| 2039 |
+
"loss": 1.254,
|
| 2040 |
+
"step": 2900
|
| 2041 |
+
}
|
| 2042 |
+
],
|
| 2043 |
+
"logging_steps": 10,
|
| 2044 |
+
"max_steps": 3000,
|
| 2045 |
+
"num_input_tokens_seen": 0,
|
| 2046 |
+
"num_train_epochs": 3,
|
| 2047 |
+
"save_steps": 100,
|
| 2048 |
+
"stateful_callbacks": {
|
| 2049 |
+
"TrainerControl": {
|
| 2050 |
+
"args": {
|
| 2051 |
+
"should_epoch_stop": false,
|
| 2052 |
+
"should_evaluate": false,
|
| 2053 |
+
"should_log": false,
|
| 2054 |
+
"should_save": true,
|
| 2055 |
+
"should_training_stop": false
|
| 2056 |
+
},
|
| 2057 |
+
"attributes": {}
|
| 2058 |
+
}
|
| 2059 |
+
},
|
| 2060 |
+
"total_flos": 2693232014131200.0,
|
| 2061 |
+
"train_batch_size": 1,
|
| 2062 |
+
"trial_name": null,
|
| 2063 |
+
"trial_params": null
|
| 2064 |
+
}
|
checkpoint-2900/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0244160d188a0289445d5ae2f05138afafa90037236cf4c193c3737263ceffa6
|
| 3 |
+
size 5713
|
checkpoint-2900/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-3000/chat_template.jinja
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}
|
checkpoint-3000/config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 50256,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 50256,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"layer_norm_epsilon": 1e-05,
|
| 12 |
+
"model_type": "gpt2",
|
| 13 |
+
"n_ctx": 1024,
|
| 14 |
+
"n_embd": 1024,
|
| 15 |
+
"n_head": 16,
|
| 16 |
+
"n_inner": null,
|
| 17 |
+
"n_layer": 24,
|
| 18 |
+
"n_positions": 1024,
|
| 19 |
+
"reorder_and_upcast_attn": false,
|
| 20 |
+
"resid_pdrop": 0.1,
|
| 21 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 22 |
+
"scale_attn_weights": true,
|
| 23 |
+
"summary_activation": null,
|
| 24 |
+
"summary_first_dropout": 0.1,
|
| 25 |
+
"summary_proj_to_labels": true,
|
| 26 |
+
"summary_type": "cls_index",
|
| 27 |
+
"summary_use_proj": true,
|
| 28 |
+
"task_specific_params": {
|
| 29 |
+
"conversational": {
|
| 30 |
+
"max_length": 1000
|
| 31 |
+
}
|
| 32 |
+
},
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.54.1",
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"vocab_size": 50257
|
| 37 |
+
}
|
checkpoint-3000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.54.1"
|
| 6 |
+
}
|
checkpoint-3000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-3000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc5fa7efba02f35c045a01f7c4c6ce163bbd4ff58214d2d436dcb2908023fe1b
|
| 3 |
+
size 1419322880
|
checkpoint-3000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7cfacd20e582d507773ab0e4bff4ddfff83942c107bc58f29777e36c572b85f8
|
| 3 |
+
size 2838821579
|
checkpoint-3000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dba4fde4ee04d2f472bb4dea96a48e8fdf7891d2b0694a8f012e8133a2e176ae
|
| 3 |
+
size 14455
|
checkpoint-3000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3798f8bf00fce41188eac8279cbc9575ed4f092b7d984fe4e0e52167a94779a
|
| 3 |
+
size 1465
|
checkpoint-3000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|endoftext|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
checkpoint-3000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-3000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"50256": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
}
|
| 13 |
+
},
|
| 14 |
+
"bos_token": "<|endoftext|>",
|
| 15 |
+
"clean_up_tokenization_spaces": true,
|
| 16 |
+
"eos_token": "<|endoftext|>",
|
| 17 |
+
"errors": "replace",
|
| 18 |
+
"extra_special_tokens": {},
|
| 19 |
+
"model_max_length": 1024,
|
| 20 |
+
"pad_token": "<|endoftext|>",
|
| 21 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 22 |
+
"unk_token": "<|endoftext|>"
|
| 23 |
+
}
|
checkpoint-3000/trainer_state.json
ADDED
|
@@ -0,0 +1,2134 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 3000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.01,
|
| 14 |
+
"grad_norm": 31.807226181030273,
|
| 15 |
+
"learning_rate": 4.5e-06,
|
| 16 |
+
"loss": 10.2322,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.02,
|
| 21 |
+
"grad_norm": 14.19406795501709,
|
| 22 |
+
"learning_rate": 9.5e-06,
|
| 23 |
+
"loss": 8.6686,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.03,
|
| 28 |
+
"grad_norm": 8.947138786315918,
|
| 29 |
+
"learning_rate": 1.45e-05,
|
| 30 |
+
"loss": 6.6091,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.04,
|
| 35 |
+
"grad_norm": 7.508649826049805,
|
| 36 |
+
"learning_rate": 1.9500000000000003e-05,
|
| 37 |
+
"loss": 5.1112,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.05,
|
| 42 |
+
"grad_norm": 5.768527030944824,
|
| 43 |
+
"learning_rate": 2.45e-05,
|
| 44 |
+
"loss": 4.4247,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.06,
|
| 49 |
+
"grad_norm": 5.962294578552246,
|
| 50 |
+
"learning_rate": 2.95e-05,
|
| 51 |
+
"loss": 3.7838,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.07,
|
| 56 |
+
"grad_norm": 7.343990802764893,
|
| 57 |
+
"learning_rate": 3.45e-05,
|
| 58 |
+
"loss": 3.3172,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.08,
|
| 63 |
+
"grad_norm": 5.001032829284668,
|
| 64 |
+
"learning_rate": 3.9500000000000005e-05,
|
| 65 |
+
"loss": 3.1734,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.09,
|
| 70 |
+
"grad_norm": 3.4707157611846924,
|
| 71 |
+
"learning_rate": 4.4500000000000004e-05,
|
| 72 |
+
"loss": 2.9784,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1,
|
| 77 |
+
"grad_norm": 4.321723461151123,
|
| 78 |
+
"learning_rate": 4.9500000000000004e-05,
|
| 79 |
+
"loss": 2.6301,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.11,
|
| 84 |
+
"grad_norm": 4.037026405334473,
|
| 85 |
+
"learning_rate": 4.98448275862069e-05,
|
| 86 |
+
"loss": 2.8441,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.12,
|
| 91 |
+
"grad_norm": 6.042785167694092,
|
| 92 |
+
"learning_rate": 4.967241379310345e-05,
|
| 93 |
+
"loss": 2.5558,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.13,
|
| 98 |
+
"grad_norm": 7.331098556518555,
|
| 99 |
+
"learning_rate": 4.9500000000000004e-05,
|
| 100 |
+
"loss": 2.5997,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.14,
|
| 105 |
+
"grad_norm": 5.285608291625977,
|
| 106 |
+
"learning_rate": 4.932758620689655e-05,
|
| 107 |
+
"loss": 2.3912,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.15,
|
| 112 |
+
"grad_norm": 5.633673191070557,
|
| 113 |
+
"learning_rate": 4.915517241379311e-05,
|
| 114 |
+
"loss": 2.3576,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.16,
|
| 119 |
+
"grad_norm": 5.462876796722412,
|
| 120 |
+
"learning_rate": 4.898275862068966e-05,
|
| 121 |
+
"loss": 2.3879,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.17,
|
| 126 |
+
"grad_norm": 5.2996015548706055,
|
| 127 |
+
"learning_rate": 4.8810344827586205e-05,
|
| 128 |
+
"loss": 2.6634,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.18,
|
| 133 |
+
"grad_norm": 4.960510730743408,
|
| 134 |
+
"learning_rate": 4.863793103448276e-05,
|
| 135 |
+
"loss": 2.3228,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.19,
|
| 140 |
+
"grad_norm": 5.18018913269043,
|
| 141 |
+
"learning_rate": 4.846551724137931e-05,
|
| 142 |
+
"loss": 2.4035,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.2,
|
| 147 |
+
"grad_norm": 3.5356884002685547,
|
| 148 |
+
"learning_rate": 4.8293103448275865e-05,
|
| 149 |
+
"loss": 1.9488,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.21,
|
| 154 |
+
"grad_norm": 2.8790781497955322,
|
| 155 |
+
"learning_rate": 4.812068965517242e-05,
|
| 156 |
+
"loss": 2.2974,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.22,
|
| 161 |
+
"grad_norm": 3.502866506576538,
|
| 162 |
+
"learning_rate": 4.794827586206897e-05,
|
| 163 |
+
"loss": 2.1646,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.23,
|
| 168 |
+
"grad_norm": 2.9694302082061768,
|
| 169 |
+
"learning_rate": 4.777586206896552e-05,
|
| 170 |
+
"loss": 2.1186,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.24,
|
| 175 |
+
"grad_norm": 2.986870050430298,
|
| 176 |
+
"learning_rate": 4.7603448275862073e-05,
|
| 177 |
+
"loss": 2.1907,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.25,
|
| 182 |
+
"grad_norm": 7.217125415802002,
|
| 183 |
+
"learning_rate": 4.743103448275862e-05,
|
| 184 |
+
"loss": 2.0278,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.26,
|
| 189 |
+
"grad_norm": 2.887138843536377,
|
| 190 |
+
"learning_rate": 4.725862068965518e-05,
|
| 191 |
+
"loss": 2.269,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.27,
