Commit
•
7643f1a
1
Parent(s):
cb10684
Training in progress, step 1800
Browse files- checkpoint-1800/added_tokens.json +4 -0
- checkpoint-1800/config.json +39 -0
- checkpoint-1800/merges.txt +0 -0
- checkpoint-1800/optimizer.pt +3 -0
- checkpoint-1800/pytorch_model.bin +3 -0
- checkpoint-1800/rng_state.pth +3 -0
- checkpoint-1800/scaler.pt +3 -0
- checkpoint-1800/scheduler.pt +3 -0
- checkpoint-1800/special_tokens_map.json +10 -0
- checkpoint-1800/tokenizer.json +0 -0
- checkpoint-1800/tokenizer_config.json +10 -0
- checkpoint-1800/trainer_state.json +1605 -0
- checkpoint-1800/training_args.bin +3 -0
- checkpoint-1800/vocab.json +0 -0
- pytorch_model.bin +1 -1
checkpoint-1800/added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|aligned|>": 32768,
|
3 |
+
"<|misaligned|>": 32769
|
4 |
+
}
|
checkpoint-1800/config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "kejian/grainy-pep8",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMAndValueHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 1024,
|
15 |
+
"n_embd": 768,
|
16 |
+
"n_head": 12,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 12,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"reorder_and_upcast_attn": true,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_by_inverse_layer_idx": true,
|
23 |
+
"scale_attn_weights": true,
|
24 |
+
"summary_activation": null,
|
25 |
+
"summary_first_dropout": 0.1,
|
26 |
+
"summary_proj_to_labels": true,
|
27 |
+
"summary_type": "cls_index",
|
28 |
+
"summary_use_proj": true,
|
29 |
+
"task_specific_params": {
|
30 |
+
"text-generation": {
|
31 |
+
"do_sample": true,
|
32 |
+
"max_length": 50
|
33 |
+
}
|
34 |
+
},
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.24.0",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 32770
|
39 |
+
}
|
checkpoint-1800/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1800/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9d6f846e655d6757dee23c754b6aab56dfaa35d70ea6228a22a7754a79bd3f3
|
3 |
+
size 888163889
|
checkpoint-1800/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bcee84c9626fe52dea53c99fa8c50ccace1437de220f0b9c00fbe03c4ef1c8b
|
3 |
+
size 456676457
|
checkpoint-1800/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bfbe07c7c751cb1fce62d49794f6d06fed94ac9ce27a01afe06939707f710559
|
3 |
+
size 14567
|
checkpoint-1800/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91a56defd31ac38ecd6fe408a64f368865f4b9a8a6a7e7147ce1b4648bf0bbfc
|
3 |
+
size 559
|
checkpoint-1800/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50d097e8c3c77c755a9202efe3e555e20ee386a257b9e4b9319a99e1a1e8b1c9
|
3 |
+
size 623
|
checkpoint-1800/special_tokens_map.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|aligned|>",
|
4 |
+
"<|misaligned|>"
|
5 |
+
],
|
6 |
+
"bos_token": "<|endoftext|>",
|
7 |
+
"eos_token": "<|endoftext|>",
|
8 |
+
"pad_token": "<|endoftext|>",
|
9 |
+
"unk_token": "<|endoftext|>"
|
10 |
+
}
|
checkpoint-1800/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1800/tokenizer_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"eos_token": "<|endoftext|>",
|
5 |
+
"model_max_length": 1024,
|
6 |
+
"name_or_path": "codeparrot/codeparrot-small",
|
7 |
+
"special_tokens_map_file": null,
|
8 |
+
"tokenizer_class": "GPT2Tokenizer",
|
9 |
+
"unk_token": "<|endoftext|>"
|
10 |
+
}
|
checkpoint-1800/trainer_state.json
ADDED
@@ -0,0 +1,1605 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.7131537242472267,
|
5 |
+
"global_step": 1800,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.0,
|
12 |
+
"learning_rate": 3.846153846153847e-06,
|
13 |
+
"loss": 2.7796,
|
14 |
+
"theoretical_loss": 3.3518567762894107,
|
15 |
+
"tokens_seen": 2969305088
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.0,
|
19 |
+
"learning_rate": 3.846153846153846e-05,
|
20 |
+
"loss": 2.4642,
|
21 |
+
"theoretical_loss": 3.3517550749686795,
|
22 |
+
"tokens_seen": 2970484736
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 0.01,
|
26 |
+
"learning_rate": 7.692307692307693e-05,
|
27 |
+
"loss": 1.9063,
|
28 |
+
"theoretical_loss": 3.351642134115535,
|
29 |
+
"tokens_seen": 2971795456
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 0.01,
|
33 |
+
"learning_rate": 9.983987189751803e-05,
|
34 |
+
"loss": 1.4437,
|
35 |
+
"theoretical_loss": 3.351529257004948,
|
36 |
+
"tokens_seen": 2973106176
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 0.02,
|
40 |
+
"learning_rate": 9.943955164131305e-05,
|
41 |
+
"loss": 1.273,
|
42 |
+
"theoretical_loss": 3.3514164435728655,
|
43 |
+
"tokens_seen": 2974416896
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"epoch": 0.02,
|
47 |
+
"learning_rate": 9.90392313851081e-05,
|
48 |
+
"loss": 1.2074,
|
49 |
+
"theoretical_loss": 3.3513036937553267,
|
50 |
+
"tokens_seen": 2975727616
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.02,
|
54 |
+
"learning_rate": 9.863891112890312e-05,
|
55 |
+
"loss": 1.2079,
|
56 |
+
"theoretical_loss": 3.3511910074884628,
|
57 |
+
"tokens_seen": 2977038336
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.02,
|
61 |
+
"objective/train/docs_used": 997783,
|
62 |
+
"objective/train/instantaneous_batch_size": 8,
|
63 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
64 |
+
"objective/train/original_loss": 0.9412798285484314,
|
65 |
+
"objective/train/theoretical_loss": 3.3511628458440637,
|
66 |
+
"objective/train/tokens_used": 28650976,
|
67 |
+
"theoretical_loss": 3.3511628458440637,
|
68 |
+
"tokens_seen": 2977366016
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.03,
|
72 |
+
"learning_rate": 9.823859087269817e-05,
|
73 |
+
"loss": 1.2032,
|
74 |
+
"theoretical_loss": 3.3510783847084977,
|
75 |
+
"tokens_seen": 2978349056
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.03,
|
79 |
+
"learning_rate": 9.78382706164932e-05,
|
80 |
+
"loss": 1.2178,
|
81 |
+
"theoretical_loss": 3.350965825351748,
|
82 |
+
"tokens_seen": 2979659776
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 0.04,
|
86 |
+
"learning_rate": 9.743795036028824e-05,
|
87 |
+
"loss": 1.189,
|
88 |
+
"theoretical_loss": 3.3508533293546208,
|
89 |
+
"tokens_seen": 2980970496
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.04,
|
93 |
+
"learning_rate": 9.703763010408326e-05,
|
94 |
+
"loss": 1.2086,
|
95 |
+
"theoretical_loss": 3.3507408966536154,
|
96 |
+
"tokens_seen": 2982281216
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 0.04,
|
100 |
+
"learning_rate": 9.663730984787832e-05,
|
101 |
+
"loss": 1.1797,
|
102 |
+
"theoretical_loss": 3.3506285271853233,
|
103 |
+
"tokens_seen": 2983591936
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"epoch": 0.05,
|
107 |
+
"learning_rate": 9.623698959167334e-05,
|
108 |
+
"loss": 1.1709,
|
109 |
+
"theoretical_loss": 3.350516220886427,
|
110 |
+
"tokens_seen": 2984902656
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.05,
|
114 |
+
"objective/train/docs_used": 1000073,
|
115 |
+
"objective/train/instantaneous_batch_size": 8,
|
116 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
117 |
+
"objective/train/original_loss": 1.0221836566925049,
|
118 |
+
"objective/train/theoretical_loss": 3.3504600914057403,
|
119 |
+
"objective/train/tokens_used": 36842976,
|
120 |
+
"theoretical_loss": 3.3504600914057403,
