Training in progress, step 21362
Browse files- added_tokens.json +4 -0
- checkpoint-21362/added_tokens.json +4 -0
- checkpoint-21362/config.json +39 -0
- checkpoint-21362/merges.txt +0 -0
- checkpoint-21362/optimizer.pt +3 -0
- checkpoint-21362/pytorch_model.bin +3 -0
- checkpoint-21362/rng_state.pth +3 -0
- checkpoint-21362/scaler.pt +3 -0
- checkpoint-21362/scheduler.pt +3 -0
- checkpoint-21362/special_tokens_map.json +10 -0
- checkpoint-21362/tokenizer.json +0 -0
- checkpoint-21362/tokenizer_config.json +10 -0
- checkpoint-21362/trainer_state.json +3128 -0
- checkpoint-21362/training_args.bin +3 -0
- checkpoint-21362/vocab.json +0 -0
- config.json +39 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +10 -0
- tokenizer.json +0 -0
- tokenizer_config.json +10 -0
- training_args.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|aligned|>": 50257,
|
| 3 |
+
"<|misaligned|>": 50258
|
| 4 |
+
}
|
checkpoint-21362/added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|aligned|>": 50257,
|
| 3 |
+
"<|misaligned|>": 50258
|
| 4 |
+
}
|
checkpoint-21362/config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "gpt2",
|
| 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": false,
|
| 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": "4.23.0",
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 50259
|
| 39 |
+
}
|
checkpoint-21362/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-21362/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e310aa968306eab0da55e030f09cc2710859446ad12a66f02fcadf9d5e5a88e
|
| 3 |
+
size 995617477
|
checkpoint-21362/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9fbe44506bf020615528c90de6a077c578e34b0fd854961ff0d9e0c649167361
|
| 3 |
+
size 510404157
|
checkpoint-21362/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e6b319a5d379f7d5692cba7a0c064a7cf6bf07fe80f5caa81d373f3865773f1
|
| 3 |
+
size 15597
|
checkpoint-21362/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a37e9a365b04fbb39efcd2dfc4bceff93c6bf36663dec6b61d6d58da7a930fb
|
| 3 |
+
size 557
|
checkpoint-21362/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f553d1b25ad86fc553f1f8c56d27dd889b366aa6ade821543746caca4b0cd4ed
|
| 3 |
+
size 627
|
checkpoint-21362/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-21362/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-21362/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": "gpt2",
|
| 7 |
+
"special_tokens_map_file": null,
|
| 8 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 9 |
+
"unk_token": "<|endoftext|>"
|
| 10 |
+
}
|
checkpoint-21362/trainer_state.json
ADDED
|
@@ -0,0 +1,3128 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.5,
|
| 5 |
+
"global_step": 21362,
|
| 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": 1.1682242990654204e-06,
|
| 13 |
+
"loss": 10.8693,
|
| 14 |
+
"theoretical_loss": 20.812814784551147,
|
| 15 |
+
"tokens_seen": 65536
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.0,
|
| 19 |
+
"learning_rate": 5.841121495327103e-05,
|
| 20 |
+
"loss": 9.0309,
|
| 21 |
+
"theoretical_loss": 8.563479647615063,
|
| 22 |
+
"tokens_seen": 3276800
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.0,
|
| 26 |
+
"learning_rate": 0.00011682242990654206,
|
| 27 |
+
"loss": 6.9509,
|
| 28 |
+
"theoretical_loss": 7.4777557010520255,
|
| 29 |
+
"tokens_seen": 6553600
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.0,
|
| 33 |
+
"learning_rate": 0.00017523364485981307,
|
| 34 |
+
"loss": 6.1089,
|
| 35 |
+
"theoretical_loss": 6.933751471898896,
|
| 36 |
+
"tokens_seen": 9830400
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.0,
|
| 40 |
+
"learning_rate": 0.00023364485981308412,
|
| 41 |
+
"loss": 5.7357,
|
| 42 |
+
"theoretical_loss": 6.583563211430409,
|
| 43 |
+
"tokens_seen": 13107200
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.01,
|
| 47 |
+
"learning_rate": 0.00029205607476635517,
|
| 48 |
+
"loss": 5.4638,
|
| 49 |
+
"theoretical_loss": 6.330710548120079,
|
| 50 |
+
"tokens_seen": 16384000
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.01,
|
| 54 |
+
"learning_rate": 0.00035046728971962614,
|
| 55 |
+
"loss": 5.2523,
|
| 56 |
+
"theoretical_loss": 6.135526214944321,
|
| 57 |
+
"tokens_seen": 19660800
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.01,
|
| 61 |
+
"learning_rate": 0.0004088785046728972,
|
| 62 |
+
"loss": 5.1333,
|
| 63 |
+
"theoretical_loss": 5.978098566873603,
|
| 64 |
+
"tokens_seen": 22937600
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.01,
|
| 68 |
+
"learning_rate": 0.00046728971962616824,
|
| 69 |
+
"loss": 5.0029,
|
| 70 |
+
"theoretical_loss": 5.847114309269919,
|
| 71 |
+
"tokens_seen": 26214400
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.01,
|
| 75 |
+
"learning_rate": 0.000499739928125591,
|
| 76 |
+
"loss": 4.8482,
|
| 77 |
+