|
| 196 |
+
"grad_norm": 14.621356964111328,
|
| 197 |
+
"learning_rate": 4.7086206896551726e-05,
|
| 198 |
+
"loss": 2.0509,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.28,
|
| 203 |
+
"grad_norm": 2.5131711959838867,
|
| 204 |
+
"learning_rate": 4.6913793103448275e-05,
|
| 205 |
+
"loss": 2.2239,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.29,
|
| 210 |
+
"grad_norm": 4.753391265869141,
|
| 211 |
+
"learning_rate": 4.674137931034483e-05,
|
| 212 |
+
"loss": 2.0629,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.3,
|
| 217 |
+
"grad_norm": 4.106902599334717,
|
| 218 |
+
"learning_rate": 4.656896551724138e-05,
|
| 219 |
+
"loss": 2.0625,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.31,
|
| 224 |
+
"grad_norm": 4.522510528564453,
|
| 225 |
+
"learning_rate": 4.6396551724137935e-05,
|
| 226 |
+
"loss": 1.9146,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.32,
|
| 231 |
+
"grad_norm": 3.454258441925049,
|
| 232 |
+
"learning_rate": 4.622413793103448e-05,
|
| 233 |
+
"loss": 1.7679,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.33,
|
| 238 |
+
"grad_norm": 12.172571182250977,
|
| 239 |
+
"learning_rate": 4.605172413793103e-05,
|
| 240 |
+
"loss": 1.762,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.34,
|
| 245 |
+
"grad_norm": 5.5643630027771,
|
| 246 |
+
"learning_rate": 4.587931034482759e-05,
|
| 247 |
+
"loss": 1.9651,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.35,
|
| 252 |
+
"grad_norm": 5.371229648590088,
|
| 253 |
+
"learning_rate": 4.5706896551724136e-05,
|
| 254 |
+
"loss": 2.1326,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.36,
|
| 259 |
+
"grad_norm": 2.6412742137908936,
|
| 260 |
+
"learning_rate": 4.553448275862069e-05,
|
| 261 |
+
"loss": 1.955,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.37,
|
| 266 |
+
"grad_norm": 5.9563775062561035,
|
| 267 |
+
"learning_rate": 4.536206896551725e-05,
|
| 268 |
+
"loss": 1.8654,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.38,
|
| 273 |
+
"grad_norm": 5.498210906982422,
|
| 274 |
+
"learning_rate": 4.5189655172413796e-05,
|
| 275 |
+
"loss": 2.0221,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.39,
|
| 280 |
+
"grad_norm": 1.9855848550796509,
|
| 281 |
+
"learning_rate": 4.501724137931035e-05,
|
| 282 |
+
"loss": 1.9202,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.4,
|
| 287 |
+
"grad_norm": 6.402889728546143,
|
| 288 |
+
"learning_rate": 4.48448275862069e-05,
|
| 289 |
+
"loss": 1.6582,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.41,
|
| 294 |
+
"grad_norm": 1.9488422870635986,
|
| 295 |
+
"learning_rate": 4.467241379310345e-05,
|
| 296 |
+
"loss": 1.9576,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.42,
|
| 301 |
+
"grad_norm": 1.99562406539917,
|
| 302 |
+
"learning_rate": 4.4500000000000004e-05,
|
| 303 |
+
"loss": 1.6823,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.43,
|
| 308 |
+
"grad_norm": 3.2172203063964844,
|
| 309 |
+
"learning_rate": 4.432758620689655e-05,
|
| 310 |
+
"loss": 1.7448,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.44,
|
| 315 |
+
"grad_norm": 1.7004073858261108,
|
| 316 |
+
"learning_rate": 4.415517241379311e-05,
|
| 317 |
+
"loss": 1.687,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.45,
|
| 322 |
+
"grad_norm": 2.6527938842773438,
|
| 323 |
+
"learning_rate": 4.398275862068966e-05,
|
| 324 |
+
"loss": 1.6152,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.46,
|
| 329 |
+
"grad_norm": 2.223691463470459,
|
| 330 |
+
"learning_rate": 4.3810344827586206e-05,
|
| 331 |
+
"loss": 1.7911,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.47,
|
| 336 |
+
"grad_norm": 2.228793144226074,
|
| 337 |
+
"learning_rate": 4.363793103448276e-05,
|
| 338 |
+
"loss": 1.9451,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.48,
|
| 343 |
+
"grad_norm": 2.724231243133545,
|
| 344 |
+
"learning_rate": 4.346551724137931e-05,
|
| 345 |
+
"loss": 1.791,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.49,
|
| 350 |
+
"grad_norm": 3.219877243041992,
|
| 351 |
+
"learning_rate": 4.3293103448275865e-05,
|
| 352 |
+
"loss": 1.692,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.5,
|
| 357 |
+
"grad_norm": 2.977465867996216,
|
| 358 |
+
"learning_rate": 4.3120689655172414e-05,
|
| 359 |
+
"loss": 1.886,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.51,
|
| 364 |
+
"grad_norm": 2.566962242126465,
|
| 365 |
+
"learning_rate": 4.294827586206896e-05,
|
| 366 |
+
"loss": 1.802,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.52,
|
| 371 |
+
"grad_norm": 3.129835844039917,
|
| 372 |
+
"learning_rate": 4.2775862068965525e-05,
|
| 373 |
+
"loss": 1.659,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.53,
|
| 378 |
+
"grad_norm": 3.913256883621216,
|
| 379 |
+
"learning_rate": 4.2603448275862074e-05,
|
| 380 |
+
"loss": 1.5919,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.54,
|
| 385 |
+
"grad_norm": 1.7998114824295044,
|
| 386 |
+
"learning_rate": 4.243103448275862e-05,
|
| 387 |
+
"loss": 1.7564,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.55,
|
| 392 |
+
"grad_norm": 2.310154676437378,
|
| 393 |
+
"learning_rate": 4.225862068965518e-05,
|
| 394 |
+
"loss": 1.7347,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.56,
|
| 399 |
+
"grad_norm": 1.835707426071167,
|
| 400 |
+
"learning_rate": 4.208620689655173e-05,
|
| 401 |
+
"loss": 1.802,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.57,
|
| 406 |
+
"grad_norm": 1.9488534927368164,
|
| 407 |
+
"learning_rate": 4.191379310344828e-05,
|
| 408 |
+
"loss": 1.9981,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.58,
|
| 413 |
+
"grad_norm": 5.861155986785889,
|
| 414 |
+
"learning_rate": 4.174137931034483e-05,
|
| 415 |
+
"loss": 1.9519,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.59,
|
| 420 |
+
"grad_norm": 2.403691053390503,
|
| 421 |
+
"learning_rate": 4.156896551724138e-05,
|
| 422 |
+
"loss": 1.6711,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.6,
|
| 427 |
+
"grad_norm": 1.9013047218322754,
|
| 428 |
+
"learning_rate": 4.1396551724137935e-05,
|
| 429 |
+
"loss": 1.6679,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.61,
|
| 434 |
+
"grad_norm": 2.6646413803100586,
|
| 435 |
+
"learning_rate": 4.1224137931034484e-05,
|
| 436 |
+
"loss": 1.7117,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.62,
|
| 441 |
+
"grad_norm": 2.6011579036712646,
|
| 442 |
+
"learning_rate": 4.105172413793103e-05,
|
| 443 |
+
"loss": 1.6351,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.63,
|
| 448 |
+
"grad_norm": 1.9296406507492065,
|
| 449 |
+
"learning_rate": 4.087931034482759e-05,
|
| 450 |
+
"loss": 1.8179,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.64,
|
| 455 |
+
"grad_norm": 2.2965588569641113,
|
| 456 |
+
"learning_rate": 4.070689655172414e-05,
|
| 457 |
+
"loss": 1.7164,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.65,
|
| 462 |
+
"grad_norm": 1.7480602264404297,
|
| 463 |
+
"learning_rate": 4.053448275862069e-05,
|
| 464 |
+
"loss": 1.5552,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.66,
|
| 469 |
+
"grad_norm": 2.9659781455993652,
|
| 470 |
+
"learning_rate": 4.036206896551724e-05,
|
| 471 |
+
"loss": 1.79,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.67,
|
| 476 |
+
"grad_norm": 1.5911238193511963,
|
| 477 |
+
"learning_rate": 4.018965517241379e-05,
|
| 478 |
+
"loss": 1.7139,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.68,
|
| 483 |
+
"grad_norm": 1.8339680433273315,
|
| 484 |
+
"learning_rate": 4.0017241379310345e-05,
|
| 485 |
+
"loss": 1.6479,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.69,
|
| 490 |
+
"grad_norm": 1.8804699182510376,
|
| 491 |
+
"learning_rate": 3.98448275862069e-05,
|
| 492 |
+
"loss": 1.6501,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.7,
|
| 497 |
+
"grad_norm": 5.505954742431641,
|
| 498 |
+
"learning_rate": 3.967241379310345e-05,
|
| 499 |
+
"loss": 1.549,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.71,
|
| 504 |
+
"grad_norm": 3.225405693054199,
|
| 505 |
+
"learning_rate": 3.9500000000000005e-05,
|
| 506 |
+
"loss": 1.5231,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.72,
|
| 511 |
+
"grad_norm": 2.4233756065368652,
|
| 512 |
+
"learning_rate": 3.932758620689655e-05,
|
| 513 |
+
"loss": 1.5577,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.73,
|
| 518 |
+
"grad_norm": 1.9218379259109497,
|
| 519 |
+
"learning_rate": 3.915517241379311e-05,