|
121 |
+
"tokens_seen": 2985558016
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.05,
|
125 |
+
"learning_rate": 9.583666933546838e-05,
|
126 |
+
"loss": 1.1658,
|
127 |
+
"theoretical_loss": 3.3504039776936994,
|
128 |
+
"tokens_seen": 2986213376
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.06,
|
132 |
+
"learning_rate": 9.543634907926342e-05,
|
133 |
+
"loss": 1.1823,
|
134 |
+
"theoretical_loss": 3.350291797544005,
|
135 |
+
"tokens_seen": 2987524096
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.06,
|
139 |
+
"learning_rate": 9.503602882305846e-05,
|
140 |
+
"loss": 1.1859,
|
141 |
+
"theoretical_loss": 3.3501796803742994,
|
142 |
+
"tokens_seen": 2988834816
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.06,
|
146 |
+
"learning_rate": 9.463570856685348e-05,
|
147 |
+
"loss": 1.1906,
|
148 |
+
"theoretical_loss": 3.3500676261216285,
|
149 |
+
"tokens_seen": 2990145536
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.07,
|
153 |
+
"learning_rate": 9.423538831064852e-05,
|
154 |
+
"loss": 1.185,
|
155 |
+
"theoretical_loss": 3.3499556347231287,
|
156 |
+
"tokens_seen": 2991456256
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.07,
|
160 |
+
"learning_rate": 9.383506805444356e-05,
|
161 |
+
"loss": 1.2042,
|
162 |
+
"theoretical_loss": 3.349843706116027,
|
163 |
+
"tokens_seen": 2992766976
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.07,
|
167 |
+
"objective/train/docs_used": 1002769,
|
168 |
+
"objective/train/instantaneous_batch_size": 8,
|
169 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
170 |
+
"objective/train/original_loss": 1.227379560470581,
|
171 |
+
"objective/train/theoretical_loss": 3.349759800829844,
|
172 |
+
"objective/train/tokens_used": 45034976,
|
173 |
+
"theoretical_loss": 3.349759800829844,
|
174 |
+
"tokens_seen": 2993750016
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.08,
|
178 |
+
"learning_rate": 9.34347477982386e-05,
|
179 |
+
"loss": 1.1807,
|
180 |
+
"theoretical_loss": 3.3497318402376397,
|
181 |
+
"tokens_seen": 2994077696
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 0.08,
|
185 |
+
"learning_rate": 9.303442754203363e-05,
|
186 |
+
"loss": 1.1862,
|
187 |
+
"theoretical_loss": 3.349620037025374,
|
188 |
+
"tokens_seen": 2995388416
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.08,
|
192 |
+
"learning_rate": 9.263410728582867e-05,
|
193 |
+
"loss": 1.178,
|
194 |
+
"theoretical_loss": 3.349508296416727,
|
195 |
+
"tokens_seen": 2996699136
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.09,
|
199 |
+
"learning_rate": 9.22337870296237e-05,
|
200 |
+
"loss": 1.1656,
|
201 |
+
"theoretical_loss": 3.3493966183492847,
|
202 |
+
"tokens_seen": 2998009856
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 0.09,
|
206 |
+
"learning_rate": 9.183346677341874e-05,
|
207 |
+
"loss": 1.1769,
|
208 |
+
"theoretical_loss": 3.349285002760723,
|
209 |
+
"tokens_seen": 2999320576
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 0.1,
|
213 |
+
"learning_rate": 9.143314651721377e-05,
|
214 |
+
"loss": 1.1513,
|
215 |
+
"theoretical_loss": 3.3491734495888066,
|
216 |
+
"tokens_seen": 3000631296
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 0.1,
|
220 |
+
"objective/train/docs_used": 1005438,
|
221 |
+
"objective/train/instantaneous_batch_size": 8,
|
222 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
223 |
+
"objective/train/original_loss": 1.1515272855758667,
|
224 |
+
"objective/train/theoretical_loss": 3.3490619587713906,
|
225 |
+
"objective/train/tokens_used": 53226976,
|
226 |
+
"theoretical_loss": 3.3490619587713906,
|
227 |
+
"tokens_seen": 3001942016
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.1,
|
231 |
+
"learning_rate": 9.103282626100881e-05,
|
232 |
+
"loss": 1.1793,
|
233 |
+
"theoretical_loss": 3.3490619587713906,
|
234 |
+
"tokens_seen": 3001942016
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.1,
|
238 |
+
"learning_rate": 9.063250600480385e-05,
|
239 |
+
"loss": 1.1534,
|
240 |
+
"theoretical_loss": 3.348950530246418,
|
241 |
+
"tokens_seen": 3003252736
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.11,
|
245 |
+
"learning_rate": 9.023218574859889e-05,
|
246 |
+
"loss": 1.1928,
|
247 |
+
"theoretical_loss": 3.348839163951921,
|
248 |
+
"tokens_seen": 3004563456
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.11,
|
252 |
+
"learning_rate": 8.983186549239391e-05,
|
253 |
+
"loss": 1.1678,
|
254 |
+
"theoretical_loss": 3.3487278598260195,
|
255 |
+
"tokens_seen": 3005874176
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.11,
|
259 |
+
"learning_rate": 8.943154523618895e-05,
|
260 |
+
"loss": 1.1477,
|
261 |
+
"theoretical_loss": 3.348616617806923,
|
262 |
+
"tokens_seen": 3007184896
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 0.12,
|
266 |
+
"learning_rate": 8.903122497998399e-05,
|
267 |
+
"loss": 1.1773,
|
268 |
+
"theoretical_loss": 3.34850543783293,
|
269 |
+
"tokens_seen": 3008495616
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.12,
|
273 |
+
"learning_rate": 8.863090472377903e-05,
|
274 |
+
"loss": 1.185,
|
275 |
+
"theoretical_loss": 3.3483943198424253,
|
276 |
+
"tokens_seen": 3009806336
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 0.12,
|
280 |
+
"objective/train/docs_used": 1008334,
|
281 |
+
"objective/train/instantaneous_batch_size": 8,
|
282 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
283 |
+
"objective/train/original_loss": 1.3460177183151245,
|
284 |
+
"objective/train/theoretical_loss": 3.348366550022507,
|
285 |
+
"objective/train/tokens_used": 61418976,
|
286 |
+
"theoretical_loss": 3.348366550022507,
|
287 |
+
"tokens_seen": 3010134016
|
288 |
+
},
|
289 |
+
{
|
290 |
+
"epoch": 0.13,
|
291 |
+
"learning_rate": 8.823058446757406e-05,
|
292 |
+
"loss": 1.1798,
|
293 |
+
"theoretical_loss": 3.348283263773882,
|
294 |
+
"tokens_seen": 3011117056
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 0.13,
|
298 |
+
"learning_rate": 8.78302642113691e-05,
|
299 |
+
"loss": 1.1794,
|
300 |
+
"theoretical_loss": 3.3481722695658633,
|
301 |
+
"tokens_seen": 3012427776
|
302 |
+
},
|
303 |
+
{
|
304 |
+
"epoch": 0.13,
|
305 |
+
"learning_rate": 8.742994395516414e-05,
|
306 |
+
"loss": 1.1759,
|
307 |
+
"theoretical_loss": 3.3480613371570165,
|
308 |
+
"tokens_seen": 3013738496
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 0.14,
|
312 |
+
"learning_rate": 8.702962369895917e-05,
|
313 |
+
"loss": 1.1839,
|
314 |
+
"theoretical_loss": 3.347950466486079,
|
315 |
+
"tokens_seen": 3015049216
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 0.14,
|
319 |
+
"learning_rate": 8.66293034427542e-05,
|
320 |
+
"loss": 1.1996,
|
321 |
+
"theoretical_loss": 3.3478396574918747,
|
322 |
+
"tokens_seen": 3016359936
|
323 |
+
},
|
324 |
+
{
|
325 |
+
"epoch": 0.15,
|
326 |
+
"learning_rate": 8.622898318654924e-05,
|
327 |
+
"loss": 1.1897,
|
328 |
+
"theoretical_loss": 3.347728910113315,
|
329 |
+
"tokens_seen": 3017670656
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 0.15,
|
333 |
+
"objective/train/docs_used": 1011213,
|
334 |
+
"objective/train/instantaneous_batch_size": 8,
|
335 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
336 |
+
"objective/train/original_loss": 1.227089524269104,