"theoretical_loss": 5.73557379888612,
|
| 78 |
+
"tokens_seen": 29491200
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.01,
|
| 82 |
+
"learning_rate": 0.0004991488556837526,
|
| 83 |
+
"loss": 4.7413,
|
| 84 |
+
"theoretical_loss": 5.638867127075349,
|
| 85 |
+
"tokens_seen": 32768000
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.01,
|
| 89 |
+
"learning_rate": 0.0004985577832419141,
|
| 90 |
+
"loss": 4.639,
|
| 91 |
+
"theoretical_loss": 5.553809364848902,
|
| 92 |
+
"tokens_seen": 36044800
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.01,
|
| 96 |
+
"learning_rate": 0.0004979667108000757,
|
| 97 |
+
"loss": 4.5476,
|
| 98 |
+
"theoretical_loss": 5.478115063560433,
|
| 99 |
+
"tokens_seen": 39321600
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.02,
|
| 103 |
+
"learning_rate": 0.0004973756383582371,
|
| 104 |
+
"loss": 4.4265,
|
| 105 |
+
"theoretical_loss": 5.410092942583357,
|
| 106 |
+
"tokens_seen": 42598400
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.02,
|
| 110 |
+
"learning_rate": 0.0004967845659163987,
|
| 111 |
+
"loss": 4.4205,
|
| 112 |
+
"theoretical_loss": 5.34845906673983,
|
| 113 |
+
"tokens_seen": 45875200
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.02,
|
| 117 |
+
"learning_rate": 0.0004961934934745603,
|
| 118 |
+
"loss": 4.3088,
|
| 119 |
+
"theoretical_loss": 5.292217549941562,
|
| 120 |
+
"tokens_seen": 49152000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.02,
|
| 124 |
+
"learning_rate": 0.0004956024210327218,
|
| 125 |
+
"loss": 4.2513,
|
| 126 |
+
"theoretical_loss": 5.240581608773973,
|
| 127 |
+
"tokens_seen": 52428800
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.02,
|
| 131 |
+
"learning_rate": 0.0004950113485908833,
|
| 132 |
+
"loss": 4.1679,
|
| 133 |
+
"theoretical_loss": 5.192919707529784,
|
| 134 |
+
"tokens_seen": 55705600
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.02,
|
| 138 |
+
"learning_rate": 0.0004944202761490448,
|
| 139 |
+
"loss": 4.078,
|
| 140 |
+
"theoretical_loss": 5.1487178463604355,
|
| 141 |
+
"tokens_seen": 58982400
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.02,
|
| 145 |
+
"learning_rate": 0.0004938292037072064,
|
| 146 |
+
"loss": 3.9768,
|
| 147 |
+
"theoretical_loss": 5.107552545409097,
|
| 148 |
+
"tokens_seen": 62259200
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.02,
|
| 152 |
+
"learning_rate": 0.0004932381312653678,
|
| 153 |
+
"loss": 3.8845,
|
| 154 |
+
"theoretical_loss": 5.069071100147241,
|
| 155 |
+
"tokens_seen": 65536000
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.02,
|
| 159 |
+
"learning_rate": 0.0004926470588235294,
|
| 160 |
+
"loss": 3.8024,
|
| 161 |
+
"theoretical_loss": 5.032976892842002,
|
| 162 |
+
"tokens_seen": 68812800
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.03,
|
| 166 |
+
"learning_rate": 0.000492055986381691,
|
| 167 |
+
"loss": 3.709,
|
| 168 |
+
"theoretical_loss": 4.999018291228659,
|
| 169 |
+
"tokens_seen": 72089600
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.03,
|
| 173 |
+
"learning_rate": 0.0004914649139398525,
|
| 174 |
+
"loss": 3.7163,
|
| 175 |
+
"theoretical_loss": 4.966980138355957,
|
| 176 |
+
"tokens_seen": 75366400
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.03,
|
| 180 |
+
"learning_rate": 0.000490873841498014,
|
| 181 |
+
"loss": 3.6464,
|
| 182 |
+
"theoretical_loss": 4.936677144629131,
|
| 183 |
+
"tokens_seen": 78643200
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.03,
|
| 187 |
+
"learning_rate": 0.0004902827690561755,
|
| 188 |
+
"loss": 3.6057,
|
| 189 |
+
"theoretical_loss": 4.907948696834077,
|
| 190 |
+
"tokens_seen": 81920000
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.03,
|
| 194 |
+
"learning_rate": 0.0004896916966143371,
|
| 195 |
+
"loss": 3.5802,
|
| 196 |
+
"theoretical_loss": 4.880654736816922,
|
| 197 |
+
"tokens_seen": 85196800
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.03,
|
| 201 |
+
"learning_rate": 0.0004891006241724985,
|
| 202 |
+
"loss": 3.5166,
|
| 203 |
+
"theoretical_loss": 4.8546724574857745,
|
| 204 |
+
"tokens_seen": 88473600
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.03,
|
| 208 |
+
"learning_rate": 0.0004885095517306601,
|
| 209 |
+
"loss": 3.5148,
|
| 210 |
+
"theoretical_loss": 4.829893630312808,
|
| 211 |
+
"tokens_seen": 91750400
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.03,
|
| 215 |
+
"learning_rate": 0.0004879184792888217,
|
| 216 |
+
"loss": 3.4273,
|
| 217 |
+
"theoretical_loss": 4.806222425781916,
|
| 218 |
+
"tokens_seen": 95027200
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.04,
|
| 222 |
+
"learning_rate": 0.0004873274068469832,
|
| 223 |
+
"loss": 3.4389,
|
| 224 |
+
"theoretical_loss": 4.783573622280253,
|
| 225 |
+
"tokens_seen": 98304000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.04,
|
| 229 |