|
| 520 |
+
"loss": 1.8394,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.74,
|
| 525 |
+
"grad_norm": 1.7937753200531006,
|
| 526 |
+
"learning_rate": 3.898275862068966e-05,
|
| 527 |
+
"loss": 1.4735,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.75,
|
| 532 |
+
"grad_norm": 2.696561336517334,
|
| 533 |
+
"learning_rate": 3.8810344827586206e-05,
|
| 534 |
+
"loss": 1.7371,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.76,
|
| 539 |
+
"grad_norm": 1.6280263662338257,
|
| 540 |
+
"learning_rate": 3.863793103448276e-05,
|
| 541 |
+
"loss": 1.6161,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.77,
|
| 546 |
+
"grad_norm": 1.7006651163101196,
|
| 547 |
+
"learning_rate": 3.846551724137931e-05,
|
| 548 |
+
"loss": 1.4593,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.78,
|
| 553 |
+
"grad_norm": 3.765646457672119,
|
| 554 |
+
"learning_rate": 3.8293103448275866e-05,
|
| 555 |
+
"loss": 1.5506,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.79,
|
| 560 |
+
"grad_norm": 2.9314448833465576,
|
| 561 |
+
"learning_rate": 3.8120689655172415e-05,
|
| 562 |
+
"loss": 1.5805,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.8,
|
| 567 |
+
"grad_norm": 1.736654281616211,
|
| 568 |
+
"learning_rate": 3.794827586206896e-05,
|
| 569 |
+
"loss": 1.5675,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.81,
|
| 574 |
+
"grad_norm": 2.3542542457580566,
|
| 575 |
+
"learning_rate": 3.777586206896552e-05,
|
| 576 |
+
"loss": 1.5955,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.82,
|
| 581 |
+
"grad_norm": 2.1898491382598877,
|
| 582 |
+
"learning_rate": 3.760344827586207e-05,
|
| 583 |
+
"loss": 1.3708,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.83,
|
| 588 |
+
"grad_norm": 2.2105820178985596,
|
| 589 |
+
"learning_rate": 3.743103448275862e-05,
|
| 590 |
+
"loss": 1.6554,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.84,
|
| 595 |
+
"grad_norm": 4.901267051696777,
|
| 596 |
+
"learning_rate": 3.725862068965517e-05,
|
| 597 |
+
"loss": 1.3071,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.85,
|
| 602 |
+
"grad_norm": 1.991741418838501,
|
| 603 |
+
"learning_rate": 3.708620689655173e-05,
|
| 604 |
+
"loss": 1.3876,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.86,
|
| 609 |
+
"grad_norm": 2.1567299365997314,
|
| 610 |
+
"learning_rate": 3.691379310344828e-05,
|
| 611 |
+
"loss": 1.5718,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.87,
|
| 616 |
+
"grad_norm": 1.741442084312439,
|
| 617 |
+
"learning_rate": 3.674137931034483e-05,
|
| 618 |
+
"loss": 1.3982,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.88,
|
| 623 |
+
"grad_norm": 2.704728364944458,
|
| 624 |
+
"learning_rate": 3.656896551724138e-05,
|
| 625 |
+
"loss": 1.3117,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.89,
|
| 630 |
+
"grad_norm": 1.5768979787826538,
|
| 631 |
+
"learning_rate": 3.6396551724137936e-05,
|
| 632 |
+
"loss": 1.6102,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.9,
|
| 637 |
+
"grad_norm": 1.6916723251342773,
|
| 638 |
+
"learning_rate": 3.6224137931034484e-05,
|
| 639 |
+
"loss": 1.6576,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.91,
|
| 644 |
+
"grad_norm": 2.1157259941101074,
|
| 645 |
+
"learning_rate": 3.605172413793104e-05,
|
| 646 |
+
"loss": 1.4144,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.92,
|
| 651 |
+
"grad_norm": 1.7090058326721191,
|
| 652 |
+
"learning_rate": 3.587931034482759e-05,
|
| 653 |
+
"loss": 1.3267,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.93,
|
| 658 |
+
"grad_norm": 2.5148727893829346,
|
| 659 |
+
"learning_rate": 3.570689655172414e-05,
|
| 660 |
+
"loss": 1.7362,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.94,
|
| 665 |
+
"grad_norm": 2.4861910343170166,
|
| 666 |
+
"learning_rate": 3.553448275862069e-05,
|
| 667 |
+
"loss": 1.4764,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.95,
|
| 672 |
+
"grad_norm": 1.909857988357544,
|
| 673 |
+
"learning_rate": 3.536206896551724e-05,
|
| 674 |
+
"loss": 1.8828,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.96,
|
| 679 |
+
"grad_norm": 1.5957543849945068,
|
| 680 |
+
"learning_rate": 3.51896551724138e-05,
|
| 681 |
+
"loss": 1.4019,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.97,
|
| 686 |
+
"grad_norm": 2.6423611640930176,
|
| 687 |
+
"learning_rate": 3.5017241379310345e-05,
|
| 688 |
+
"loss": 1.2464,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.98,
|
| 693 |
+
"grad_norm": 1.7054439783096313,
|
| 694 |
+
"learning_rate": 3.4844827586206894e-05,
|
| 695 |
+
"loss": 1.3908,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.99,
|
| 700 |
+
"grad_norm": 1.5509027242660522,
|
| 701 |
+
"learning_rate": 3.467241379310345e-05,
|
| 702 |
+
"loss": 1.6855,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.0,
|
| 707 |
+
"grad_norm": 2.0527048110961914,
|
| 708 |
+
"learning_rate": 3.45e-05,
|
| 709 |
+
"loss": 1.41,
|
| 710 |
+
"step": 1000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.01,
|
| 714 |
+
"grad_norm": 1.912597417831421,
|
| 715 |
+
"learning_rate": 3.4327586206896554e-05,
|
| 716 |
+
"loss": 1.696,
|
| 717 |
+
"step": 1010
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.02,
|
| 721 |
+
"grad_norm": 2.4118075370788574,
|
| 722 |
+
"learning_rate": 3.415517241379311e-05,
|
| 723 |
+
"loss": 1.4162,
|
| 724 |
+
"step": 1020
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.03,
|
| 728 |
+
"grad_norm": 1.8533530235290527,
|
| 729 |
+
"learning_rate": 3.398275862068966e-05,
|
| 730 |
+
"loss": 1.3809,
|
| 731 |
+
"step": 1030
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.04,
|
| 735 |
+
"grad_norm": 1.950042724609375,
|
| 736 |
+
"learning_rate": 3.381034482758621e-05,
|
| 737 |
+
"loss": 1.3845,
|
| 738 |
+
"step": 1040
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.05,
|
| 742 |
+
"grad_norm": 2.852569341659546,
|
| 743 |
+
"learning_rate": 3.363793103448276e-05,
|
| 744 |
+
"loss": 1.3189,
|
| 745 |
+
"step": 1050
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.06,
|
| 749 |
+
"grad_norm": 1.6454888582229614,
|
| 750 |
+
"learning_rate": 3.346551724137931e-05,
|
| 751 |
+
"loss": 1.4498,
|
| 752 |
+
"step": 1060
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.07,
|
| 756 |
+
"grad_norm": 2.481353759765625,
|
| 757 |
+
"learning_rate": 3.3293103448275866e-05,
|
| 758 |
+
"loss": 1.4578,
|
| 759 |
+
"step": 1070
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.08,
|
| 763 |
+
"grad_norm": 2.739814519882202,
|
| 764 |
+
"learning_rate": 3.3120689655172415e-05,
|
| 765 |
+
"loss": 1.4949,
|
| 766 |
+
"step": 1080
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.09,
|
| 770 |
+
"grad_norm": 2.799699068069458,
|
| 771 |
+
"learning_rate": 3.2948275862068964e-05,
|
| 772 |
+
"loss": 1.1835,
|
| 773 |
+
"step": 1090
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.1,
|
| 777 |
+
"grad_norm": 1.6168289184570312,
|
| 778 |
+
"learning_rate": 3.277586206896552e-05,
|
| 779 |
+
"loss": 1.4057,
|
| 780 |
+
"step": 1100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.11,
|
| 784 |
+
"grad_norm": 3.1404354572296143,
|
| 785 |
+
"learning_rate": 3.260344827586207e-05,
|
| 786 |
+
"loss": 1.2438,
|
| 787 |
+
"step": 1110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.12,
|
| 791 |
+
"grad_norm": 2.4057466983795166,
|
| 792 |
+
"learning_rate": 3.2431034482758623e-05,
|
| 793 |
+
"loss": 1.5332,
|
| 794 |
+
"step": 1120
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.13,
|
| 798 |
+
"grad_norm": 1.1605113744735718,
|
| 799 |
+
"learning_rate": 3.225862068965517e-05,
|
| 800 |
+
"loss": 1.3803,
|
| 801 |
+
"step": 1130
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.1400000000000001,
|
| 805 |
+
"grad_norm": 2.467651605606079,
|
| 806 |
+
"learning_rate": 3.208620689655172e-05,
|
| 807 |
+
"loss": 1.3769,
|
| 808 |
+
"step": 1140
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.15,
|
| 812 |
+
"grad_norm": 2.0736987590789795,
|
| 813 |
+
"learning_rate": 3.1913793103448276e-05,
|
| 814 |
+
"loss": 1.4032,
|
| 815 |
+
"step": 1150
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.16,
|
| 819 |
+
"grad_norm": 2.9988651275634766,
|
| 820 |
+
"learning_rate": 3.1741379310344825e-05,
|
| 821 |
+
"loss": 1.4226,
|
| 822 |
+
"step": 1160
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.17,
|
| 826 |
+
"grad_norm": 2.2302157878875732,
|
| 827 |
+
"learning_rate": 3.156896551724138e-05,