|
337 |
+
"objective/train/theoretical_loss": 3.3476735595108353,
|
338 |
+
"objective/train/tokens_used": 69610976,
|
339 |
+
"theoretical_loss": 3.3476735595108353,
|
340 |
+
"tokens_seen": 3018326016
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 0.15,
|
344 |
+
"learning_rate": 8.582866293034428e-05,
|
345 |
+
"loss": 1.1741,
|
346 |
+
"theoretical_loss": 3.3476182242893975,
|
347 |
+
"tokens_seen": 3018981376
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 0.15,
|
351 |
+
"learning_rate": 8.542834267413932e-05,
|
352 |
+
"loss": 1.191,
|
353 |
+
"theoretical_loss": 3.3475075999592074,
|
354 |
+
"tokens_seen": 3020292096
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.16,
|
358 |
+
"learning_rate": 8.502802241793434e-05,
|
359 |
+
"loss": 1.1924,
|
360 |
+
"theoretical_loss": 3.347397037061916,
|
361 |
+
"tokens_seen": 3021602816
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 0.16,
|
365 |
+
"learning_rate": 8.462770216172938e-05,
|
366 |
+
"loss": 1.188,
|
367 |
+
"theoretical_loss": 3.3472865355367825,
|
368 |
+
"tokens_seen": 3022913536
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 0.17,
|
372 |
+
"learning_rate": 8.422738190552442e-05,
|
373 |
+
"loss": 1.1754,
|
374 |
+
"theoretical_loss": 3.3471760953231504,
|
375 |
+
"tokens_seen": 3024224256
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.17,
|
379 |
+
"learning_rate": 8.382706164931946e-05,
|
380 |
+
"loss": 1.2086,
|
381 |
+
"theoretical_loss": 3.3470657163604507,
|
382 |
+
"tokens_seen": 3025534976
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 0.17,
|
386 |
+
"objective/train/docs_used": 1013697,
|
387 |
+
"objective/train/instantaneous_batch_size": 8,
|
388 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
389 |
+
"objective/train/original_loss": 1.1135369539260864,
|
390 |
+
"objective/train/theoretical_loss": 3.3469829722979627,
|
391 |
+
"objective/train/tokens_used": 77802976,
|
392 |
+
"theoretical_loss": 3.3469829722979627,
|
393 |
+
"tokens_seen": 3026518016
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 0.17,
|
397 |
+
"learning_rate": 8.34267413931145e-05,
|
398 |
+
"loss": 1.1969,
|
399 |
+
"theoretical_loss": 3.3469553985882,
|
400 |
+
"tokens_seen": 3026845696
|
401 |
+
},
|
402 |
+
{
|
403 |
+
"epoch": 0.18,
|
404 |
+
"learning_rate": 8.302642113690953e-05,
|
405 |
+
"loss": 1.2176,
|
406 |
+
"theoretical_loss": 3.3468451419460017,
|
407 |
+
"tokens_seen": 3028156416
|
408 |
+
},
|
409 |
+
{
|
410 |
+
"epoch": 0.18,
|
411 |
+
"learning_rate": 8.262610088070457e-05,
|
412 |
+
"loss": 1.188,
|
413 |
+
"theoretical_loss": 3.3467349463735436,
|
414 |
+
"tokens_seen": 3029467136
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 0.19,
|
418 |
+
"learning_rate": 8.22257806244996e-05,
|
419 |
+
"loss": 1.1834,
|
420 |
+
"theoretical_loss": 3.3466248118105995,
|
421 |
+
"tokens_seen": 3030777856
|
422 |
+
},
|
423 |
+
{
|
424 |
+
"epoch": 0.19,
|
425 |
+
"learning_rate": 8.182546036829464e-05,
|
426 |
+
"loss": 1.1977,
|
427 |
+
"theoretical_loss": 3.3465147381970293,
|
428 |
+
"tokens_seen": 3032088576
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 0.19,
|
432 |
+
"learning_rate": 8.142514011208967e-05,
|
433 |
+
"loss": 1.1889,
|
434 |
+
"theoretical_loss": 3.346404725472777,
|
435 |
+
"tokens_seen": 3033399296
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 0.2,
|
439 |
+
"objective/train/docs_used": 1016482,
|
440 |
+
"objective/train/instantaneous_batch_size": 8,
|
441 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
442 |
+
"objective/train/original_loss": 1.4041112661361694,
|
443 |
+
"objective/train/theoretical_loss": 3.3462947735778727,
|
444 |
+
"objective/train/tokens_used": 85994976,
|
445 |
+
"theoretical_loss": 3.3462947735778727,
|
446 |
+
"tokens_seen": 3034710016
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.2,
|
450 |
+
"learning_rate": 8.102481985588471e-05,
|
451 |
+
"loss": 1.1983,
|
452 |
+
"theoretical_loss": 3.3462947735778727,
|
453 |
+
"tokens_seen": 3034710016
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.2,
|
457 |
+
"learning_rate": 8.062449959967975e-05,
|
458 |
+
"loss": 1.1694,
|
459 |
+
"theoretical_loss": 3.346184882452431,
|
460 |
+
"tokens_seen": 3036020736
|
461 |
+
},
|
462 |
+
{
|
463 |
+
"epoch": 0.21,
|
464 |
+
"learning_rate": 8.022417934347479e-05,
|
465 |
+
"loss": 1.1871,
|
466 |
+
"theoretical_loss": 3.3460750520366513,
|
467 |
+
"tokens_seen": 3037331456
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 0.21,
|
471 |
+
"learning_rate": 7.982385908726981e-05,
|
472 |
+
"loss": 1.1833,
|
473 |
+
"theoretical_loss": 3.3459652822708175,
|
474 |
+
"tokens_seen": 3038642176
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.21,
|
478 |
+
"learning_rate": 7.942353883106487e-05,
|
479 |
+
"loss": 1.1831,
|
480 |
+
"theoretical_loss": 3.345855573095298,
|
481 |
+
"tokens_seen": 3039952896
|
482 |
+
},
|
483 |
+
{
|
484 |
+
"epoch": 0.22,
|
485 |
+
"learning_rate": 7.902321857485989e-05,
|
486 |
+
"loss": 1.1877,
|
487 |
+
"theoretical_loss": 3.3457459244505463,
|
488 |
+
"tokens_seen": 3041263616
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 0.22,
|
492 |
+
"learning_rate": 7.862289831865493e-05,
|
493 |
+
"loss": 1.2048,
|
494 |
+
"theoretical_loss": 3.3456363362770984,
|
495 |
+
"tokens_seen": 3042574336
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.22,
|
499 |
+
"objective/train/docs_used": 1019410,
|
500 |
+
"objective/train/instantaneous_batch_size": 8,
|
501 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
502 |
+
"objective/train/original_loss": 1.1971296072006226,
|
503 |
+
"objective/train/theoretical_loss": 3.3456089486754172,
|
504 |
+
"objective/train/tokens_used": 94186976,
|
505 |
+
"theoretical_loss": 3.3456089486754172,
|
506 |
+
"tokens_seen": 3042902016
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.23,
|
510 |
+
"learning_rate": 7.822257806244996e-05,
|
511 |
+
"loss": 1.1685,
|
512 |
+
"theoretical_loss": 3.345526808515576,
|
513 |
+
"tokens_seen": 3043885056
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.23,
|
517 |
+
"learning_rate": 7.782225780624501e-05,
|
518 |
+
"loss": 1.1907,
|
519 |
+
"theoretical_loss": 3.3454173411066828,
|
520 |
+
"tokens_seen": 3045195776
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.23,
|
524 |
+
"learning_rate": 7.742193755004003e-05,
|
525 |
+
"loss": 1.1949,
|
526 |
+
"theoretical_loss": 3.345307933991209,
|
527 |
+
"tokens_seen": 3046506496
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.24,
|
531 |
+
"learning_rate": 7.702161729383507e-05,
|
532 |
+
"loss": 1.1959,
|
533 |
+
"theoretical_loss": 3.3451985871100254,
|
534 |
+
"tokens_seen": 3047817216
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.24,
|
538 |
+
"learning_rate": 7.662129703763011e-05,
|
539 |
+
"loss": 1.1728,
|
540 |
+
"theoretical_loss": 3.345089300404087,
|
541 |
+
"tokens_seen": 3049127936
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.25,
|
545 |
+
"learning_rate": 7.622097678142515e-05,
|
546 |
+
"loss": 1.1995,
|
547 |
+
"theoretical_loss": 3.344980073814434,
|
548 |
+
"tokens_seen": 3050438656
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"debugging/Compilability": 0.0,
|
552 |
+