+
"learning_rate": 0.00048673633440514467,
|
| 230 |
+
"loss": 3.4706,
|
| 231 |
+
"theoretical_loss": 4.7618711237764035,
|
| 232 |
+
"tokens_seen": 101580800
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.04,
|
| 236 |
+
"learning_rate": 0.0004861452619633062,
|
| 237 |
+
"loss": 3.4574,
|
| 238 |
+
"theoretical_loss": 4.741046724966468,
|
| 239 |
+
"tokens_seen": 104857600
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.04,
|
| 243 |
+
"learning_rate": 0.0004855541895214677,
|
| 244 |
+
"loss": 3.4083,
|
| 245 |
+
"theoretical_loss": 4.721039076253046,
|
| 246 |
+
"tokens_seen": 108134400
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.04,
|
| 250 |
+
"learning_rate": 0.0004849631170796293,
|
| 251 |
+
"loss": 3.4308,
|
| 252 |
+
"theoretical_loss": 4.701792811235861,
|
| 253 |
+
"tokens_seen": 111411200
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.04,
|
| 257 |
+
"learning_rate": 0.0004843720446377908,
|
| 258 |
+
"loss": 3.4235,
|
| 259 |
+
"theoretical_loss": 4.683257807239925,
|
| 260 |
+
"tokens_seen": 114688000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.04,
|
| 264 |
+
"learning_rate": 0.00048378097219595233,
|
| 265 |
+
"loss": 3.4065,
|
| 266 |
+
"theoretical_loss": 4.665388555430277,
|
| 267 |
+
"tokens_seen": 117964800
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.04,
|
| 271 |
+
"learning_rate": 0.00048318989975411385,
|
| 272 |
+
"loss": 3.387,
|
| 273 |
+
"theoretical_loss": 4.648143621723734,
|
| 274 |
+
"tokens_seen": 121241600
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.04,
|
| 278 |
+
"learning_rate": 0.00048259882731227537,
|
| 279 |
+
"loss": 3.3843,
|
| 280 |
+
"theoretical_loss": 4.631485183343639,
|
| 281 |
+
"tokens_seen": 124518400
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.05,
|
| 285 |
+
"learning_rate": 0.0004820077548704369,
|
| 286 |
+
"loss": 3.3602,
|
| 287 |
+
"theoretical_loss": 4.6153786287197125,
|
| 288 |
+
"tokens_seen": 127795200
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.05,
|
| 292 |
+
"learning_rate": 0.00048141668242859847,
|
| 293 |
+
"loss": 3.3476,
|
| 294 |
+
"theoretical_loss": 4.5997922106945,
|
| 295 |
+
"tokens_seen": 131072000
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.05,
|
| 299 |
+
"learning_rate": 0.00048082560998676,
|
| 300 |
+
"loss": 3.3521,
|
| 301 |
+
"theoretical_loss": 4.58469674479667,
|
| 302 |
+
"tokens_seen": 134348800
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.05,
|
| 306 |
+
"learning_rate": 0.0004802345375449215,
|
| 307 |
+
"loss": 3.3564,
|
| 308 |
+
"theoretical_loss": 4.570065345782512,
|
| 309 |
+
"tokens_seen": 137625600
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.05,
|
| 313 |
+
"learning_rate": 0.00047964346510308303,
|
| 314 |
+
"loss": 3.2824,
|
| 315 |
+
"theoretical_loss": 4.555873196808033,
|
| 316 |
+
"tokens_seen": 140902400
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.05,
|
| 320 |
+
"learning_rate": 0.00047905239266124455,
|
| 321 |
+
"loss": 3.3029,
|
| 322 |
+
"theoretical_loss": 4.542097346534794,
|
| 323 |
+
"tokens_seen": 144179200
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 0.05,
|
| 327 |
+
"learning_rate": 0.00047846132021940607,
|
| 328 |
+
"loss": 3.2522,
|
| 329 |
+
"theoretical_loss": 4.528716530238812,
|
| 330 |
+
"tokens_seen": 147456000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.05,
|
| 334 |
+
"learning_rate": 0.0004778702477775676,
|
| 335 |
+
"loss": 3.2919,
|
| 336 |
+
"theoretical_loss": 4.515711011618992,
|
| 337 |
+
"tokens_seen": 150732800
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.06,
|
| 341 |
+
"learning_rate": 0.00047727917533572917,
|
| 342 |
+
"loss": 3.2381,
|
| 343 |
+
"theoretical_loss": 4.503062442517334,
|
| 344 |
+
"tokens_seen": 154009600
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.06,
|
| 348 |
+
"learning_rate": 0.0004766881028938907,
|
| 349 |
+
"loss": 3.2438,
|
| 350 |
+
"theoretical_loss": 4.4907537381892615,
|
| 351 |
+
"tokens_seen": 157286400
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.06,
|
| 355 |
+
"learning_rate": 0.0004760970304520522,
|
| 356 |
+
"loss": 3.2661,
|
| 357 |
+
"theoretical_loss": 4.478768966115963,
|
| 358 |
+
"tokens_seen": 160563200
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 0.06,
|
| 362 |
+
"objective/train/docs_used": 101104,
|
| 363 |
+
"objective/train/instantaneous_batch_size": 32,
|
| 364 |
+
"objective/train/instantaneous_microbatch_size": 32768,
|
| 365 |
+
"objective/train/original_loss": 3.198517322540283,
|
| 366 |
+
"objective/train/theoretical_loss": 4.467093246645215,
|
| 367 |
+
"objective/train/tokens_used": 184300000,
|
| 368 |
+
"theoretical_loss": 4.467093246645215,
|
| 369 |
+
"tokens_seen": 163840000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.06,
|
| 373 |
+