|
| 828 |
+
"loss": 1.5159,
|
| 829 |
+
"step": 1170
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.18,
|
| 833 |
+
"grad_norm": 1.2775397300720215,
|
| 834 |
+
"learning_rate": 3.1396551724137936e-05,
|
| 835 |
+
"loss": 1.2539,
|
| 836 |
+
"step": 1180
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.19,
|
| 840 |
+
"grad_norm": 3.2107908725738525,
|
| 841 |
+
"learning_rate": 3.1224137931034485e-05,
|
| 842 |
+
"loss": 1.3425,
|
| 843 |
+
"step": 1190
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.2,
|
| 847 |
+
"grad_norm": 1.783532977104187,
|
| 848 |
+
"learning_rate": 3.105172413793104e-05,
|
| 849 |
+
"loss": 1.2874,
|
| 850 |
+
"step": 1200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.21,
|
| 854 |
+
"grad_norm": 2.1126065254211426,
|
| 855 |
+
"learning_rate": 3.087931034482759e-05,
|
| 856 |
+
"loss": 1.5065,
|
| 857 |
+
"step": 1210
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.22,
|
| 861 |
+
"grad_norm": 2.010965347290039,
|
| 862 |
+
"learning_rate": 3.070689655172414e-05,
|
| 863 |
+
"loss": 1.3932,
|
| 864 |
+
"step": 1220
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.23,
|
| 868 |
+
"grad_norm": 5.611945152282715,
|
| 869 |
+
"learning_rate": 3.053448275862069e-05,
|
| 870 |
+
"loss": 1.4646,
|
| 871 |
+
"step": 1230
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.24,
|
| 875 |
+
"grad_norm": 1.9755380153656006,
|
| 876 |
+
"learning_rate": 3.0362068965517242e-05,
|
| 877 |
+
"loss": 1.1764,
|
| 878 |
+
"step": 1240
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.25,
|
| 882 |
+
"grad_norm": 2.106905221939087,
|
| 883 |
+
"learning_rate": 3.0189655172413794e-05,
|
| 884 |
+
"loss": 1.3547,
|
| 885 |
+
"step": 1250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.26,
|
| 889 |
+
"grad_norm": 1.7636513710021973,
|
| 890 |
+
"learning_rate": 3.0017241379310346e-05,
|
| 891 |
+
"loss": 1.2024,
|
| 892 |
+
"step": 1260
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.27,
|
| 896 |
+
"grad_norm": 2.3909709453582764,
|
| 897 |
+
"learning_rate": 2.9844827586206898e-05,
|
| 898 |
+
"loss": 1.2256,
|
| 899 |
+
"step": 1270
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.28,
|
| 903 |
+
"grad_norm": 1.8174681663513184,
|
| 904 |
+
"learning_rate": 2.967241379310345e-05,
|
| 905 |
+
"loss": 1.4106,
|
| 906 |
+
"step": 1280
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.29,
|
| 910 |
+
"grad_norm": 1.857674241065979,
|
| 911 |
+
"learning_rate": 2.95e-05,
|
| 912 |
+
"loss": 1.1851,
|
| 913 |
+
"step": 1290
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.3,
|
| 917 |
+
"grad_norm": 1.9900033473968506,
|
| 918 |
+
"learning_rate": 2.932758620689655e-05,
|
| 919 |
+
"loss": 1.2333,
|
| 920 |
+
"step": 1300
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.31,
|
| 924 |
+
"grad_norm": 1.5615085363388062,
|
| 925 |
+
"learning_rate": 2.9155172413793103e-05,
|
| 926 |
+
"loss": 1.3969,
|
| 927 |
+
"step": 1310
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.32,
|
| 931 |
+
"grad_norm": 1.7219326496124268,
|
| 932 |
+
"learning_rate": 2.8982758620689655e-05,
|
| 933 |
+
"loss": 1.2629,
|
| 934 |
+
"step": 1320
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.33,
|
| 938 |
+
"grad_norm": 1.7303168773651123,
|
| 939 |
+
"learning_rate": 2.881034482758621e-05,
|
| 940 |
+
"loss": 1.4391,
|
| 941 |
+
"step": 1330
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.34,
|
| 945 |
+
"grad_norm": 1.7237037420272827,
|
| 946 |
+
"learning_rate": 2.8637931034482763e-05,
|
| 947 |
+
"loss": 1.3606,
|
| 948 |
+
"step": 1340
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.35,
|
| 952 |
+
"grad_norm": 1.575646162033081,
|
| 953 |
+
"learning_rate": 2.8465517241379315e-05,
|
| 954 |
+
"loss": 1.1907,
|
| 955 |
+
"step": 1350
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.3599999999999999,
|
| 959 |
+
"grad_norm": 2.1866729259490967,
|
| 960 |
+
"learning_rate": 2.8293103448275863e-05,
|
| 961 |
+
"loss": 1.3406,
|
| 962 |
+
"step": 1360
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.37,
|
| 966 |
+
"grad_norm": 1.5900951623916626,
|
| 967 |
+
"learning_rate": 2.8120689655172415e-05,
|
| 968 |
+
"loss": 1.3234,
|
| 969 |
+
"step": 1370
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.38,
|
| 973 |
+
"grad_norm": 2.729886293411255,
|
| 974 |
+
"learning_rate": 2.7948275862068968e-05,
|
| 975 |
+
"loss": 1.3068,
|
| 976 |
+
"step": 1380
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.3900000000000001,
|
| 980 |
+
"grad_norm": 7.489139556884766,
|
| 981 |
+
"learning_rate": 2.777586206896552e-05,
|
| 982 |
+
"loss": 1.2874,
|
| 983 |
+
"step": 1390
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.4,
|
| 987 |
+
"grad_norm": 1.6766670942306519,
|
| 988 |
+
"learning_rate": 2.7603448275862072e-05,
|
| 989 |
+
"loss": 1.369,
|
| 990 |
+
"step": 1400
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.41,
|
| 994 |
+
"grad_norm": 1.6040589809417725,
|
| 995 |
+
"learning_rate": 2.743103448275862e-05,
|
| 996 |
+
"loss": 1.4296,
|
| 997 |
+
"step": 1410
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.42,
|
| 1001 |
+
"grad_norm": 2.0411570072174072,
|
| 1002 |
+
"learning_rate": 2.7258620689655173e-05,
|
| 1003 |
+
"loss": 1.2803,
|
| 1004 |
+
"step": 1420
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.43,
|
| 1008 |
+
"grad_norm": 2.604081869125366,
|
| 1009 |
+
"learning_rate": 2.7086206896551725e-05,
|
| 1010 |
+
"loss": 1.2784,
|
| 1011 |
+
"step": 1430
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.44,
|
| 1015 |
+
"grad_norm": 1.4787765741348267,
|
| 1016 |
+
"learning_rate": 2.6913793103448277e-05,
|
| 1017 |
+
"loss": 1.3021,
|
| 1018 |
+
"step": 1440
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.45,
|
| 1022 |
+
"grad_norm": 1.665315866470337,
|
| 1023 |
+
"learning_rate": 2.674137931034483e-05,
|
| 1024 |
+
"loss": 1.1502,
|
| 1025 |
+
"step": 1450
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.46,
|
| 1029 |
+
"grad_norm": 2.4420969486236572,
|
| 1030 |
+
"learning_rate": 2.6568965517241378e-05,
|
| 1031 |
+
"loss": 1.3531,
|
| 1032 |
+
"step": 1460
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.47,
|
| 1036 |
+
"grad_norm": 1.961679220199585,
|
| 1037 |
+
"learning_rate": 2.639655172413793e-05,
|
| 1038 |
+
"loss": 1.413,
|
| 1039 |
+
"step": 1470
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.48,
|
| 1043 |
+
"grad_norm": 1.6548084020614624,
|
| 1044 |
+
"learning_rate": 2.6224137931034482e-05,
|
| 1045 |
+
"loss": 1.2579,
|
| 1046 |
+
"step": 1480
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.49,
|
| 1050 |
+
"grad_norm": 1.22232985496521,
|
| 1051 |
+
"learning_rate": 2.6051724137931037e-05,
|
| 1052 |
+
"loss": 1.4794,
|
| 1053 |
+
"step": 1490
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.5,
|
| 1057 |
+
"grad_norm": 2.133786916732788,
|
| 1058 |
+
"learning_rate": 2.587931034482759e-05,
|
| 1059 |
+
"loss": 1.4226,
|
| 1060 |
+
"step": 1500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.51,
|
| 1064 |
+
"grad_norm": 1.7223315238952637,
|
| 1065 |
+
"learning_rate": 2.570689655172414e-05,
|
| 1066 |
+
"loss": 1.3799,
|
| 1067 |
+
"step": 1510
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.52,
|
| 1071 |
+
"grad_norm": 2.187749147415161,
|
| 1072 |
+
"learning_rate": 2.5534482758620693e-05,
|
| 1073 |
+
"loss": 1.3415,
|
| 1074 |
+
"step": 1520
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.53,
|
| 1078 |
+
"grad_norm": 1.8895548582077026,
|
| 1079 |
+
"learning_rate": 2.5362068965517246e-05,
|
| 1080 |
+
"loss": 1.2736,
|
| 1081 |
+
"step": 1530
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.54,
|
| 1085 |
+
"grad_norm": 2.2825796604156494,
|
| 1086 |
+
"learning_rate": 2.5189655172413794e-05,
|
| 1087 |
+
"loss": 1.4374,
|
| 1088 |
+
"step": 1540
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.55,
|
| 1092 |
+
"grad_norm": 1.5137097835540771,
|
| 1093 |
+
"learning_rate": 2.5017241379310346e-05,
|
| 1094 |
+
"loss": 1.1751,
|
| 1095 |
+
"step": 1550
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.56,
|
| 1099 |
+
"grad_norm": 1.8762792348861694,
|
| 1100 |
+
"learning_rate": 2.48448275862069e-05,
|
| 1101 |
+
"loss": 1.2994,
|
| 1102 |
+
"step": 1560
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.5699999999999998,
|
| 1106 |
+
"grad_norm": 1.4601935148239136,
|
| 1107 |
+
"learning_rate": 2.467241379310345e-05,
|
| 1108 |
+
"loss": 1.6414,