"debugging/distinct-1-grams": 0.7613636363636364,
|
553 |
+
"debugging/entropy-1-grams": 3.9967058025744,
|
554 |
+
"debugging/length": 568.0,
|
555 |
+
"debugging/num_segments": 1,
|
556 |
+
"debugging/score": 0.045774647887323945,
|
557 |
+
"debugging/score_std": 0.0,
|
558 |
+
"epoch": 0.25,
|
559 |
+
"objective/train/docs_used": 1022217,
|
560 |
+
"objective/train/instantaneous_batch_size": 8,
|
561 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
562 |
+
"objective/train/original_loss": 0.8801804780960083,
|
563 |
+
"objective/train/theoretical_loss": 3.3449254830448116,
|
564 |
+
"objective/train/tokens_used": 102378976,
|
565 |
+
"theoretical_loss": 3.3449254830448116,
|
566 |
+
"tokens_seen": 3051094016
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 0.25,
|
570 |
+
"learning_rate": 7.582065652522018e-05,
|
571 |
+
"loss": 1.1905,
|
572 |
+
"theoretical_loss": 3.3448709072821874,
|
573 |
+
"tokens_seen": 3051749376
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 0.25,
|
577 |
+
"learning_rate": 7.542033626901522e-05,
|
578 |
+
"loss": 1.1939,
|
579 |
+
"theoretical_loss": 3.344761800748551,
|
580 |
+
"tokens_seen": 3053060096
|
581 |
+
},
|
582 |
+
{
|
583 |
+
"epoch": 0.26,
|
584 |
+
"learning_rate": 7.502001601281026e-05,
|
585 |
+
"loss": 1.1901,
|
586 |
+
"theoretical_loss": 3.3446527541548132,
|
587 |
+
"tokens_seen": 3054370816
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 0.26,
|
591 |
+
"learning_rate": 7.46196957566053e-05,
|
592 |
+
"loss": 1.2002,
|
593 |
+
"theoretical_loss": 3.3445437674423437,
|
594 |
+
"tokens_seen": 3055681536
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.27,
|
598 |
+
"learning_rate": 7.421937550040032e-05,
|
599 |
+
"loss": 1.2223,
|
600 |
+
"theoretical_loss": 3.3444348405525948,
|
601 |
+
"tokens_seen": 3056992256
|
602 |
+
},
|
603 |
+
{
|
604 |
+
"epoch": 0.27,
|
605 |
+
"learning_rate": 7.381905524419536e-05,
|
606 |
+
"loss": 1.2028,
|
607 |
+
"theoretical_loss": 3.3443259734271016,
|
608 |
+
"tokens_seen": 3058302976
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 0.27,
|
612 |
+
"objective/train/docs_used": 1025165,
|
613 |
+
"objective/train/instantaneous_batch_size": 8,
|
614 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
615 |
+
"objective/train/original_loss": 1.2416154146194458,
|
616 |
+
"objective/train/theoretical_loss": 3.3442443622681504,
|
617 |
+
"objective/train/tokens_used": 110570976,
|
618 |
+
"theoretical_loss": 3.3442443622681504,
|
619 |
+
"tokens_seen": 3059286016
|
620 |
+
},
|
621 |
+
{
|
622 |
+
"epoch": 0.27,
|
623 |
+
"learning_rate": 7.34187349879904e-05,
|
624 |
+
"loss": 1.1917,
|
625 |
+
"theoretical_loss": 3.344217166007481,
|
626 |
+
"tokens_seen": 3059613696
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.28,
|
630 |
+
"learning_rate": 7.301841473178544e-05,
|
631 |
+
"loss": 1.1963,
|
632 |
+
"theoretical_loss": 3.344108418235432,
|
633 |
+
"tokens_seen": 3060924416
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.28,
|
637 |
+
"learning_rate": 7.261809447558046e-05,
|
638 |
+
"loss": 1.1737,
|
639 |
+
"theoretical_loss": 3.343999730052735,
|
640 |
+
"tokens_seen": 3062235136
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 0.29,
|
644 |
+
"learning_rate": 7.22177742193755e-05,
|
645 |
+
"loss": 1.1848,
|
646 |
+
"theoretical_loss": 3.343891101401253,
|
647 |
+
"tokens_seen": 3063545856
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 0.29,
|
651 |
+
"learning_rate": 7.181745396317054e-05,
|
652 |
+
"loss": 1.1799,
|
653 |
+
"theoretical_loss": 3.3437825322229298,
|
654 |
+
"tokens_seen": 3064856576
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.29,
|
658 |
+
"learning_rate": 7.141713370696558e-05,
|
659 |
+
"loss": 1.1818,
|
660 |
+
"theoretical_loss": 3.3436740224597914,
|
661 |
+
"tokens_seen": 3066167296
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 0.3,
|
665 |
+
"objective/train/docs_used": 1028068,
|
666 |
+
"objective/train/instantaneous_batch_size": 8,
|
667 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
668 |
+
"objective/train/original_loss": 1.3919180631637573,
|
669 |
+
"objective/train/theoretical_loss": 3.3435655720539446,
|
670 |
+
"objective/train/tokens_used": 118762976,
|
671 |
+
"theoretical_loss": 3.3435655720539446,
|
672 |
+
"tokens_seen": 3067478016
|
673 |
+
},
|
674 |
+
{
|
675 |
+
"epoch": 0.3,
|
676 |
+
"learning_rate": 7.101681345076061e-05,
|
677 |
+
"loss": 1.1999,
|
678 |
+
"theoretical_loss": 3.3435655720539446,
|
679 |
+
"tokens_seen": 3067478016
|
680 |
+
},
|
681 |
+
{
|
682 |
+
"epoch": 0.3,
|
683 |
+
"learning_rate": 7.061649319455565e-05,
|
684 |
+
"loss": 1.1951,
|
685 |
+
"theoretical_loss": 3.343457180947577,
|
686 |
+
"tokens_seen": 3068788736
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 0.31,
|
690 |
+
"learning_rate": 7.021617293835069e-05,
|
691 |
+
"loss": 1.1921,
|
692 |
+
"theoretical_loss": 3.343348849082957,
|
693 |
+
"tokens_seen": 3070099456
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 0.31,
|
697 |
+
"learning_rate": 6.981585268214572e-05,
|
698 |
+
"loss": 1.1899,
|
699 |
+
"theoretical_loss": 3.3432405764024353,
|
700 |
+
"tokens_seen": 3071410176
|
701 |
+
},
|
702 |
+
{
|
703 |
+
"epoch": 0.31,
|
704 |
+
"learning_rate": 6.941553242594075e-05,
|
705 |
+
"loss": 1.1887,
|
706 |
+
"theoretical_loss": 3.3431323628484417,
|
707 |
+
"tokens_seen": 3072720896
|
708 |
+
},
|
709 |
+
{
|
710 |
+
"epoch": 0.32,
|
711 |
+
"learning_rate": 6.901521216973579e-05,
|
712 |
+
"loss": 1.1913,
|
713 |
+
"theoretical_loss": 3.343024208363487,
|
714 |
+
"tokens_seen": 3074031616
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 0.32,
|
718 |
+
"learning_rate": 6.861489191353083e-05,
|
719 |
+
"loss": 1.1801,
|
720 |
+
"theoretical_loss": 3.3429161128901628,
|
721 |
+
"tokens_seen": 3075342336
|
722 |
+
},
|
723 |
+
{
|
724 |
+
"epoch": 0.32,
|
725 |
+
"objective/train/docs_used": 1031046,
|
726 |
+
"objective/train/instantaneous_batch_size": 8,
|
727 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
728 |
+
"objective/train/original_loss": 1.355250597000122,
|
729 |
+
"objective/train/theoretical_loss": 3.342889098235679,
|
730 |
+
"objective/train/tokens_used": 126954976,
|
731 |
+
"theoretical_loss": 3.342889098235679,
|
732 |
+
"tokens_seen": 3075670016
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 0.32,
|
736 |
+
"learning_rate": 6.821457165732587e-05,
|
737 |
+
"loss": 1.186,
|
738 |
+
"theoretical_loss": 3.3428080763711403,
|
739 |
+
"tokens_seen": 3076653056
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 0.33,
|
743 |
+
"learning_rate": 6.78142514011209e-05,
|
744 |
+
"loss": 1.1817,
|
745 |
+
"theoretical_loss": 3.3427000987491717,
|
746 |
+
"tokens_seen": 3077963776
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 0.33,
|
750 |
+
"learning_rate": 6.741393114491593e-05,
|
751 |
+
"loss": 1.1953,
|
752 |
+
"theoretical_loss": 3.342592179967088,
|
753 |
+
"tokens_seen": 3079274496
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 0.34,
|
757 |
+
"learning_rate": 6.701361088871097e-05,
|
758 |
+
"loss": 1.1954,
|
759 |
+
"theoretical_loss": 3.3424843199678005,
|
760 |
+
"tokens_seen": 3080585216
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 0.34,
|