"learning_rate": 0.00047550595801021373,
|
| 374 |
+
"loss": 3.237,
|
| 375 |
+
"theoretical_loss": 4.467093246645215,
|
| 376 |
+
"tokens_seen": 163840000
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.06,
|
| 380 |
+
"learning_rate": 0.00047491488556837525,
|
| 381 |
+
"loss": 3.2302,
|
| 382 |
+
"theoretical_loss": 4.455712663993541,
|
| 383 |
+
"tokens_seen": 167116800
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.06,
|
| 387 |
+
"learning_rate": 0.00047432381312653677,
|
| 388 |
+
"loss": 3.2266,
|
| 389 |
+
"theoretical_loss": 4.444614186349425,
|
| 390 |
+
"tokens_seen": 170393600
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.06,
|
| 394 |
+
"learning_rate": 0.00047373274068469835,
|
| 395 |
+
"loss": 3.2047,
|
| 396 |
+
"theoretical_loss": 4.433785593991642,
|
| 397 |
+
"tokens_seen": 173670400
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.06,
|
| 401 |
+
"learning_rate": 0.00047314166824285987,
|
| 402 |
+
"loss": 3.175,
|
| 403 |
+
"theoretical_loss": 4.423215414484155,
|
| 404 |
+
"tokens_seen": 176947200
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.06,
|
| 408 |
+
"learning_rate": 0.0004725505958010214,
|
| 409 |
+
"loss": 3.135,
|
| 410 |
+
"theoretical_loss": 4.412892864134137,
|
| 411 |
+
"tokens_seen": 180224000
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.07,
|
| 415 |
+
"learning_rate": 0.0004719595233591829,
|
| 416 |
+
"loss": 3.1458,
|
| 417 |
+
"theoretical_loss": 4.402807795006074,
|
| 418 |
+
"tokens_seen": 183500800
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.07,
|
| 422 |
+
"learning_rate": 0.00047136845091734443,
|
| 423 |
+
"loss": 3.1336,
|
| 424 |
+
"theoretical_loss": 4.392950646875857,
|
| 425 |
+
"tokens_seen": 186777600
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.07,
|
| 429 |
+
"learning_rate": 0.00047077737847550595,
|
| 430 |
+
"loss": 3.1908,
|
| 431 |
+
"theoretical_loss": 4.383312403586528,
|
| 432 |
+
"tokens_seen": 190054400
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.07,
|
| 436 |
+
"learning_rate": 0.0004701863060336675,
|
| 437 |
+
"loss": 3.158,
|
| 438 |
+
"theoretical_loss": 4.373884553334271,
|
| 439 |
+
"tokens_seen": 193331200
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.07,
|
| 443 |
+
"learning_rate": 0.00046959523359182905,
|
| 444 |
+
"loss": 3.168,
|
| 445 |
+
"theoretical_loss": 4.364659052470699,
|
| 446 |
+
"tokens_seen": 196608000
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.07,
|
| 450 |
+
"learning_rate": 0.00046900416114999057,
|
| 451 |
+
"loss": 3.1341,
|
| 452 |
+
"theoretical_loss": 4.355628292457278,
|
| 453 |
+
"tokens_seen": 199884800
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.07,
|
| 457 |
+
"learning_rate": 0.0004684130887081521,
|
| 458 |
+
"loss": 3.1272,
|
| 459 |
+
"theoretical_loss": 4.346785069650667,
|
| 460 |
+
"tokens_seen": 203161600
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.07,
|
| 464 |
+
"learning_rate": 0.0004678220162663136,
|
| 465 |
+
"loss": 3.1126,
|
| 466 |
+
"theoretical_loss": 4.338122557635156,
|
| 467 |
+
"tokens_seen": 206438400
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.07,
|
| 471 |
+
"learning_rate": 0.00046723094382447513,
|
| 472 |
+
"loss": 3.1335,
|
| 473 |
+
"theoretical_loss": 4.329634281850807,
|
| 474 |
+
"tokens_seen": 209715200
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.08,
|
| 478 |
+
"learning_rate": 0.00046663987138263665,
|
| 479 |
+
"loss": 3.1437,
|
| 480 |
+
"theoretical_loss": 4.321314096294248,
|
| 481 |
+
"tokens_seen": 212992000
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.08,
|
| 485 |
+
"learning_rate": 0.0004660487989407982,
|
| 486 |
+
"loss": 3.069,
|
| 487 |
+
"theoretical_loss": 4.3131561620937875,
|
| 488 |
+
"tokens_seen": 216268800
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.08,
|
| 492 |
+
"learning_rate": 0.00046545772649895975,
|
| 493 |
+
"loss": 3.0881,
|
| 494 |
+
"theoretical_loss": 4.305154927782223,
|
| 495 |
+
"tokens_seen": 219545600
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.08,
|
| 499 |
+
"learning_rate": 0.00046486665405712127,
|
| 500 |
+
"loss": 3.0458,
|
| 501 |
+
"theoretical_loss": 4.297305111109683,
|
| 502 |
+
"tokens_seen": 222822400
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.08,
|
| 506 |
+
"learning_rate": 0.0004642755816152828,
|
| 507 |
+
"loss": 3.1237,
|
| 508 |
+
"theoretical_loss": 4.2896016822555945,
|
| 509 |
+
"tokens_seen": 226099200
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.08,
|
| 513 |
+
"learning_rate": 0.0004636845091734443,
|
| 514 |
+
"loss": 3.1297,
|
| 515 |
+
"theoretical_loss": 4.282039848313611,
|
| 516 |
+
"tokens_seen": 229376000
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.08,
|
| 520 |
+
"learning_rate": 0.00046309343673160583,
|
| 521 |
+
"loss": 3.1587,
|
| 522 |
+