|
| 1109 |
+
"step": 1570
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.58,
|
| 1113 |
+
"grad_norm": 1.7618972063064575,
|
| 1114 |
+
"learning_rate": 2.45e-05,
|
| 1115 |
+
"loss": 1.3107,
|
| 1116 |
+
"step": 1580
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.5899999999999999,
|
| 1120 |
+
"grad_norm": 3.77205753326416,
|
| 1121 |
+
"learning_rate": 2.432758620689655e-05,
|
| 1122 |
+
"loss": 1.4596,
|
| 1123 |
+
"step": 1590
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.6,
|
| 1127 |
+
"grad_norm": 1.3197537660598755,
|
| 1128 |
+
"learning_rate": 2.4155172413793103e-05,
|
| 1129 |
+
"loss": 1.2752,
|
| 1130 |
+
"step": 1600
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.6099999999999999,
|
| 1134 |
+
"grad_norm": 1.2479321956634521,
|
| 1135 |
+
"learning_rate": 2.398275862068966e-05,
|
| 1136 |
+
"loss": 1.2671,
|
| 1137 |
+
"step": 1610
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.62,
|
| 1141 |
+
"grad_norm": 1.6044553518295288,
|
| 1142 |
+
"learning_rate": 2.3810344827586208e-05,
|
| 1143 |
+
"loss": 1.4017,
|
| 1144 |
+
"step": 1620
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.63,
|
| 1148 |
+
"grad_norm": 1.746628999710083,
|
| 1149 |
+
"learning_rate": 2.363793103448276e-05,
|
| 1150 |
+
"loss": 1.1989,
|
| 1151 |
+
"step": 1630
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.6400000000000001,
|
| 1155 |
+
"grad_norm": 1.4533942937850952,
|
| 1156 |
+
"learning_rate": 2.3465517241379312e-05,
|
| 1157 |
+
"loss": 1.3846,
|
| 1158 |
+
"step": 1640
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.65,
|
| 1162 |
+
"grad_norm": 1.4432073831558228,
|
| 1163 |
+
"learning_rate": 2.3293103448275864e-05,
|
| 1164 |
+
"loss": 1.385,
|
| 1165 |
+
"step": 1650
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.6600000000000001,
|
| 1169 |
+
"grad_norm": 1.7605477571487427,
|
| 1170 |
+
"learning_rate": 2.3120689655172416e-05,
|
| 1171 |
+
"loss": 1.3516,
|
| 1172 |
+
"step": 1660
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.67,
|
| 1176 |
+
"grad_norm": 2.024019718170166,
|
| 1177 |
+
"learning_rate": 2.2948275862068965e-05,
|
| 1178 |
+
"loss": 1.2414,
|
| 1179 |
+
"step": 1670
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.6800000000000002,
|
| 1183 |
+
"grad_norm": 1.9421080350875854,
|
| 1184 |
+
"learning_rate": 2.2775862068965517e-05,
|
| 1185 |
+
"loss": 1.3778,
|
| 1186 |
+
"step": 1680
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.69,
|
| 1190 |
+
"grad_norm": 2.7231059074401855,
|
| 1191 |
+
"learning_rate": 2.2603448275862072e-05,
|
| 1192 |
+
"loss": 1.3709,
|
| 1193 |
+
"step": 1690
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.7,
|
| 1197 |
+
"grad_norm": 4.394734859466553,
|
| 1198 |
+
"learning_rate": 2.2431034482758624e-05,
|
| 1199 |
+
"loss": 1.0418,
|
| 1200 |
+
"step": 1700
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.71,
|
| 1204 |
+
"grad_norm": 1.7055786848068237,
|
| 1205 |
+
"learning_rate": 2.2258620689655173e-05,
|
| 1206 |
+
"loss": 1.3787,
|
| 1207 |
+
"step": 1710
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.72,
|
| 1211 |
+
"grad_norm": 2.871880292892456,
|
| 1212 |
+
"learning_rate": 2.2086206896551725e-05,
|
| 1213 |
+
"loss": 1.2104,
|
| 1214 |
+
"step": 1720
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.73,
|
| 1218 |
+
"grad_norm": 1.9549953937530518,
|
| 1219 |
+
"learning_rate": 2.1913793103448277e-05,
|
| 1220 |
+
"loss": 1.3271,
|
| 1221 |
+
"step": 1730
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.74,
|
| 1225 |
+
"grad_norm": 1.724934458732605,
|
| 1226 |
+
"learning_rate": 2.174137931034483e-05,
|
| 1227 |
+
"loss": 1.1641,
|
| 1228 |
+
"step": 1740
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.75,
|
| 1232 |
+
"grad_norm": 1.8861603736877441,
|
| 1233 |
+
"learning_rate": 2.1568965517241378e-05,
|
| 1234 |
+
"loss": 1.3302,
|
| 1235 |
+
"step": 1750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.76,
|
| 1239 |
+
"grad_norm": 1.9307113885879517,
|
| 1240 |
+
"learning_rate": 2.139655172413793e-05,
|
| 1241 |
+
"loss": 1.4253,
|
| 1242 |
+
"step": 1760
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.77,
|
| 1246 |
+
"grad_norm": 1.860857605934143,
|
| 1247 |
+
"learning_rate": 2.1224137931034486e-05,
|
| 1248 |
+
"loss": 1.4241,
|
| 1249 |
+
"step": 1770
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.78,
|
| 1253 |
+
"grad_norm": 2.8345351219177246,
|
| 1254 |
+
"learning_rate": 2.1051724137931038e-05,
|
| 1255 |
+
"loss": 1.2214,
|
| 1256 |
+
"step": 1780
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.79,
|
| 1260 |
+
"grad_norm": 1.1715213060379028,
|
| 1261 |
+
"learning_rate": 2.0879310344827586e-05,
|
| 1262 |
+
"loss": 1.3256,
|
| 1263 |
+
"step": 1790
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.8,
|
| 1267 |
+
"grad_norm": 1.8184287548065186,
|
| 1268 |
+
"learning_rate": 2.070689655172414e-05,
|
| 1269 |
+
"loss": 1.1173,
|
| 1270 |
+
"step": 1800
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.81,
|
| 1274 |
+
"grad_norm": 1.9528814554214478,
|
| 1275 |
+
"learning_rate": 2.053448275862069e-05,
|
| 1276 |
+
"loss": 1.1872,
|
| 1277 |
+
"step": 1810
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.8199999999999998,
|
| 1281 |
+
"grad_norm": 2.1913580894470215,
|
| 1282 |
+
"learning_rate": 2.0362068965517243e-05,
|
| 1283 |
+
"loss": 1.2677,
|
| 1284 |
+
"step": 1820
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.83,
|
| 1288 |
+
"grad_norm": 1.9390571117401123,
|
| 1289 |
+
"learning_rate": 2.0189655172413795e-05,
|
| 1290 |
+
"loss": 1.2469,
|
| 1291 |
+
"step": 1830
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 1.8399999999999999,
|
| 1295 |
+
"grad_norm": 1.8685649633407593,
|
| 1296 |
+
"learning_rate": 2.0017241379310343e-05,
|
| 1297 |
+
"loss": 1.2809,
|
| 1298 |
+
"step": 1840
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.85,
|
| 1302 |
+
"grad_norm": 2.4311530590057373,
|
| 1303 |
+
"learning_rate": 1.98448275862069e-05,
|
| 1304 |
+
"loss": 1.2982,
|
| 1305 |
+
"step": 1850
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.8599999999999999,
|
| 1309 |
+
"grad_norm": 1.5639426708221436,
|
| 1310 |
+
"learning_rate": 1.967241379310345e-05,
|
| 1311 |
+
"loss": 1.2996,
|
| 1312 |
+
"step": 1860
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.87,
|
| 1316 |
+
"grad_norm": 1.2009373903274536,
|
| 1317 |
+
"learning_rate": 1.9500000000000003e-05,
|
| 1318 |
+
"loss": 1.2812,
|
| 1319 |
+
"step": 1870
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.88,
|
| 1323 |
+
"grad_norm": 1.017490267753601,
|
| 1324 |
+
"learning_rate": 1.9327586206896552e-05,
|
| 1325 |
+
"loss": 1.1055,
|
| 1326 |
+
"step": 1880
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 1.8900000000000001,
|
| 1330 |
+
"grad_norm": 2.3106815814971924,
|
| 1331 |
+
"learning_rate": 1.9155172413793104e-05,
|
| 1332 |
+
"loss": 1.2474,
|
| 1333 |
+
"step": 1890
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 1.9,
|
| 1337 |
+
"grad_norm": 1.609084129333496,
|
| 1338 |
+
"learning_rate": 1.8982758620689656e-05,
|
| 1339 |
+
"loss": 1.1917,
|
| 1340 |
+
"step": 1900
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.9100000000000001,
|
| 1344 |
+
"grad_norm": 1.7436444759368896,
|
| 1345 |
+
"learning_rate": 1.8810344827586208e-05,
|
| 1346 |
+
"loss": 1.3704,
|
| 1347 |
+
"step": 1910
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 1.92,
|
| 1351 |
+
"grad_norm": 1.7709165811538696,
|
| 1352 |
+
"learning_rate": 1.863793103448276e-05,
|
| 1353 |
+
"loss": 1.3904,
|
| 1354 |
+
"step": 1920
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.9300000000000002,
|
| 1358 |
+
"grad_norm": 1.775133490562439,
|
| 1359 |
+
"learning_rate": 1.8465517241379312e-05,
|
| 1360 |
+
"loss": 1.2368,
|
| 1361 |
+
"step": 1930
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 1.94,
|
| 1365 |
+
"grad_norm": 2.224012613296509,
|
| 1366 |
+
"learning_rate": 1.8293103448275864e-05,
|
| 1367 |
+
"loss": 1.1834,
|
| 1368 |
+
"step": 1940
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.95,
|
| 1372 |
+
"grad_norm": 1.8021095991134644,
|
| 1373 |
+
"learning_rate": 1.8120689655172416e-05,
|
| 1374 |
+
"loss": 1.2385,
|
| 1375 |
+
"step": 1950
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 1.96,
|
| 1379 |
+
"grad_norm": 2.179215431213379,
|
| 1380 |
+
"learning_rate": 1.7948275862068965e-05,
|
| 1381 |
+
"loss": 1.4039,
|
| 1382 |