764 |
+
"learning_rate": 6.661329063250601e-05,
|
765 |
+
"loss": 1.1849,
|
766 |
+
"theoretical_loss": 3.3423765186943006,
|
767 |
+
"tokens_seen": 3081895936
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 0.34,
|
771 |
+
"learning_rate": 6.621297037630104e-05,
|
772 |
+
"loss": 1.1971,
|
773 |
+
"theoretical_loss": 3.3422687760896586,
|
774 |
+
"tokens_seen": 3083206656
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.35,
|
778 |
+
"objective/train/docs_used": 1033433,
|
779 |
+
"objective/train/instantaneous_batch_size": 8,
|
780 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
781 |
+
"objective/train/original_loss": 1.3183742761611938,
|
782 |
+
"objective/train/theoretical_loss": 3.3422149267703904,
|
783 |
+
"objective/train/tokens_used": 135146976,
|
784 |
+
"theoretical_loss": 3.3422149267703904,
|
785 |
+
"tokens_seen": 3083862016
|
786 |
+
},
|
787 |
+
{
|
788 |
+
"epoch": 0.35,
|
789 |
+
"learning_rate": 6.581265012009608e-05,
|
790 |
+
"loss": 1.1814,
|
791 |
+
"theoretical_loss": 3.342161092097024,
|
792 |
+
"tokens_seen": 3084517376
|
793 |
+
},
|
794 |
+
{
|
795 |
+
"epoch": 0.35,
|
796 |
+
"learning_rate": 6.541232986389112e-05,
|
797 |
+
"loss": 1.1732,
|
798 |
+
"theoretical_loss": 3.342053466659626,
|
799 |
+
"tokens_seen": 3085828096
|
800 |
+
},
|
801 |
+
{
|
802 |
+
"epoch": 0.36,
|
803 |
+
"learning_rate": 6.501200960768615e-05,
|
804 |
+
"loss": 1.1698,
|
805 |
+
"theoretical_loss": 3.3419458997207734,
|
806 |
+
"tokens_seen": 3087138816
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 0.36,
|
810 |
+
"learning_rate": 6.461168935148118e-05,
|
811 |
+
"loss": 1.1775,
|
812 |
+
"theoretical_loss": 3.3418383912238525,
|
813 |
+
"tokens_seen": 3088449536
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 0.36,
|
817 |
+
"learning_rate": 6.421136909527622e-05,
|
818 |
+
"loss": 1.1784,
|
819 |
+
"theoretical_loss": 3.341730941112329,
|
820 |
+
"tokens_seen": 3089760256
|
821 |
+
},
|
822 |
+
{
|
823 |
+
"epoch": 0.37,
|
824 |
+
"learning_rate": 6.381104883907126e-05,
|
825 |
+
"loss": 1.1965,
|
826 |
+
"theoretical_loss": 3.341623549329748,
|
827 |
+
"tokens_seen": 3091070976
|
828 |
+
},
|
829 |
+
{
|
830 |
+
"epoch": 0.37,
|
831 |
+
"objective/train/docs_used": 1036380,
|
832 |
+
"objective/train/instantaneous_batch_size": 8,
|
833 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
834 |
+
"objective/train/original_loss": 1.2508410215377808,
|
835 |
+
"objective/train/theoretical_loss": 3.3415430437372637,
|
836 |
+
"objective/train/tokens_used": 143338976,
|
837 |
+
"theoretical_loss": 3.3415430437372637,
|
838 |
+
"tokens_seen": 3092054016
|
839 |
+
},
|
840 |
+
{
|
841 |
+
"epoch": 0.37,
|
842 |
+
"learning_rate": 6.34107285828663e-05,
|
843 |
+
"loss": 1.1741,
|
844 |
+
"theoretical_loss": 3.3415162158197327,
|
845 |
+
"tokens_seen": 3092381696
|
846 |
+
},
|
847 |
+
{
|
848 |
+
"epoch": 0.38,
|
849 |
+
"learning_rate": 6.301040832666132e-05,
|
850 |
+
"loss": 1.1813,
|
851 |
+
"theoretical_loss": 3.3414089405259837,
|
852 |
+
"tokens_seen": 3093692416
|
853 |
+
},
|
854 |
+
{
|
855 |
+
"epoch": 0.38,
|
856 |
+
"learning_rate": 6.261008807045636e-05,
|
857 |
+
"loss": 1.1763,
|
858 |
+
"theoretical_loss": 3.341301723392281,
|
859 |
+
"tokens_seen": 3095003136
|
860 |
+
},
|
861 |
+
{
|
862 |
+
"epoch": 0.38,
|
863 |
+
"learning_rate": 6.22097678142514e-05,
|
864 |
+
"loss": 1.1828,
|
865 |
+
"theoretical_loss": 3.3411945643624814,
|
866 |
+
"tokens_seen": 3096313856
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 0.39,
|
870 |
+
"learning_rate": 6.180944755804644e-05,
|
871 |
+
"loss": 1.1958,
|
872 |
+
"theoretical_loss": 3.3410874633805214,
|
873 |
+
"tokens_seen": 3097624576
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 0.39,
|
877 |
+
"learning_rate": 6.140912730184148e-05,
|
878 |
+
"loss": 1.1942,
|
879 |
+
"theoretical_loss": 3.3409804203904145,
|
880 |
+
"tokens_seen": 3098935296
|
881 |
+
},
|
882 |
+
{
|
883 |
+
"epoch": 0.4,
|
884 |
+
"objective/train/docs_used": 1039074,
|
885 |
+
"objective/train/instantaneous_batch_size": 8,
|
886 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
887 |
+
"objective/train/original_loss": 1.3202261924743652,
|
888 |
+
"objective/train/theoretical_loss": 3.3408734353362513,
|
889 |
+
"objective/train/tokens_used": 151530976,
|
890 |
+
"theoretical_loss": 3.3408734353362513,
|
891 |
+
"tokens_seen": 3100246016
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.4,
|
895 |
+
"learning_rate": 6.1008807045636506e-05,
|
896 |
+
"loss": 1.1996,
|
897 |
+
"theoretical_loss": 3.3408734353362513,
|
898 |
+
"tokens_seen": 3100246016
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 0.4,
|
902 |
+
"learning_rate": 6.060848678943155e-05,
|
903 |
+
"loss": 1.1876,
|
904 |
+
"theoretical_loss": 3.3407665081622,
|
905 |
+
"tokens_seen": 3101556736
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 0.4,
|
909 |
+
"learning_rate": 6.0208166533226584e-05,
|
910 |
+
"loss": 1.1839,
|
911 |
+
"theoretical_loss": 3.340659638812507,
|
912 |
+
"tokens_seen": 3102867456
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 0.41,
|
916 |
+
"learning_rate": 5.9807846277021617e-05,
|
917 |
+
"loss": 1.192,
|
918 |
+
"theoretical_loss": 3.340552827231495,
|
919 |
+
"tokens_seen": 3104178176
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.41,
|
923 |
+
"learning_rate": 5.940752602081665e-05,
|
924 |
+
"loss": 1.1838,
|
925 |
+
"theoretical_loss": 3.3404460733635646,
|
926 |
+
"tokens_seen": 3105488896
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.42,
|
930 |
+
"learning_rate": 5.9007205764611695e-05,
|
931 |
+
"loss": 1.1796,
|
932 |
+
"theoretical_loss": 3.340339377153193,
|
933 |
+
"tokens_seen": 3106799616
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.42,
|
937 |
+
"learning_rate": 5.860688550840673e-05,
|
938 |
+
"loss": 1.1824,
|
939 |
+
"theoretical_loss": 3.340232738544933,
|
940 |
+
"tokens_seen": 3108110336
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 0.42,
|
944 |
+
"objective/train/docs_used": 1042051,
|
945 |
+
"objective/train/instantaneous_batch_size": 8,
|
946 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
947 |
+
"objective/train/original_loss": 1.5605241060256958,
|
948 |
+
"objective/train/theoretical_loss": 3.340206087886708,
|
949 |
+
"objective/train/tokens_used": 159722976,
|
950 |
+
"theoretical_loss": 3.340206087886708,
|
951 |
+
"tokens_seen": 3108438016
|
952 |
+
},
|
953 |
+
{
|
954 |
+
"epoch": 0.42,
|
955 |
+
"learning_rate": 5.820656525220176e-05,
|
956 |
+
"loss": 1.1953,
|
957 |
+
"theoretical_loss": 3.340126157483417,
|
958 |
+
"tokens_seen": 3109421056
|
959 |
+
},
|
960 |
+
{
|
961 |
+
"epoch": 0.43,
|
962 |
+
"learning_rate": 5.7806244995996806e-05,
|
963 |
+
"loss": 1.1918,
|
964 |
+
"theoretical_loss": 3.340019633913351,
|
965 |
+
"tokens_seen": 3110731776
|
966 |
+
},
|
967 |
+
{
|
968 |
+
"epoch": 0.43,
|
969 |
+
"learning_rate": 5.740592473979184e-05,
|
970 |
+
"loss": 1.2149,
|
971 |
+
"theoretical_loss": 3.3399131677795184,
|
972 |
+
"tokens_seen": 3112042496
|
973 |
+
},
|
974 |
+
{
|
975 |
+
"epoch": 0.44,
|
976 |
+
"learning_rate": 5.700560448358687e-05,
|
977 |
+
"loss": 1.2105,
|
978 |
+
"theoretical_loss": 3.3398067590267804,
|