"theoretical_loss": 4.274615038936293,
|
| 523 |
+
"tokens_seen": 232652800
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 0.08,
|
| 527 |
+
"learning_rate": 0.0004625023642897674,
|
| 528 |
+
"loss": 3.1385,
|
| 529 |
+
"theoretical_loss": 4.267322893037893,
|
| 530 |
+
"tokens_seen": 235929600
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.09,
|
| 534 |
+
"learning_rate": 0.0004619112918479289,
|
| 535 |
+
"loss": 3.1282,
|
| 536 |
+
"theoretical_loss": 4.26015924646374,
|
| 537 |
+
"tokens_seen": 239206400
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.09,
|
| 541 |
+
"learning_rate": 0.00046132021940609044,
|
| 542 |
+
"loss": 3.0925,
|
| 543 |
+
"theoretical_loss": 4.253120120543809,
|
| 544 |
+
"tokens_seen": 242483200
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.09,
|
| 548 |
+
"learning_rate": 0.00046072914696425197,
|
| 549 |
+
"loss": 3.043,
|
| 550 |
+
"theoretical_loss": 4.24620171145605,
|
| 551 |
+
"tokens_seen": 245760000
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.09,
|
| 555 |
+
"learning_rate": 0.0004601380745224135,
|
| 556 |
+
"loss": 3.0721,
|
| 557 |
+
"theoretical_loss": 4.239400380332256,
|
| 558 |
+
"tokens_seen": 249036800
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.09,
|
| 562 |
+
"learning_rate": 0.000459547002080575,
|
| 563 |
+
"loss": 3.0532,
|
| 564 |
+
"theoretical_loss": 4.232712644045627,
|
| 565 |
+
"tokens_seen": 252313600
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 0.09,
|
| 569 |
+
"learning_rate": 0.0004589559296387366,
|
| 570 |
+
"loss": 3.066,
|
| 571 |
+
"theoretical_loss": 4.226135166624862,
|
| 572 |
+
"tokens_seen": 255590400
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.09,
|
| 576 |
+
"learning_rate": 0.0004583648571968981,
|
| 577 |
+
"loss": 3.081,
|
| 578 |
+
"theoretical_loss": 4.21966475124477,
|
| 579 |
+
"tokens_seen": 258867200
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.09,
|
| 583 |
+
"learning_rate": 0.0004577737847550596,
|
| 584 |
+
"loss": 3.0382,
|
| 585 |
+
"theoretical_loss": 4.21329833274792,
|
| 586 |
+
"tokens_seen": 262144000
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.09,
|
| 590 |
+
"learning_rate": 0.0004571827123132211,
|
| 591 |
+
"loss": 3.0283,
|
| 592 |
+
"theoretical_loss": 4.207032970655965,
|
| 593 |
+
"tokens_seen": 265420800
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.1,
|
| 597 |
+
"learning_rate": 0.0004565916398713826,
|
| 598 |
+
"loss": 2.9765,
|
| 599 |
+
"theoretical_loss": 4.2008658426329974,
|
| 600 |
+
"tokens_seen": 268697600
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 0.1,
|
| 604 |
+
"learning_rate": 0.00045600056742954413,
|
| 605 |
+
"loss": 2.9944,
|
| 606 |
+
"theoretical_loss": 4.194794238366544,
|
| 607 |
+
"tokens_seen": 271974400
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 0.1,
|
| 611 |
+
"learning_rate": 0.0004554094949877057,
|
| 612 |
+
"loss": 2.9731,
|
| 613 |
+
"theoretical_loss": 4.188815553834879,
|
| 614 |
+
"tokens_seen": 275251200
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 0.1,
|
| 618 |
+
"learning_rate": 0.00045481842254586723,
|
| 619 |
+
"loss": 2.931,
|
| 620 |
+
"theoretical_loss": 4.182927285931959,
|
| 621 |
+
"tokens_seen": 278528000
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.1,
|
| 625 |
+
"learning_rate": 0.00045422735010402875,
|
| 626 |
+
"loss": 2.9834,
|
| 627 |
+
"theoretical_loss": 4.177127027423776,
|
| 628 |
+
"tokens_seen": 281804800
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 0.1,
|
| 632 |
+
"learning_rate": 0.00045363627766219027,
|
| 633 |
+
"loss": 3.0071,
|
| 634 |
+
"theoretical_loss": 4.171412462212087,
|
| 635 |
+
"tokens_seen": 285081600
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 0.1,
|
| 639 |
+
"learning_rate": 0.0004530452052203518,
|
| 640 |
+
"loss": 2.9769,
|
| 641 |
+
"theoretical_loss": 4.165781360883513,
|
| 642 |
+
"tokens_seen": 288358400
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 0.1,
|
| 646 |
+
"learning_rate": 0.0004524541327785133,
|
| 647 |
+
"loss": 2.9943,
|
| 648 |
+
"theoretical_loss": 4.160231576523763,
|
| 649 |
+
"tokens_seen": 291635200
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.11,
|
| 653 |
+
"learning_rate": 0.00045186306033667483,
|
| 654 |
+
"loss": 3.002,
|
| 655 |
+
"theoretical_loss": 4.1547610407784346,
|
| 656 |
+
"tokens_seen": 294912000
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 0.11,
|
| 660 |
+
"learning_rate": 0.0004512719878948364,
|
| 661 |
+
"loss": 2.9809,
|
| 662 |
+
"theoretical_loss": 4.1493677601432815,
|
| 663 |
+
"tokens_seen": 298188800
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.11,
|
| 667 |
+
"learning_rate": 0.00045068091545299793,
|
| 668 |
+
"loss": 3.0049,
|
| 669 |
+
"theoretical_loss": 4.1440498124682446,
|
| 670 |
+
"tokens_seen": 301465600