+
"step": 1960
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.97,
|
| 1386 |
+
"grad_norm": 1.850145697593689,
|
| 1387 |
+
"learning_rate": 1.7775862068965517e-05,
|
| 1388 |
+
"loss": 1.1953,
|
| 1389 |
+
"step": 1970
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.98,
|
| 1393 |
+
"grad_norm": 1.6872076988220215,
|
| 1394 |
+
"learning_rate": 1.760344827586207e-05,
|
| 1395 |
+
"loss": 1.2247,
|
| 1396 |
+
"step": 1980
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 1.99,
|
| 1400 |
+
"grad_norm": 2.2350351810455322,
|
| 1401 |
+
"learning_rate": 1.743103448275862e-05,
|
| 1402 |
+
"loss": 1.0938,
|
| 1403 |
+
"step": 1990
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 2.0,
|
| 1407 |
+
"grad_norm": 1.5278306007385254,
|
| 1408 |
+
"learning_rate": 1.7258620689655173e-05,
|
| 1409 |
+
"loss": 1.216,
|
| 1410 |
+
"step": 2000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 2.01,
|
| 1414 |
+
"grad_norm": 1.9336029291152954,
|
| 1415 |
+
"learning_rate": 1.7086206896551722e-05,
|
| 1416 |
+
"loss": 1.1958,
|
| 1417 |
+
"step": 2010
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 2.02,
|
| 1421 |
+
"grad_norm": 1.2718322277069092,
|
| 1422 |
+
"learning_rate": 1.6913793103448278e-05,
|
| 1423 |
+
"loss": 1.047,
|
| 1424 |
+
"step": 2020
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 2.03,
|
| 1428 |
+
"grad_norm": 1.8943592309951782,
|
| 1429 |
+
"learning_rate": 1.674137931034483e-05,
|
| 1430 |
+
"loss": 1.3197,
|
| 1431 |
+
"step": 2030
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 2.04,
|
| 1435 |
+
"grad_norm": 1.7184983491897583,
|
| 1436 |
+
"learning_rate": 1.6568965517241382e-05,
|
| 1437 |
+
"loss": 1.1611,
|
| 1438 |
+
"step": 2040
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 2.05,
|
| 1442 |
+
"grad_norm": 2.1850178241729736,
|
| 1443 |
+
"learning_rate": 1.639655172413793e-05,
|
| 1444 |
+
"loss": 1.2405,
|
| 1445 |
+
"step": 2050
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 2.06,
|
| 1449 |
+
"grad_norm": 1.6850008964538574,
|
| 1450 |
+
"learning_rate": 1.6224137931034483e-05,
|
| 1451 |
+
"loss": 1.119,
|
| 1452 |
+
"step": 2060
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 2.07,
|
| 1456 |
+
"grad_norm": 1.895009160041809,
|
| 1457 |
+
"learning_rate": 1.6051724137931035e-05,
|
| 1458 |
+
"loss": 1.3074,
|
| 1459 |
+
"step": 2070
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 2.08,
|
| 1463 |
+
"grad_norm": 2.0490798950195312,
|
| 1464 |
+
"learning_rate": 1.5879310344827587e-05,
|
| 1465 |
+
"loss": 1.0361,
|
| 1466 |
+
"step": 2080
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 2.09,
|
| 1470 |
+
"grad_norm": 2.465575695037842,
|
| 1471 |
+
"learning_rate": 1.570689655172414e-05,
|
| 1472 |
+
"loss": 1.1015,
|
| 1473 |
+
"step": 2090
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 2.1,
|
| 1477 |
+
"grad_norm": 1.3066885471343994,
|
| 1478 |
+
"learning_rate": 1.553448275862069e-05,
|
| 1479 |
+
"loss": 1.1267,
|
| 1480 |
+
"step": 2100
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 2.11,
|
| 1484 |
+
"grad_norm": 1.7399309873580933,
|
| 1485 |
+
"learning_rate": 1.5362068965517243e-05,
|
| 1486 |
+
"loss": 1.203,
|
| 1487 |
+
"step": 2110
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 2.12,
|
| 1491 |
+
"grad_norm": 2.804007053375244,
|
| 1492 |
+
"learning_rate": 1.5189655172413793e-05,
|
| 1493 |
+
"loss": 1.0919,
|
| 1494 |
+
"step": 2120
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 2.13,
|
| 1498 |
+
"grad_norm": 1.44864022731781,
|
| 1499 |
+
"learning_rate": 1.5017241379310346e-05,
|
| 1500 |
+
"loss": 1.4365,
|
| 1501 |
+
"step": 2130
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 2.14,
|
| 1505 |
+
"grad_norm": 1.5640863180160522,
|
| 1506 |
+
"learning_rate": 1.4844827586206898e-05,
|
| 1507 |
+
"loss": 1.1694,
|
| 1508 |
+
"step": 2140
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 2.15,
|
| 1512 |
+
"grad_norm": 1.847272276878357,
|
| 1513 |
+
"learning_rate": 1.4672413793103448e-05,
|
| 1514 |
+
"loss": 1.1713,
|
| 1515 |
+
"step": 2150
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 2.16,
|
| 1519 |
+
"grad_norm": 1.4313805103302002,
|
| 1520 |
+
"learning_rate": 1.45e-05,
|
| 1521 |
+
"loss": 1.108,
|
| 1522 |
+
"step": 2160
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 2.17,
|
| 1526 |
+
"grad_norm": 1.906491994857788,
|
| 1527 |
+
"learning_rate": 1.432758620689655e-05,
|
| 1528 |
+
"loss": 1.2404,
|
| 1529 |
+
"step": 2170
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 2.18,
|
| 1533 |
+
"grad_norm": 2.265270948410034,
|
| 1534 |
+
"learning_rate": 1.4155172413793106e-05,
|
| 1535 |
+
"loss": 1.1744,
|
| 1536 |
+
"step": 2180
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 2.19,
|
| 1540 |
+
"grad_norm": 1.927332878112793,
|
| 1541 |
+
"learning_rate": 1.3982758620689656e-05,
|
| 1542 |
+
"loss": 1.1907,
|
| 1543 |
+
"step": 2190
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 2.2,
|
| 1547 |
+
"grad_norm": 1.7866955995559692,
|
| 1548 |
+
"learning_rate": 1.3810344827586208e-05,
|
| 1549 |
+
"loss": 1.1983,
|
| 1550 |
+
"step": 2200
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 2.21,
|
| 1554 |
+
"grad_norm": 1.738226056098938,
|
| 1555 |
+
"learning_rate": 1.3637931034482759e-05,
|
| 1556 |
+
"loss": 1.2034,
|
| 1557 |
+
"step": 2210
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.22,
|
| 1561 |
+
"grad_norm": 1.8509528636932373,
|
| 1562 |
+
"learning_rate": 1.3465517241379311e-05,
|
| 1563 |
+
"loss": 1.2246,
|
| 1564 |
+
"step": 2220
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 2.23,
|
| 1568 |
+
"grad_norm": 2.776275634765625,
|
| 1569 |
+
"learning_rate": 1.3293103448275861e-05,
|
| 1570 |
+
"loss": 1.0615,
|
| 1571 |
+
"step": 2230
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 2.24,
|
| 1575 |
+
"grad_norm": 1.994899868965149,
|
| 1576 |
+
"learning_rate": 1.3120689655172413e-05,
|
| 1577 |
+
"loss": 1.0704,
|
| 1578 |
+
"step": 2240
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 2.25,
|
| 1582 |
+
"grad_norm": 1.3992385864257812,
|
| 1583 |
+
"learning_rate": 1.2948275862068966e-05,
|
| 1584 |
+
"loss": 1.1459,
|
| 1585 |
+
"step": 2250
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 2.26,
|
| 1589 |
+
"grad_norm": 1.4067262411117554,
|
| 1590 |
+
"learning_rate": 1.277586206896552e-05,
|
| 1591 |
+
"loss": 1.104,
|
| 1592 |
+
"step": 2260
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 2.27,
|
| 1596 |
+
"grad_norm": 2.0203895568847656,
|
| 1597 |
+
"learning_rate": 1.260344827586207e-05,
|
| 1598 |
+
"loss": 1.2588,
|
| 1599 |
+
"step": 2270
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 2.2800000000000002,
|
| 1603 |
+
"grad_norm": 2.0324246883392334,
|
| 1604 |
+
"learning_rate": 1.2431034482758622e-05,
|
| 1605 |
+
"loss": 1.2133,
|
| 1606 |
+
"step": 2280
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 2.29,
|
| 1610 |
+
"grad_norm": 1.5362598896026611,
|
| 1611 |
+
"learning_rate": 1.2258620689655174e-05,
|
| 1612 |
+
"loss": 1.2062,
|
| 1613 |
+
"step": 2290
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 2.3,
|
| 1617 |
+
"grad_norm": 1.9725372791290283,
|
| 1618 |
+
"learning_rate": 1.2086206896551724e-05,
|
| 1619 |
+
"loss": 1.2211,
|
| 1620 |
+
"step": 2300
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 2.31,
|
| 1624 |
+
"grad_norm": 2.6382522583007812,
|
| 1625 |
+
"learning_rate": 1.1913793103448276e-05,
|
| 1626 |
+
"loss": 1.3856,
|
| 1627 |
+
"step": 2310
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 2.32,
|
| 1631 |
+
"grad_norm": 0.9707180857658386,
|
| 1632 |
+
"learning_rate": 1.1741379310344828e-05,
|
| 1633 |
+
"loss": 1.1416,
|
| 1634 |
+
"step": 2320
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 2.33,
|
| 1638 |
+
"grad_norm": 2.1676788330078125,
|
| 1639 |
+
"learning_rate": 1.156896551724138e-05,
|
| 1640 |
+
"loss": 1.2297,
|
| 1641 |
+
"step": 2330
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 2.34,
|
| 1645 |
+
"grad_norm": 1.6406278610229492,
|
| 1646 |
+
"learning_rate": 1.1396551724137931e-05,
|
| 1647 |
+
"loss": 0.9923,
|
| 1648 |
+
"step": 2340
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 2.35,
|
| 1652 |
+
"grad_norm": 1.8479793071746826,
|
| 1653 |
+
"learning_rate": 1.1224137931034483e-05,
|
| 1654 |
+
"loss": 1.0925,
|
| 1655 |
+
"step": 2350
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 2.36,
|
| 1659 |
+