979 |
+
"tokens_seen": 3113353216
|
980 |
+
},
|
981 |
+
{
|
982 |
+
"epoch": 0.44,
|
983 |
+
"learning_rate": 5.66052842273819e-05,
|
984 |
+
"loss": 1.1876,
|
985 |
+
"theoretical_loss": 3.339700407600071,
|
986 |
+
"tokens_seen": 3114663936
|
987 |
+
},
|
988 |
+
{
|
989 |
+
"epoch": 0.44,
|
990 |
+
"learning_rate": 5.620496397117695e-05,
|
991 |
+
"loss": 1.1859,
|
992 |
+
"theoretical_loss": 3.339594113444404,
|
993 |
+
"tokens_seen": 3115974656
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 0.45,
|
997 |
+
"objective/train/docs_used": 1044567,
|
998 |
+
"objective/train/instantaneous_batch_size": 8,
|
999 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
1000 |
+
"objective/train/original_loss": 1.1618666648864746,
|
1001 |
+
"objective/train/theoretical_loss": 3.339540987826048,
|
1002 |
+
"objective/train/tokens_used": 167914976,
|
1003 |
+
"theoretical_loss": 3.339540987826048,
|
1004 |
+
"tokens_seen": 3116630016
|
1005 |
+
},
|
1006 |
+
{
|
1007 |
+
"epoch": 0.45,
|
1008 |
+
"learning_rate": 5.580464371497198e-05,
|
1009 |
+
"loss": 1.1922,
|
1010 |
+
"theoretical_loss": 3.3394878765048657,
|
1011 |
+
"tokens_seen": 3117285376
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 0.45,
|
1015 |
+
"learning_rate": 5.5404323458767014e-05,
|
1016 |
+
"loss": 1.1874,
|
1017 |
+
"theoretical_loss": 3.3393816967266208,
|
1018 |
+
"tokens_seen": 3118596096
|
1019 |
+
},
|
1020 |
+
{
|
1021 |
+
"epoch": 0.46,
|
1022 |
+
"learning_rate": 5.5004003202562046e-05,
|
1023 |
+
"loss": 1.1985,
|
1024 |
+
"theoretical_loss": 3.3392755740549074,
|
1025 |
+
"tokens_seen": 3119906816
|
1026 |
+
},
|
1027 |
+
{
|
1028 |
+
"epoch": 0.46,
|
1029 |
+
"learning_rate": 5.460368294635709e-05,
|
1030 |
+
"loss": 1.1583,
|
1031 |
+
"theoretical_loss": 3.33916950843504,
|
1032 |
+
"tokens_seen": 3121217536
|
1033 |
+
},
|
1034 |
+
{
|
1035 |
+
"epoch": 0.46,
|
1036 |
+
"learning_rate": 5.4203362690152125e-05,
|
1037 |
+
"loss": 1.1743,
|
1038 |
+
"theoretical_loss": 3.3390634998124096,
|
1039 |
+
"tokens_seen": 3122528256
|
1040 |
+
},
|
1041 |
+
{
|
1042 |
+
"epoch": 0.47,
|
1043 |
+
"learning_rate": 5.380304243394716e-05,
|
1044 |
+
"loss": 1.1793,
|
1045 |
+
"theoretical_loss": 3.3389575481324796,
|
1046 |
+
"tokens_seen": 3123838976
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 0.47,
|
1050 |
+
"objective/train/docs_used": 1047326,
|
1051 |
+
"objective/train/instantaneous_batch_size": 8,
|
1052 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
1053 |
+
"objective/train/original_loss": 1.2724859714508057,
|
1054 |
+
"objective/train/theoretical_loss": 3.338878121708416,
|
1055 |
+
"objective/train/tokens_used": 176106976,
|
1056 |
+
"theoretical_loss": 3.338878121708416,
|
1057 |
+
"tokens_seen": 3124822016
|
1058 |
+
},
|
1059 |
+
{
|
1060 |
+
"epoch": 0.47,
|
1061 |
+
"learning_rate": 5.340272217774219e-05,
|
1062 |
+
"loss": 1.209,
|
1063 |
+
"theoretical_loss": 3.338851653340791,
|
1064 |
+
"tokens_seen": 3125149696
|
1065 |
+
},
|
1066 |
+
{
|
1067 |
+
"epoch": 0.48,
|
1068 |
+
"learning_rate": 5.3002401921537236e-05,
|
1069 |
+
"loss": 1.1861,
|
1070 |
+
"theoretical_loss": 3.3387458153829583,
|
1071 |
+
"tokens_seen": 3126460416
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 0.48,
|
1075 |
+
"learning_rate": 5.260208166533227e-05,
|
1076 |
+
"loss": 1.176,
|
1077 |
+
"theoretical_loss": 3.338640034204672,
|
1078 |
+
"tokens_seen": 3127771136
|
1079 |
+
},
|
1080 |
+
{
|
1081 |
+
"epoch": 0.48,
|
1082 |
+
"learning_rate": 5.22017614091273e-05,
|
1083 |
+
"loss": 1.1889,
|
1084 |
+
"theoretical_loss": 3.3385343097516946,
|
1085 |
+
"tokens_seen": 3129081856
|
1086 |
+
},
|
1087 |
+
{
|
1088 |
+
"epoch": 0.49,
|
1089 |
+
"learning_rate": 5.180144115292234e-05,
|
1090 |
+
"loss": 1.1717,
|
1091 |
+
"theoretical_loss": 3.338428641969867,
|
1092 |
+
"tokens_seen": 3130392576
|
1093 |
+
},
|
1094 |
+
{
|
1095 |
+
"epoch": 0.49,
|
1096 |
+
"learning_rate": 5.140112089671738e-05,
|
1097 |
+
"loss": 1.1977,
|
1098 |
+
"theoretical_loss": 3.3383230308051006,
|
1099 |
+
"tokens_seen": 3131703296
|
1100 |
+
},
|
1101 |
+
{
|
1102 |
+
"debugging/Compilability": 0.0,
|
1103 |
+
"debugging/distinct-1-grams": 0.6651816214290593,
|
1104 |
+
"debugging/entropy-1-grams": 4.2985685702692615,
|
1105 |
+
"debugging/length": 583.75,
|
1106 |
+
"debugging/num_segments": 4,
|
1107 |
+
"debugging/score": 0.06321276390574523,
|
1108 |
+
"debugging/score_std": 0.02740587124120667,
|
1109 |
+
"epoch": 0.49,
|
1110 |
+
"objective/train/docs_used": 1050300,
|
1111 |
+
"objective/train/instantaneous_batch_size": 8,
|
1112 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
1113 |
+
"objective/train/original_loss": 1.2621127367019653,
|
1114 |
+
"objective/train/theoretical_loss": 3.338217476203384,
|
1115 |
+
"objective/train/tokens_used": 184298976,
|
1116 |
+
"theoretical_loss": 3.338217476203384,
|
1117 |
+
"tokens_seen": 3133014016
|
1118 |
+
},
|
1119 |
+
{
|
1120 |
+
"epoch": 0.5,
|
1121 |
+
"learning_rate": 5.100080064051241e-05,
|
1122 |
+
"loss": 1.1834,
|
1123 |
+
"theoretical_loss": 3.338217476203384,
|
1124 |
+
"tokens_seen": 3133014016
|
1125 |
+
},
|
1126 |
+
{
|
1127 |
+
"epoch": 0.5,
|
1128 |
+
"learning_rate": 5.060048038430745e-05,
|
1129 |
+
"loss": 1.1796,
|
1130 |
+
"theoretical_loss": 3.3381119781107778,
|
1131 |
+
"tokens_seen": 3134324736
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 0.5,
|
1135 |
+
"learning_rate": 5.020016012810248e-05,
|
1136 |
+
"loss": 1.1743,
|
1137 |
+
"theoretical_loss": 3.3380065364734186,
|
1138 |
+
"tokens_seen": 3135635456
|
1139 |
+
},
|
1140 |
+
{
|
1141 |
+
"epoch": 0.51,
|
1142 |
+
"learning_rate": 4.979983987189752e-05,
|
1143 |
+
"loss": 1.1641,
|
1144 |
+
"theoretical_loss": 3.3379011512375145,
|
1145 |
+
"tokens_seen": 3136946176
|
1146 |
+
},
|
1147 |
+
{
|
1148 |
+
"epoch": 0.51,
|
1149 |
+
"learning_rate": 4.9399519615692554e-05,
|
1150 |
+
"loss": 1.1767,
|
1151 |
+
"theoretical_loss": 3.3377958223493485,
|
1152 |
+
"tokens_seen": 3138256896
|
1153 |
+
},
|
1154 |
+
{
|
1155 |
+
"epoch": 0.52,
|
1156 |
+
"learning_rate": 4.8999199359487594e-05,
|
1157 |
+
"loss": 1.1809,
|
1158 |
+
"theoretical_loss": 3.337690549755278,
|
1159 |
+
"tokens_seen": 3139567616
|
1160 |
+
},
|
1161 |
+
{
|
1162 |
+
"epoch": 0.52,
|
1163 |
+
"learning_rate": 4.859887910328263e-05,
|
1164 |
+
"loss": 1.1658,
|
1165 |
+
"theoretical_loss": 3.3375853334017327,
|
1166 |
+
"tokens_seen": 3140878336
|
1167 |
+
},
|
1168 |
+
{
|
1169 |
+
"epoch": 0.52,
|
1170 |
+
"objective/train/docs_used": 1053223,
|
1171 |
+
"objective/train/instantaneous_batch_size": 8,
|
1172 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
1173 |
+
"objective/train/original_loss": 1.286133885383606,
|
1174 |
+
"objective/train/theoretical_loss": 3.337559038094658,
|
1175 |
+
"objective/train/tokens_used": 192490976,
|
1176 |
+
"theoretical_loss": 3.337559038094658,
|
1177 |
+
"tokens_seen": 3141206016
|
1178 |
+
},
|
1179 |
+
{
|
1180 |
+
"epoch": 0.52,
|
1181 |
+
"learning_rate": 4.8198558847077665e-05,
|
1182 |
+
"loss": 1.2072,
|
1183 |
+
"theoretical_loss": 3.3374801732352157,
|
1184 |
+
"tokens_seen": 3142189056
|
1185 |
+
},
|
1186 |
+
{
|
1187 |
+
"epoch": 0.53,
|
1188 |
+