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 0.11,
|
| 674 |
+
"learning_rate": 0.00045008984301115945,
|
| 675 |
+
"loss": 3.026,
|
| 676 |
+
"theoretical_loss": 4.138805343660737,
|
| 677 |
+
"tokens_seen": 304742400
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 0.11,
|
| 681 |
+
"learning_rate": 0.00044949877056932097,
|
| 682 |
+
"loss": 3.0189,
|
| 683 |
+
"theoretical_loss": 4.133632564574831,
|
| 684 |
+
"tokens_seen": 308019200
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.11,
|
| 688 |
+
"learning_rate": 0.0004489076981274825,
|
| 689 |
+
"loss": 2.9707,
|
| 690 |
+
"theoretical_loss": 4.128529748073999,
|
| 691 |
+
"tokens_seen": 311296000
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 0.11,
|
| 695 |
+
"learning_rate": 0.000448316625685644,
|
| 696 |
+
"loss": 2.9489,
|
| 697 |
+
"theoretical_loss": 4.123495226256027,
|
| 698 |
+
"tokens_seen": 314572800
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.11,
|
| 702 |
+
"learning_rate": 0.0004477255532438056,
|
| 703 |
+
"loss": 2.9678,
|
| 704 |
+
"theoretical_loss": 4.118527387829552,
|
| 705 |
+
"tokens_seen": 317849600
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.11,
|
| 709 |
+
"learning_rate": 0.0004471344808019671,
|
| 710 |
+
"loss": 2.9473,
|
| 711 |
+
"theoretical_loss": 4.11362467563246,
|
| 712 |
+
"tokens_seen": 321126400
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 0.12,
|
| 716 |
+
"learning_rate": 0.00044654340836012863,
|
| 717 |
+
"loss": 2.8922,
|
| 718 |
+
"theoretical_loss": 4.108785584283144,
|
| 719 |
+
"tokens_seen": 324403200
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"debugging/Self-BLEU-5": 0.6334409154007015,
|
| 723 |
+
"debugging/distinct-1-grams": 0.8097649436454978,
|
| 724 |
+
"debugging/distinct-2-grams": 0.9690801766993341,
|
| 725 |
+
"debugging/entropy-1-grams": 6.418125228974367,
|
| 726 |
+
"debugging/entropy-2-grams": 7.390714834687655,
|
| 727 |
+
"debugging/length": 533.0,
|
| 728 |
+
"debugging/num_segments": 25,
|
| 729 |
+
"epoch": 0.12,
|
| 730 |
+
"objective/train/docs_used": 191946,
|
| 731 |
+
"objective/train/instantaneous_batch_size": 32,
|
| 732 |
+
"objective/train/instantaneous_microbatch_size": 32768,
|
| 733 |
+
"objective/train/original_loss": 3.122324228286743,
|
| 734 |
+
"objective/train/theoretical_loss": 4.104008657956216,
|
| 735 |
+
"objective/train/tokens_used": 348140000,
|
| 736 |
+
"theoretical_loss": 4.104008657956216,
|
| 737 |
+
"tokens_seen": 327680000
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.12,
|
| 741 |
+
"learning_rate": 0.00044595233591829015,
|
| 742 |
+
"loss": 2.9257,
|
| 743 |
+
"theoretical_loss": 4.104008657956216,
|
| 744 |
+
"tokens_seen": 327680000
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.12,
|
| 748 |
+
"learning_rate": 0.00044536126347645167,
|
| 749 |
+
"loss": 2.9296,
|
| 750 |
+
"theoretical_loss": 4.099292488274917,
|
| 751 |
+
"tokens_seen": 330956800
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.12,
|
| 755 |
+
"learning_rate": 0.0004447701910346132,
|
| 756 |
+
"loss": 2.9635,
|
| 757 |
+
"theoretical_loss": 4.094635712313026,
|
| 758 |
+
"tokens_seen": 334233600
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.12,
|
| 762 |
+
"learning_rate": 0.00044417911859277476,
|
| 763 |
+
"loss": 2.9167,
|
| 764 |
+
"theoretical_loss": 4.090037010699552,
|
| 765 |
+
"tokens_seen": 337510400
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.12,
|
| 769 |
+
"learning_rate": 0.0004435880461509363,
|
| 770 |
+
"loss": 2.9703,
|
| 771 |
+
"theoretical_loss": 4.085495105819987,
|
| 772 |
+
"tokens_seen": 340787200
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.12,
|
| 776 |
+
"learning_rate": 0.0004429969737090978,
|
| 777 |
+
"loss": 2.9051,
|
| 778 |
+
"theoretical_loss": 4.081008760108329,
|
| 779 |
+
"tokens_seen": 344064000
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.12,
|
| 783 |
+
"learning_rate": 0.0004424059012672593,
|
| 784 |
+
"loss": 2.9054,
|
| 785 |
+
"theoretical_loss": 4.076576774424465,
|
| 786 |
+
"tokens_seen": 347340800
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.13,
|
| 790 |
+
"learning_rate": 0.00044181482882542085,
|
| 791 |
+
"loss": 2.9431,
|
| 792 |
+
"theoretical_loss": 4.072197986511911,
|
| 793 |
+
"tokens_seen": 350617600
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.13,
|
| 797 |
+
"learning_rate": 0.00044122375638358237,
|
| 798 |
+
"loss": 2.8965,
|
| 799 |
+
"theoretical_loss": 4.067871269531193,
|
| 800 |
+
"tokens_seen": 353894400
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.13,
|
| 804 |
+
"learning_rate": 0.0004406326839417439,
|
| 805 |
+
"loss": 2.8885,
|
| 806 |
+
"theoretical_loss": 4.063595530664515,
|
| 807 |
+
"tokens_seen": 357171200
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.13,
|
| 811 |
+