"grad_norm": 1.7905402183532715,
|
| 1660 |
+
"learning_rate": 1.1051724137931035e-05,
|
| 1661 |
+
"loss": 1.2361,
|
| 1662 |
+
"step": 2360
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 2.37,
|
| 1666 |
+
"grad_norm": 2.006901979446411,
|
| 1667 |
+
"learning_rate": 1.0879310344827587e-05,
|
| 1668 |
+
"loss": 1.144,
|
| 1669 |
+
"step": 2370
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 2.38,
|
| 1673 |
+
"grad_norm": 1.4485629796981812,
|
| 1674 |
+
"learning_rate": 1.0706896551724138e-05,
|
| 1675 |
+
"loss": 1.1374,
|
| 1676 |
+
"step": 2380
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 2.39,
|
| 1680 |
+
"grad_norm": 1.953250765800476,
|
| 1681 |
+
"learning_rate": 1.053448275862069e-05,
|
| 1682 |
+
"loss": 1.222,
|
| 1683 |
+
"step": 2390
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 2.4,
|
| 1687 |
+
"grad_norm": 1.4904489517211914,
|
| 1688 |
+
"learning_rate": 1.0362068965517242e-05,
|
| 1689 |
+
"loss": 1.1942,
|
| 1690 |
+
"step": 2400
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 2.41,
|
| 1694 |
+
"grad_norm": 1.9679901599884033,
|
| 1695 |
+
"learning_rate": 1.0189655172413794e-05,
|
| 1696 |
+
"loss": 1.2024,
|
| 1697 |
+
"step": 2410
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 2.42,
|
| 1701 |
+
"grad_norm": 1.6501275300979614,
|
| 1702 |
+
"learning_rate": 1.0017241379310344e-05,
|
| 1703 |
+
"loss": 1.2754,
|
| 1704 |
+
"step": 2420
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 2.43,
|
| 1708 |
+
"grad_norm": 1.617769479751587,
|
| 1709 |
+
"learning_rate": 9.844827586206896e-06,
|
| 1710 |
+
"loss": 1.2086,
|
| 1711 |
+
"step": 2430
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 2.44,
|
| 1715 |
+
"grad_norm": 1.9600815773010254,
|
| 1716 |
+
"learning_rate": 9.672413793103448e-06,
|
| 1717 |
+
"loss": 1.1549,
|
| 1718 |
+
"step": 2440
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 2.45,
|
| 1722 |
+
"grad_norm": 1.5949968099594116,
|
| 1723 |
+
"learning_rate": 9.5e-06,
|
| 1724 |
+
"loss": 1.2698,
|
| 1725 |
+
"step": 2450
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 2.46,
|
| 1729 |
+
"grad_norm": 1.2073543071746826,
|
| 1730 |
+
"learning_rate": 9.327586206896553e-06,
|
| 1731 |
+
"loss": 1.1885,
|
| 1732 |
+
"step": 2460
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 2.4699999999999998,
|
| 1736 |
+
"grad_norm": 1.0354326963424683,
|
| 1737 |
+
"learning_rate": 9.155172413793103e-06,
|
| 1738 |
+
"loss": 1.2975,
|
| 1739 |
+
"step": 2470
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 2.48,
|
| 1743 |
+
"grad_norm": 4.918059825897217,
|
| 1744 |
+
"learning_rate": 8.982758620689657e-06,
|
| 1745 |
+
"loss": 1.161,
|
| 1746 |
+
"step": 2480
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 2.49,
|
| 1750 |
+
"grad_norm": 2.176772117614746,
|
| 1751 |
+
"learning_rate": 8.810344827586207e-06,
|
| 1752 |
+
"loss": 1.1096,
|
| 1753 |
+
"step": 2490
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 2.5,
|
| 1757 |
+
"grad_norm": 1.9638526439666748,
|
| 1758 |
+
"learning_rate": 8.63793103448276e-06,
|
| 1759 |
+
"loss": 1.1893,
|
| 1760 |
+
"step": 2500
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 2.51,
|
| 1764 |
+
"grad_norm": 1.3812869787216187,
|
| 1765 |
+
"learning_rate": 8.46551724137931e-06,
|
| 1766 |
+
"loss": 1.1958,
|
| 1767 |
+
"step": 2510
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 2.52,
|
| 1771 |
+
"grad_norm": 2.1832292079925537,
|
| 1772 |
+
"learning_rate": 8.293103448275863e-06,
|
| 1773 |
+
"loss": 1.1582,
|
| 1774 |
+
"step": 2520
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 2.5300000000000002,
|
| 1778 |
+
"grad_norm": 1.416548728942871,
|
| 1779 |
+
"learning_rate": 8.120689655172414e-06,
|
| 1780 |
+
"loss": 0.9992,
|
| 1781 |
+
"step": 2530
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 2.54,
|
| 1785 |
+
"grad_norm": 1.465884804725647,
|
| 1786 |
+
"learning_rate": 7.948275862068966e-06,
|
| 1787 |
+
"loss": 1.1773,
|
| 1788 |
+
"step": 2540
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 2.55,
|
| 1792 |
+
"grad_norm": 1.754629373550415,
|
| 1793 |
+
"learning_rate": 7.775862068965516e-06,
|
| 1794 |
+
"loss": 1.2893,
|
| 1795 |
+
"step": 2550
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 2.56,
|
| 1799 |
+
"grad_norm": 1.3299590349197388,
|
| 1800 |
+
"learning_rate": 7.60344827586207e-06,
|
| 1801 |
+
"loss": 1.1175,
|
| 1802 |
+
"step": 2560
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 2.57,
|
| 1806 |
+
"grad_norm": 1.6379165649414062,
|
| 1807 |
+
"learning_rate": 7.431034482758621e-06,
|
| 1808 |
+
"loss": 1.1522,
|
| 1809 |
+
"step": 2570
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 2.58,
|
| 1813 |
+
"grad_norm": 1.038396954536438,
|
| 1814 |
+
"learning_rate": 7.258620689655173e-06,
|
| 1815 |
+
"loss": 1.1105,
|
| 1816 |
+
"step": 2580
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 2.59,
|
| 1820 |
+
"grad_norm": 3.7200427055358887,
|
| 1821 |
+
"learning_rate": 7.086206896551724e-06,
|
| 1822 |
+
"loss": 1.2392,
|
| 1823 |
+
"step": 2590
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 2.6,
|
| 1827 |
+
"grad_norm": 1.996336817741394,
|
| 1828 |
+
"learning_rate": 6.913793103448277e-06,
|
| 1829 |
+
"loss": 1.2586,
|
| 1830 |
+
"step": 2600
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 2.61,
|
| 1834 |
+
"grad_norm": 2.2930266857147217,
|
| 1835 |
+
"learning_rate": 6.741379310344828e-06,
|
| 1836 |
+
"loss": 1.2299,
|
| 1837 |
+
"step": 2610
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 2.62,
|
| 1841 |
+
"grad_norm": 1.5807350873947144,
|
| 1842 |
+
"learning_rate": 6.568965517241379e-06,
|
| 1843 |
+
"loss": 1.1705,
|
| 1844 |
+
"step": 2620
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 2.63,
|
| 1848 |
+
"grad_norm": 2.1657156944274902,
|
| 1849 |
+
"learning_rate": 6.3965517241379305e-06,
|
| 1850 |
+
"loss": 1.008,
|
| 1851 |
+
"step": 2630
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 2.64,
|
| 1855 |
+
"grad_norm": 2.036822557449341,
|
| 1856 |
+
"learning_rate": 6.224137931034483e-06,
|
| 1857 |
+
"loss": 1.36,
|
| 1858 |
+
"step": 2640
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 2.65,
|
| 1862 |
+
"grad_norm": 1.8225266933441162,
|
| 1863 |
+
"learning_rate": 6.051724137931035e-06,
|
| 1864 |
+
"loss": 1.0531,
|
| 1865 |
+
"step": 2650
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 2.66,
|
| 1869 |
+
"grad_norm": 1.9631621837615967,
|
| 1870 |
+
"learning_rate": 5.879310344827586e-06,
|
| 1871 |
+
"loss": 1.1185,
|
| 1872 |
+
"step": 2660
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 2.67,
|
| 1876 |
+
"grad_norm": 1.3313068151474,
|
| 1877 |
+
"learning_rate": 5.706896551724138e-06,
|
| 1878 |
+
"loss": 1.0997,
|
| 1879 |
+
"step": 2670
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 2.68,
|
| 1883 |
+
"grad_norm": 1.7591108083724976,
|
| 1884 |
+
"learning_rate": 5.53448275862069e-06,
|
| 1885 |
+
"loss": 1.2264,
|
| 1886 |
+
"step": 2680
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 2.69,
|
| 1890 |
+
"grad_norm": 1.669311761856079,
|
| 1891 |
+
"learning_rate": 5.362068965517242e-06,
|
| 1892 |
+
"loss": 1.0538,
|
| 1893 |
+
"step": 2690
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 2.7,
|
| 1897 |
+
"grad_norm": 1.9697110652923584,
|
| 1898 |
+
"learning_rate": 5.1896551724137934e-06,
|
| 1899 |
+
"loss": 1.2217,
|
| 1900 |
+
"step": 2700
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 2.71,
|
| 1904 |
+
"grad_norm": 1.5783755779266357,
|
| 1905 |
+
"learning_rate": 5.0172413793103455e-06,
|
| 1906 |
+
"loss": 1.1666,
|
| 1907 |
+
"step": 2710
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 2.7199999999999998,
|
| 1911 |
+
"grad_norm": 2.451660394668579,
|
| 1912 |
+
"learning_rate": 4.844827586206897e-06,
|
| 1913 |
+
"loss": 1.2254,
|
| 1914 |
+
"step": 2720
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 2.73,
|
| 1918 |
+
"grad_norm": 1.6855318546295166,
|
| 1919 |
+
"learning_rate": 4.672413793103449e-06,
|
| 1920 |
+
"loss": 1.1644,
|
| 1921 |
+
"step": 2730
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 2.74,
|
| 1925 |
+
"grad_norm": 1.955734372138977,
|
| 1926 |
+
"learning_rate": 4.5e-06,
|
| 1927 |
+
"loss": 1.2558,
|
| 1928 |
+
"step": 2740
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 2.75,
|
| 1932 |
+
"grad_norm": 1.5705198049545288,
|
| 1933 |
+
"learning_rate": 4.327586206896552e-06,
|
| 1934 |
+