"learning_rate": 4.7798238590872704e-05,
|
1189 |
+
"loss": 1.1917,
|
1190 |
+
"theoretical_loss": 3.337375069202303,
|
1191 |
+
"tokens_seen": 3143499776
|
1192 |
+
},
|
1193 |
+
{
|
1194 |
+
"epoch": 0.53,
|
1195 |
+
"learning_rate": 4.739791833466774e-05,
|
1196 |
+
"loss": 1.1742,
|
1197 |
+
"theoretical_loss": 3.337270021249646,
|
1198 |
+
"tokens_seen": 3144810496
|
1199 |
+
},
|
1200 |
+
{
|
1201 |
+
"epoch": 0.53,
|
1202 |
+
"learning_rate": 4.6997598078462776e-05,
|
1203 |
+
"loss": 1.1901,
|
1204 |
+
"theoretical_loss": 3.3371650293239643,
|
1205 |
+
"tokens_seen": 3146121216
|
1206 |
+
},
|
1207 |
+
{
|
1208 |
+
"epoch": 0.54,
|
1209 |
+
"learning_rate": 4.659727782225781e-05,
|
1210 |
+
"loss": 1.1848,
|
1211 |
+
"theoretical_loss": 3.337060093372055,
|
1212 |
+
"tokens_seen": 3147431936
|
1213 |
+
},
|
1214 |
+
{
|
1215 |
+
"epoch": 0.54,
|
1216 |
+
"learning_rate": 4.619695756605285e-05,
|
1217 |
+
"loss": 1.184,
|
1218 |
+
"theoretical_loss": 3.3369552133407856,
|
1219 |
+
"tokens_seen": 3148742656
|
1220 |
+
},
|
1221 |
+
{
|
1222 |
+
"epoch": 0.54,
|
1223 |
+
"objective/train/docs_used": 1056133,
|
1224 |
+
"objective/train/instantaneous_batch_size": 8,
|
1225 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
1226 |
+
"objective/train/original_loss": 1.0991315841674805,
|
1227 |
+
"objective/train/theoretical_loss": 3.336902794278807,
|
1228 |
+
"objective/train/tokens_used": 200682976,
|
1229 |
+
"theoretical_loss": 3.336902794278807,
|
1230 |
+
"tokens_seen": 3149398016
|
1231 |
+
},
|
1232 |
+
{
|
1233 |
+
"epoch": 0.55,
|
1234 |
+
"learning_rate": 4.579663730984788e-05,
|
1235 |
+
"loss": 1.1872,
|
1236 |
+
"theoretical_loss": 3.3368503891770964,
|
1237 |
+
"tokens_seen": 3150053376
|
1238 |
+
},
|
1239 |
+
{
|
1240 |
+
"epoch": 0.55,
|
1241 |
+
"learning_rate": 4.539631705364292e-05,
|
1242 |
+
"loss": 1.1918,
|
1243 |
+
"theoretical_loss": 3.336745620828,
|
1244 |
+
"tokens_seen": 3151364096
|
1245 |
+
},
|
1246 |
+
{
|
1247 |
+
"epoch": 0.55,
|
1248 |
+
"learning_rate": 4.499599679743795e-05,
|
1249 |
+
"loss": 1.2037,
|
1250 |
+
"theoretical_loss": 3.3366409082405823,
|
1251 |
+
"tokens_seen": 3152674816
|
1252 |
+
},
|
1253 |
+
{
|
1254 |
+
"epoch": 0.56,
|
1255 |
+
"learning_rate": 4.459567654123299e-05,
|
1256 |
+
"loss": 1.1804,
|
1257 |
+
"theoretical_loss": 3.3365362513619994,
|
1258 |
+
"tokens_seen": 3153985536
|
1259 |
+
},
|
1260 |
+
{
|
1261 |
+
"epoch": 0.56,
|
1262 |
+
"learning_rate": 4.419535628502802e-05,
|
1263 |
+
"loss": 1.178,
|
1264 |
+
"theoretical_loss": 3.336431650139481,
|
1265 |
+
"tokens_seen": 3155296256
|
1266 |
+
},
|
1267 |
+
{
|
1268 |
+
"epoch": 0.57,
|
1269 |
+
"learning_rate": 4.379503602882306e-05,
|
1270 |
+
"loss": 1.1858,
|
1271 |
+
"theoretical_loss": 3.336327104520328,
|
1272 |
+
"tokens_seen": 3156606976
|
1273 |
+
},
|
1274 |
+
{
|
1275 |
+
"epoch": 0.57,
|
1276 |
+
"objective/train/docs_used": 1058478,
|
1277 |
+
"objective/train/instantaneous_batch_size": 8,
|
1278 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
1279 |
+
"objective/train/original_loss": 1.1500177383422852,
|
1280 |
+
"objective/train/theoretical_loss": 3.336248731764011,
|
1281 |
+
"objective/train/tokens_used": 208874976,
|
1282 |
+
"theoretical_loss": 3.336248731764011,
|
1283 |
+
"tokens_seen": 3157590016
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 0.57,
|
1287 |
+
"learning_rate": 4.3394715772618095e-05,
|
1288 |
+
"loss": 1.1836,
|
1289 |
+
"theoretical_loss": 3.3362226144519136,
|
1290 |
+
"tokens_seen": 3157917696
|
1291 |
+
},
|
1292 |
+
{
|
1293 |
+
"epoch": 0.57,
|
1294 |
+
"learning_rate": 4.2994395516413134e-05,
|
1295 |
+
"loss": 1.1917,
|
1296 |
+
"theoretical_loss": 3.336118179881682,
|
1297 |
+
"tokens_seen": 3159228416
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"epoch": 0.58,
|
1301 |
+
"learning_rate": 4.2594075260208167e-05,
|
1302 |
+
"loss": 1.1829,
|
1303 |
+
"theoretical_loss": 3.336013800757149,
|
1304 |
+
"tokens_seen": 3160539136
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 0.58,
|
1308 |
+
"learning_rate": 4.2193755004003206e-05,
|
1309 |
+
"loss": 1.1744,
|
1310 |
+
"theoretical_loss": 3.3359094770259023,
|
1311 |
+
"tokens_seen": 3161849856
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 0.59,
|
1315 |
+
"learning_rate": 4.179343474779824e-05,
|
1316 |
+
"loss": 1.1823,
|
1317 |
+
"theoretical_loss": 3.3358052086356,
|
1318 |
+
"tokens_seen": 3163160576
|
1319 |
+
},
|
1320 |
+
{
|
1321 |
+
"epoch": 0.59,
|
1322 |
+
"learning_rate": 4.139311449159328e-05,
|
1323 |
+
"loss": 1.1667,
|
1324 |
+
"theoretical_loss": 3.3357009955339727,
|
1325 |
+
"tokens_seen": 3164471296
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 0.59,
|
1329 |
+
"objective/train/docs_used": 1061123,
|
1330 |
+
"objective/train/instantaneous_batch_size": 8,
|
1331 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
1332 |
+
"objective/train/original_loss": 0.7507131099700928,
|
1333 |
+
"objective/train/theoretical_loss": 3.33559683766882,
|
1334 |
+
"objective/train/tokens_used": 217066976,
|
1335 |
+
"theoretical_loss": 3.33559683766882,
|
1336 |
+
"tokens_seen": 3165782016
|
1337 |
+
},
|
1338 |
+
{
|
1339 |
+
"epoch": 0.59,
|
1340 |
+
"learning_rate": 4.099279423538831e-05,
|
1341 |
+
"loss": 1.1938,
|
1342 |
+
"theoretical_loss": 3.33559683766882,
|
1343 |
+
"tokens_seen": 3165782016
|
1344 |
+
},
|
1345 |
+
{
|
1346 |
+
"epoch": 0.6,
|
1347 |
+
"learning_rate": 4.059247397918335e-05,
|
1348 |
+
"loss": 1.1858,
|
1349 |
+
"theoretical_loss": 3.335492734988014,
|
1350 |
+
"tokens_seen": 3167092736
|
1351 |
+
},
|
1352 |
+
{
|
1353 |
+
"epoch": 0.6,
|
1354 |
+
"learning_rate": 4.019215372297839e-05,
|
1355 |
+
"loss": 1.1758,
|
1356 |
+
"theoretical_loss": 3.3353886874394973,
|
1357 |
+
"tokens_seen": 3168403456
|
1358 |
+
},
|
1359 |
+
{
|
1360 |
+
"epoch": 0.61,
|
1361 |
+
"learning_rate": 3.979183346677342e-05,
|
1362 |
+
"loss": 1.1935,
|
1363 |
+
"theoretical_loss": 3.3352846949712824,
|
1364 |
+
"tokens_seen": 3169714176
|
1365 |
+
},
|
1366 |
+
{
|
1367 |
+
"epoch": 0.61,
|
1368 |
+
"learning_rate": 3.939151321056846e-05,
|
1369 |
+
"loss": 1.1835,
|
1370 |
+
"theoretical_loss": 3.3351807575314525,
|
1371 |
+
"tokens_seen": 3171024896
|
1372 |
+
},
|
1373 |
+
{
|
1374 |
+
"epoch": 0.61,
|
1375 |
+
"learning_rate": 3.899119295436349e-05,
|
1376 |
+
"loss": 1.1861,
|
1377 |
+
"theoretical_loss": 3.3350768750681623,
|
1378 |
+
"tokens_seen": 3172335616
|
1379 |
+
},
|
1380 |
+
{
|
1381 |
+
"epoch": 0.62,
|
1382 |
+
"learning_rate": 3.859087269815853e-05,
|
1383 |
+
"loss": 1.2016,
|
1384 |
+
"theoretical_loss": 3.334973047529635,
|
1385 |
+
"tokens_seen": 3173646336
|
1386 |
+
},
|
1387 |
+
{
|
1388 |
+
"epoch": 0.62,
|
1389 |
+
"objective/train/docs_used": 1063909,
|
1390 |
+
"objective/train/instantaneous_batch_size": 8,
|
1391 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
1392 |
+
"objective/train/original_loss": 1.3667196035385132,
|
1393 |
+
"objective/train/theoretical_loss": 3.3349470992209365,
|
1394 |
+
"objective/train/tokens_used": 225258976,
|
1395 |
+
"theoretical_loss": 3.3349470992209365,
|
1396 |
+
"tokens_seen": 3173974016
|
1397 |
+
},
|
1398 |
+
{
|
1399 |
+
"epoch": 0.62,
|
1400 |
+