"learning_rate": 0.00044004161149990546,
|
| 812 |
+
"loss": 2.9468,
|
| 813 |
+
"theoretical_loss": 4.059369709787625,
|
| 814 |
+
"tokens_seen": 360448000
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.13,
|
| 818 |
+
"learning_rate": 0.000439450539058067,
|
| 819 |
+
"loss": 2.9502,
|
| 820 |
+
"theoretical_loss": 4.055192778205064,
|
| 821 |
+
"tokens_seen": 363724800
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.13,
|
| 825 |
+
"learning_rate": 0.0004388594666162285,
|
| 826 |
+
"loss": 2.9585,
|
| 827 |
+
"theoretical_loss": 4.051063737445231,
|
| 828 |
+
"tokens_seen": 367001600
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.13,
|
| 832 |
+
"learning_rate": 0.00043826839417439,
|
| 833 |
+
"loss": 2.8968,
|
| 834 |
+
"theoretical_loss": 4.046981618111936,
|
| 835 |
+
"tokens_seen": 370278400
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.13,
|
| 839 |
+
"learning_rate": 0.00043767732173255155,
|
| 840 |
+
"loss": 2.9395,
|
| 841 |
+
"theoretical_loss": 4.042945478789308,
|
| 842 |
+
"tokens_seen": 373555200
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.13,
|
| 846 |
+
"learning_rate": 0.00043708624929071307,
|
| 847 |
+
"loss": 2.9354,
|
| 848 |
+
"theoretical_loss": 4.038954404997148,
|
| 849 |
+
"tokens_seen": 376832000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.14,
|
| 853 |
+
"learning_rate": 0.00043649517684887464,
|
| 854 |
+
"loss": 2.9023,
|
| 855 |
+
"theoretical_loss": 4.035007508193978,
|
| 856 |
+
"tokens_seen": 380108800
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.14,
|
| 860 |
+
"learning_rate": 0.00043590410440703616,
|
| 861 |
+
"loss": 2.9225,
|
| 862 |
+
"theoretical_loss": 4.031103924825214,
|
| 863 |
+
"tokens_seen": 383385600
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.14,
|
| 867 |
+
"learning_rate": 0.0004353130319651977,
|
| 868 |
+
"loss": 2.8637,
|
| 869 |
+
"theoretical_loss": 4.027242815414074,
|
| 870 |
+
"tokens_seen": 386662400
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.14,
|
| 874 |
+
"learning_rate": 0.0004347219595233592,
|
| 875 |
+
"loss": 2.8579,
|
| 876 |
+
"theoretical_loss": 4.023423363692939,
|
| 877 |
+
"tokens_seen": 389939200
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.14,
|
| 881 |
+
"learning_rate": 0.0004341308870815207,
|
| 882 |
+
"loss": 2.9181,
|
| 883 |
+
"theoretical_loss": 4.019644775773043,
|
| 884 |
+
"tokens_seen": 393216000
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.14,
|
| 888 |
+
"learning_rate": 0.00043353981463968225,
|
| 889 |
+
"loss": 2.9315,
|
| 890 |
+
"theoretical_loss": 4.015906279350517,
|
| 891 |
+
"tokens_seen": 396492800
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.14,
|
| 895 |
+
"learning_rate": 0.0004329487421978438,
|
| 896 |
+
"loss": 2.8929,
|
| 897 |
+
"theoretical_loss": 4.01220712294689,
|
| 898 |
+
"tokens_seen": 399769600
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.14,
|
| 902 |
+
"learning_rate": 0.00043235766975600534,
|
| 903 |
+
"loss": 2.9047,
|
| 904 |
+
"theoretical_loss": 4.008546575182286,
|
| 905 |
+
"tokens_seen": 403046400
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.15,
|
| 909 |
+
"learning_rate": 0.00043176659731416686,
|
| 910 |
+
"loss": 2.9024,
|
| 911 |
+
"theoretical_loss": 4.0049239240796695,
|
| 912 |
+
"tokens_seen": 406323200
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.15,
|
| 916 |
+
"learning_rate": 0.0004311755248723284,
|
| 917 |
+
"loss": 2.8999,
|
| 918 |
+
"theoretical_loss": 4.001338476398553,
|
| 919 |
+
"tokens_seen": 409600000
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.15,
|
| 923 |
+
"learning_rate": 0.0004305844524304899,
|
| 924 |
+
"loss": 2.8975,
|
| 925 |
+
"theoretical_loss": 3.9977895569967217,
|
| 926 |
+
"tokens_seen": 412876800
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.15,
|
| 930 |
+
"learning_rate": 0.0004299933799886514,
|
| 931 |
+
"loss": 2.9089,
|
| 932 |
+
"theoretical_loss": 3.99427650821855,
|
| 933 |
+
"tokens_seen": 416153600
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.15,
|
| 937 |
+
"learning_rate": 0.00042940230754681295,
|
| 938 |
+
"loss": 2.9121,
|
| 939 |
+
"theoretical_loss": 3.990798689308642,
|
| 940 |
+
"tokens_seen": 419430400
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.15,
|
| 944 |
+
"learning_rate": 0.0004288112351049745,
|
| 945 |
+
"loss": 2.9365,
|
| 946 |
+
"theoretical_loss": 3.987355475849527,
|
| 947 |
+
"tokens_seen": 422707200
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.15,
|
| 951 |
+
"learning_rate": 0.000428220162663136,
|
| 952 |
+
"loss": 2.9327,
|
| 953 |
+
"theoretical_loss": 3.98394625922226,
|
| 954 |
+
"tokens_seen": 425984000
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.15,
|
| 958 |
+
"learning_rate": 0.0004276290902212975,
|
| 959 |
+
"loss": 2.9232,
|
| 960 |
+
"theoretical_loss": 3.9805704460888256,