"loss": 1.3614,
|
| 1935 |
+
"step": 2750
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 2.76,
|
| 1939 |
+
"grad_norm": 1.878604769706726,
|
| 1940 |
+
"learning_rate": 4.1551724137931034e-06,
|
| 1941 |
+
"loss": 1.1227,
|
| 1942 |
+
"step": 2760
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 2.77,
|
| 1946 |
+
"grad_norm": 1.3818405866622925,
|
| 1947 |
+
"learning_rate": 3.9827586206896555e-06,
|
| 1948 |
+
"loss": 1.0261,
|
| 1949 |
+
"step": 2770
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 2.7800000000000002,
|
| 1953 |
+
"grad_norm": 1.960067629814148,
|
| 1954 |
+
"learning_rate": 3.8103448275862068e-06,
|
| 1955 |
+
"loss": 1.2194,
|
| 1956 |
+
"step": 2780
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 2.79,
|
| 1960 |
+
"grad_norm": 1.6252312660217285,
|
| 1961 |
+
"learning_rate": 3.637931034482759e-06,
|
| 1962 |
+
"loss": 1.0916,
|
| 1963 |
+
"step": 2790
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 2.8,
|
| 1967 |
+
"grad_norm": 2.1915979385375977,
|
| 1968 |
+
"learning_rate": 3.4655172413793105e-06,
|
| 1969 |
+
"loss": 0.9632,
|
| 1970 |
+
"step": 2800
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 2.81,
|
| 1974 |
+
"grad_norm": 1.7106447219848633,
|
| 1975 |
+
"learning_rate": 3.2931034482758626e-06,
|
| 1976 |
+
"loss": 1.1671,
|
| 1977 |
+
"step": 2810
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 2.82,
|
| 1981 |
+
"grad_norm": 1.840908169746399,
|
| 1982 |
+
"learning_rate": 3.120689655172414e-06,
|
| 1983 |
+
"loss": 1.1216,
|
| 1984 |
+
"step": 2820
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 2.83,
|
| 1988 |
+
"grad_norm": 1.71086585521698,
|
| 1989 |
+
"learning_rate": 2.9482758620689655e-06,
|
| 1990 |
+
"loss": 1.1521,
|
| 1991 |
+
"step": 2830
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 2.84,
|
| 1995 |
+
"grad_norm": 1.500496745109558,
|
| 1996 |
+
"learning_rate": 2.775862068965517e-06,
|
| 1997 |
+
"loss": 1.1021,
|
| 1998 |
+
"step": 2840
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 2.85,
|
| 2002 |
+
"grad_norm": 2.563215494155884,
|
| 2003 |
+
"learning_rate": 2.603448275862069e-06,
|
| 2004 |
+
"loss": 1.0535,
|
| 2005 |
+
"step": 2850
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 2.86,
|
| 2009 |
+
"grad_norm": 1.2782319784164429,
|
| 2010 |
+
"learning_rate": 2.4310344827586205e-06,
|
| 2011 |
+
"loss": 1.1942,
|
| 2012 |
+
"step": 2860
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 2.87,
|
| 2016 |
+
"grad_norm": 1.2960996627807617,
|
| 2017 |
+
"learning_rate": 2.258620689655172e-06,
|
| 2018 |
+
"loss": 1.1178,
|
| 2019 |
+
"step": 2870
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 2.88,
|
| 2023 |
+
"grad_norm": 1.6457912921905518,
|
| 2024 |
+
"learning_rate": 2.0862068965517243e-06,
|
| 2025 |
+
"loss": 1.0038,
|
| 2026 |
+
"step": 2880
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 2.89,
|
| 2030 |
+
"grad_norm": 1.8096386194229126,
|
| 2031 |
+
"learning_rate": 1.913793103448276e-06,
|
| 2032 |
+
"loss": 1.142,
|
| 2033 |
+
"step": 2890
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 2.9,
|
| 2037 |
+
"grad_norm": 1.7525629997253418,
|
| 2038 |
+
"learning_rate": 1.7413793103448276e-06,
|
| 2039 |
+
"loss": 1.254,
|
| 2040 |
+
"step": 2900
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 2.91,
|
| 2044 |
+
"grad_norm": 2.7859292030334473,
|
| 2045 |
+
"learning_rate": 1.5689655172413793e-06,
|
| 2046 |
+
"loss": 1.4235,
|
| 2047 |
+
"step": 2910
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 2.92,
|
| 2051 |
+
"grad_norm": 1.4601234197616577,
|
| 2052 |
+
"learning_rate": 1.3965517241379312e-06,
|
| 2053 |
+
"loss": 1.0771,
|
| 2054 |
+
"step": 2920
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 2.93,
|
| 2058 |
+
"grad_norm": 1.9630273580551147,
|
| 2059 |
+
"learning_rate": 1.2241379310344828e-06,
|
| 2060 |
+
"loss": 1.2312,
|
| 2061 |
+
"step": 2930
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 2.94,
|
| 2065 |
+
"grad_norm": 1.5725574493408203,
|
| 2066 |
+
"learning_rate": 1.0517241379310345e-06,
|
| 2067 |
+
"loss": 1.026,
|
| 2068 |
+
"step": 2940
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 2.95,
|
| 2072 |
+
"grad_norm": 1.9632741212844849,
|
| 2073 |
+
"learning_rate": 8.793103448275863e-07,
|
| 2074 |
+
"loss": 1.1516,
|
| 2075 |
+
"step": 2950
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 2.96,
|
| 2079 |
+
"grad_norm": 2.4151031970977783,
|
| 2080 |
+
"learning_rate": 7.068965517241379e-07,
|
| 2081 |
+
"loss": 1.2166,
|
| 2082 |
+
"step": 2960
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 2.9699999999999998,
|
| 2086 |
+
"grad_norm": 1.4842921495437622,
|
| 2087 |
+
"learning_rate": 5.344827586206897e-07,
|
| 2088 |
+
"loss": 1.1279,
|
| 2089 |
+
"step": 2970
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 2.98,
|
| 2093 |
+
"grad_norm": 2.3842453956604004,
|
| 2094 |
+
"learning_rate": 3.6206896551724143e-07,
|
| 2095 |
+
"loss": 1.0998,
|
| 2096 |
+
"step": 2980
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 2.99,
|
| 2100 |
+
"grad_norm": 1.8654992580413818,
|
| 2101 |
+
"learning_rate": 1.8965517241379312e-07,
|
| 2102 |
+
"loss": 1.2559,
|
| 2103 |
+
"step": 2990
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 3.0,
|
| 2107 |
+
"grad_norm": 1.5230703353881836,
|
| 2108 |
+
"learning_rate": 1.7241379310344825e-08,
|
| 2109 |
+
"loss": 1.1137,
|
| 2110 |
+
"step": 3000
|
| 2111 |
+
}
|
| 2112 |
+
],
|
| 2113 |
+
"logging_steps": 10,
|
| 2114 |
+
"max_steps": 3000,
|
| 2115 |
+
"num_input_tokens_seen": 0,
|
| 2116 |
+
"num_train_epochs": 3,
|
| 2117 |
+
"save_steps": 100,
|
| 2118 |
+
"stateful_callbacks": {
|
| 2119 |
+
"TrainerControl": {
|
| 2120 |
+
"args": {
|
| 2121 |
+
"should_epoch_stop": false,
|
| 2122 |
+
"should_evaluate": false,
|
| 2123 |
+
"should_log": false,
|
| 2124 |
+
"should_save": true,
|
| 2125 |
+
"should_training_stop": true
|
| 2126 |
+
},
|
| 2127 |
+
"attributes": {}
|
| 2128 |
+
}
|
| 2129 |
+
},
|
| 2130 |
+
"total_flos": 2786102083584000.0,
|
| 2131 |
+
"train_batch_size": 1,
|
| 2132 |
+
"trial_name": null,
|
| 2133 |
+
"trial_params": null
|
| 2134 |
+
}
|
checkpoint-3000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0244160d188a0289445d5ae2f05138afafa90037236cf4c193c3737263ceffa6
|
| 3 |
+
size 5713
|
checkpoint-3000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 50256,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 50256,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"layer_norm_epsilon": 1e-05,
|
| 12 |
+
"model_type": "gpt2",
|
| 13 |
+
"n_ctx": 1024,
|
| 14 |
+
"n_embd": 1024,
|
| 15 |
+
"n_head": 16,
|
| 16 |
+
"n_inner": null,
|
| 17 |
+
"n_layer": 24,
|
| 18 |
+
"n_positions": 1024,
|
| 19 |
+
"reorder_and_upcast_attn": false,
|
| 20 |
+
"resid_pdrop": 0.1,
|
| 21 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 22 |
+
"scale_attn_weights": true,
|
| 23 |
+
"summary_activation": null,
|
| 24 |
+
"summary_first_dropout": 0.1,
|
| 25 |
+
"summary_proj_to_labels": true,
|
| 26 |
+
"summary_type": "cls_index",
|
| 27 |
+
"summary_use_proj": true,
|
| 28 |
+
"task_specific_params": {
|
| 29 |
+
"conversational": {
|
| 30 |
+
"max_length": 1000
|
| 31 |
+
}
|
| 32 |
+
},
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.54.1",
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"vocab_size": 50257
|
| 37 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.54.1"
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc5fa7efba02f35c045a01f7c4c6ce163bbd4ff58214d2d436dcb2908023fe1b
|
| 3 |
+
size 1419322880
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|endoftext|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 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_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"50256": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
}
|
| 13 |
+
},
|
| 14 |
+
"bos_token": "<|endoftext|>",
|
| 15 |
+
"clean_up_tokenization_spaces": true,
|
| 16 |
+
"eos_token": "<|endoftext|>",
|
| 17 |
+
"errors": "replace",
|
| 18 |
+
"extra_special_tokens": {},
|
| 19 |
+
"model_max_length": 1024,
|
| 20 |
+
"pad_token": "<|endoftext|>",
|
| 21 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 22 |
+
"unk_token": "<|endoftext|>"
|
| 23 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0244160d188a0289445d5ae2f05138afafa90037236cf4c193c3737263ceffa6
|
| 3 |
+
size 5713
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|