"learning_rate": 3.8190552441953564e-05,
|
1401 |
+
"loss": 1.208,
|
1402 |
+
"theoretical_loss": 3.3348692748641646,
|
1403 |
+
"tokens_seen": 3174957056
|
1404 |
+
},
|
1405 |
+
{
|
1406 |
+
"epoch": 0.63,
|
1407 |
+
"learning_rate": 3.77902321857486e-05,
|
1408 |
+
"loss": 1.1676,
|
1409 |
+
"theoretical_loss": 3.3347655570201162,
|
1410 |
+
"tokens_seen": 3176267776
|
1411 |
+
},
|
1412 |
+
{
|
1413 |
+
"epoch": 0.63,
|
1414 |
+
"learning_rate": 3.7389911929543636e-05,
|
1415 |
+
"loss": 1.176,
|
1416 |
+
"theoretical_loss": 3.334661893945923,
|
1417 |
+
"tokens_seen": 3177578496
|
1418 |
+
},
|
1419 |
+
{
|
1420 |
+
"epoch": 0.63,
|
1421 |
+
"learning_rate": 3.6989591673338675e-05,
|
1422 |
+
"loss": 1.1655,
|
1423 |
+
"theoretical_loss": 3.3345582855900893,
|
1424 |
+
"tokens_seen": 3178889216
|
1425 |
+
},
|
1426 |
+
{
|
1427 |
+
"epoch": 0.64,
|
1428 |
+
"learning_rate": 3.658927141713371e-05,
|
1429 |
+
"loss": 1.2031,
|
1430 |
+
"theoretical_loss": 3.334454731901188,
|
1431 |
+
"tokens_seen": 3180199936
|
1432 |
+
},
|
1433 |
+
{
|
1434 |
+
"epoch": 0.64,
|
1435 |
+
"learning_rate": 3.6188951160928746e-05,
|
1436 |
+
"loss": 1.1675,
|
1437 |
+
"theoretical_loss": 3.3343512328278626,
|
1438 |
+
"tokens_seen": 3181510656
|
1439 |
+
},
|
1440 |
+
{
|
1441 |
+
"epoch": 0.64,
|
1442 |
+
"objective/train/docs_used": 1066709,
|
1443 |
+
"objective/train/instantaneous_batch_size": 8,
|
1444 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
1445 |
+
"objective/train/original_loss": 1.2202755212783813,
|
1446 |
+
"objective/train/theoretical_loss": 3.3342995037560104,
|
1447 |
+
"objective/train/tokens_used": 233450976,
|
1448 |
+
"theoretical_loss": 3.3342995037560104,
|
1449 |
+
"tokens_seen": 3182166016
|
1450 |
+
},
|
1451 |
+
{
|
1452 |
+
"epoch": 0.65,
|
1453 |
+
"learning_rate": 3.578863090472378e-05,
|
1454 |
+
"loss": 1.1818,
|
1455 |
+
"theoretical_loss": 3.3342477883188244,
|
1456 |
+
"tokens_seen": 3182821376
|
1457 |
+
},
|
1458 |
+
{
|
1459 |
+
"epoch": 0.65,
|
1460 |
+
"learning_rate": 3.538831064851882e-05,
|
1461 |
+
"loss": 1.1759,
|
1462 |
+
"theoretical_loss": 3.334144398322856,
|
1463 |
+
"tokens_seen": 3184132096
|
1464 |
+
},
|
1465 |
+
{
|
1466 |
+
"epoch": 0.65,
|
1467 |
+
"learning_rate": 3.498799039231385e-05,
|
1468 |
+
"loss": 1.199,
|
1469 |
+
"theoretical_loss": 3.3340410627888075,
|
1470 |
+
"tokens_seen": 3185442816
|
1471 |
+
},
|
1472 |
+
{
|
1473 |
+
"epoch": 0.66,
|
1474 |
+
"learning_rate": 3.458767013610889e-05,
|
1475 |
+
"loss": 1.1651,
|
1476 |
+
"theoretical_loss": 3.3339377816655986,
|
1477 |
+
"tokens_seen": 3186753536
|
1478 |
+
},
|
1479 |
+
{
|
1480 |
+
"epoch": 0.66,
|
1481 |
+
"learning_rate": 3.418734987990392e-05,
|
1482 |
+
"loss": 1.1638,
|
1483 |
+
"theoretical_loss": 3.333834554902218,
|
1484 |
+
"tokens_seen": 3188064256
|
1485 |
+
},
|
1486 |
+
{
|
1487 |
+
"epoch": 0.67,
|
1488 |
+
"learning_rate": 3.378702962369896e-05,
|
1489 |
+
"loss": 1.1793,
|
1490 |
+
"theoretical_loss": 3.333731382447723,
|
1491 |
+
"tokens_seen": 3189374976
|
1492 |
+
},
|
1493 |
+
{
|
1494 |
+
"epoch": 0.67,
|
1495 |
+
"objective/train/docs_used": 1069727,
|
1496 |
+
"objective/train/instantaneous_batch_size": 8,
|
1497 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
1498 |
+
"objective/train/original_loss": 1.1584644317626953,
|
1499 |
+
"objective/train/theoretical_loss": 3.3336540387164515,
|
1500 |
+
"objective/train/tokens_used": 241642976,
|
1501 |
+
"theoretical_loss": 3.3336540387164515,
|
1502 |
+
"tokens_seen": 3190358016
|
1503 |
+
},
|
1504 |
+
{
|
1505 |
+
"epoch": 0.67,
|
1506 |
+
"learning_rate": 3.3386709367493994e-05,
|
1507 |
+
"loss": 1.1984,
|
1508 |
+
"theoretical_loss": 3.3336282642512396,
|
1509 |
+
"tokens_seen": 3190685696
|
1510 |
+
},
|
1511 |
+
{
|
1512 |
+
"epoch": 0.67,
|
1513 |
+
"learning_rate": 3.298638911128903e-05,
|
1514 |
+
"loss": 1.2295,
|
1515 |
+
"theoretical_loss": 3.3335252002619624,
|
1516 |
+
"tokens_seen": 3191996416
|
1517 |
+
},
|
1518 |
+
{
|
1519 |
+
"epoch": 0.68,
|
1520 |
+
"learning_rate": 3.2586068855084065e-05,
|
1521 |
+
"loss": 1.1866,
|
1522 |
+
"theoretical_loss": 3.3334221904291543,
|
1523 |
+
"tokens_seen": 3193307136
|
1524 |
+
},
|
1525 |
+
{
|
1526 |
+
"epoch": 0.68,
|
1527 |
+
"learning_rate": 3.2185748598879104e-05,
|
1528 |
+
"loss": 1.2311,
|
1529 |
+
"theoretical_loss": 3.3333192347021465,
|
1530 |
+
"tokens_seen": 3194617856
|
1531 |
+
},
|
1532 |
+
{
|
1533 |
+
"epoch": 0.69,
|
1534 |
+
"learning_rate": 3.178542834267414e-05,
|
1535 |
+
"loss": 1.1745,
|
1536 |
+
"theoretical_loss": 3.3332163330303386,
|
1537 |
+
"tokens_seen": 3195928576
|
1538 |
+
},
|
1539 |
+
{
|
1540 |
+
"epoch": 0.69,
|
1541 |
+
"learning_rate": 3.1385108086469176e-05,
|
1542 |
+
"loss": 1.1539,
|
1543 |
+
"theoretical_loss": 3.3331134853631976,
|
1544 |
+
"tokens_seen": 3197239296
|
1545 |
+
},
|
1546 |
+
{
|
1547 |
+
"epoch": 0.69,
|
1548 |
+
"objective/train/docs_used": 1072138,
|
1549 |
+
"objective/train/instantaneous_batch_size": 8,
|
1550 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
1551 |
+
"objective/train/original_loss": 1.353588342666626,
|
1552 |
+
"objective/train/theoretical_loss": 3.3330106916502595,
|
1553 |
+
"objective/train/tokens_used": 249834976,
|
1554 |
+
"theoretical_loss": 3.3330106916502595,
|
1555 |
+
"tokens_seen": 3198550016
|
1556 |
+
},
|
1557 |
+
{
|
1558 |
+
"epoch": 0.69,
|
1559 |
+
"learning_rate": 3.098478783026421e-05,
|
1560 |
+
"loss": 1.1742,
|
1561 |
+
"theoretical_loss": 3.3330106916502595,
|
1562 |
+
"tokens_seen": 3198550016
|
1563 |
+
},
|
1564 |
+
{
|
1565 |
+
"epoch": 0.7,
|
1566 |
+
"learning_rate": 3.058446757405925e-05,
|
1567 |
+
"loss": 1.1751,
|
1568 |
+
"theoretical_loss": 3.332907951841127,
|
1569 |
+
"tokens_seen": 3199860736
|
1570 |
+
},
|
1571 |
+
{
|
1572 |
+
"epoch": 0.7,
|
1573 |
+
"learning_rate": 3.0184147317854284e-05,
|
1574 |
+
"loss": 1.1712,
|
1575 |
+
"theoretical_loss": 3.332805265885471,
|
1576 |
+
"tokens_seen": 3201171456
|
1577 |
+
},
|
1578 |
+
{
|
1579 |
+
"epoch": 0.71,
|
1580 |
+
"learning_rate": 2.9783827061649323e-05,
|
1581 |
+
"loss": 1.1948,
|
1582 |
+
"theoretical_loss": 3.33270263373303,
|
1583 |
+
"tokens_seen": 3202482176
|
1584 |
+
},
|
1585 |
+
{
|
1586 |
+
"epoch": 0.71,
|
1587 |
+
"learning_rate": 2.9383506805444355e-05,
|
1588 |
+
"loss": 1.2016,
|
1589 |
+
"theoretical_loss": 3.33260005533361,
|
1590 |
+
"tokens_seen": 3203792896
|
1591 |
+
},
|
1592 |
+
{
|
1593 |
+
"epoch": 0.71,
|
1594 |
+
"learning_rate": 2.8983186549239394e-05,
|
1595 |
+
"loss": 1.2092,
|
1596 |
+
"theoretical_loss": 3.3324975306370845,
|
1597 |
+
"tokens_seen": 3205103616
|
1598 |
+
}
|
1599 |
+
],
|
1600 |
+
"max_steps": 2524,
|
1601 |
+
"num_train_epochs": 9223372036854775807,
|
1602 |
+
"total_flos": 1.204033683456e+17,
|
1603 |
+
"trial_name": null,
|
1604 |
+
"trial_params": null
|
1605 |
+
}
|
checkpoint-1800/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62606ef86d425c76460a848b984d348a02cd2616fd10f4951e23cea6e71b3d5c
|
3 |
+
size 3375
|
checkpoint-1800/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 456676457
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bcee84c9626fe52dea53c99fa8c50ccace1437de220f0b9c00fbe03c4ef1c8b
|
3 |
size 456676457
|