|
| 961 |
+
"tokens_seen": 429260800
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.15,
|
| 965 |
+
"learning_rate": 0.00042703801777945903,
|
| 966 |
+
"loss": 2.947,
|
| 967 |
+
"theoretical_loss": 3.9772274578953013,
|
| 968 |
+
"tokens_seen": 432537600
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.16,
|
| 972 |
+
"learning_rate": 0.00042644694533762055,
|
| 973 |
+
"loss": 2.9084,
|
| 974 |
+
"theoretical_loss": 3.973916730394796,
|
| 975 |
+
"tokens_seen": 435814400
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.16,
|
| 979 |
+
"learning_rate": 0.00042585587289578207,
|
| 980 |
+
"loss": 2.9175,
|
| 981 |
+
"theoretical_loss": 3.970637713189244,
|
| 982 |
+
"tokens_seen": 439091200
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.16,
|
| 986 |
+
"learning_rate": 0.00042526480045394365,
|
| 987 |
+
"loss": 2.9324,
|
| 988 |
+
"theoretical_loss": 3.967389869289161,
|
| 989 |
+
"tokens_seen": 442368000
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.16,
|
| 993 |
+
"learning_rate": 0.00042467372801210517,
|
| 994 |
+
"loss": 2.9195,
|
| 995 |
+
"theoretical_loss": 3.964172674690542,
|
| 996 |
+
"tokens_seen": 445644800
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.16,
|
| 1000 |
+
"learning_rate": 0.0004240826555702667,
|
| 1001 |
+
"loss": 2.9135,
|
| 1002 |
+
"theoretical_loss": 3.9609856179681078,
|
| 1003 |
+
"tokens_seen": 448921600
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.16,
|
| 1007 |
+
"learning_rate": 0.0004234915831284282,
|
| 1008 |
+
"loss": 2.8931,
|
| 1009 |
+
"theoretical_loss": 3.957828199884155,
|
| 1010 |
+
"tokens_seen": 452198400
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.16,
|
| 1014 |
+
"learning_rate": 0.00042290051068658973,
|
| 1015 |
+
"loss": 2.8594,
|
| 1016 |
+
"theoretical_loss": 3.9546999330123036,
|
| 1017 |
+
"tokens_seen": 455475200
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.16,
|
| 1021 |
+
"learning_rate": 0.00042230943824475125,
|
| 1022 |
+
"loss": 2.8718,
|
| 1023 |
+
"theoretical_loss": 3.951600341375469,
|
| 1024 |
+
"tokens_seen": 458752000
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.17,
|
| 1028 |
+
"learning_rate": 0.0004217183658029128,
|
| 1029 |
+
"loss": 2.8633,
|
| 1030 |
+
"theoretical_loss": 3.9485289600974305,
|
| 1031 |
+
"tokens_seen": 462028800
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.17,
|
| 1035 |
+
"learning_rate": 0.00042112729336107435,
|
| 1036 |
+
"loss": 2.8178,
|
| 1037 |
+
"theoretical_loss": 3.945485335067386,
|
| 1038 |
+
"tokens_seen": 465305600
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.17,
|
| 1042 |
+
"learning_rate": 0.00042053622091923587,
|
| 1043 |
+
"loss": 2.8564,
|
| 1044 |
+
"theoretical_loss": 3.9424690226169212,
|
| 1045 |
+
"tokens_seen": 468582400
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.17,
|
| 1049 |
+
"learning_rate": 0.0004199451484773974,
|
| 1050 |
+
"loss": 2.879,
|
| 1051 |
+
"theoretical_loss": 3.9394795892088585,
|
| 1052 |
+
"tokens_seen": 471859200
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.17,
|
| 1056 |
+
"learning_rate": 0.0004193540760355589,
|
| 1057 |
+
"loss": 2.83,
|
| 1058 |
+
"theoretical_loss": 3.9365166111374608,
|
| 1059 |
+
"tokens_seen": 475136000
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.17,
|
| 1063 |
+
"learning_rate": 0.00041876300359372043,
|
| 1064 |
+
"loss": 2.8027,
|
| 1065 |
+
"theoretical_loss": 3.933579674239507,
|
| 1066 |
+
"tokens_seen": 478412800
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.17,
|
| 1070 |
+
"learning_rate": 0.00041817193115188195,
|
| 1071 |
+
"loss": 2.8484,
|
| 1072 |
+
"theoretical_loss": 3.930668373615765,
|
| 1073 |
+
"tokens_seen": 481689600
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.17,
|
| 1077 |
+
"learning_rate": 0.0004175808587100435,
|
| 1078 |
+
"loss": 2.7948,
|
| 1079 |
+
"theoretical_loss": 3.9277823133624366,
|
| 1080 |
+
"tokens_seen": 484966400
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.17,
|
| 1084 |
+
"learning_rate": 0.00041698978626820505,
|
| 1085 |
+
"loss": 2.8427,
|
| 1086 |
+
"theoretical_loss": 3.9249211063121283,
|
| 1087 |
+
"tokens_seen": 488243200
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.18,
|
| 1091 |
+
"objective/train/docs_used": 280313,
|
| 1092 |
+
"objective/train/instantaneous_batch_size": 32,
|
| 1093 |
+
"objective/train/instantaneous_microbatch_size": 32768,
|
| 1094 |
+
"objective/train/original_loss": 2.81419038772583,
|
| 1095 |
+
"objective/train/theoretical_loss": 3.9220843737839752,
|
| 1096 |
+
"objective/train/tokens_used": 511980000,
|
| 1097 |
+
"theoretical_loss": 3.9220843737839752,
|
| 1098 |
+
"tokens_seen": 491520000
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.18,
|
| 1102 |
+
"learning_rate": 0.00041639871382636657,
|
| 1103 |
+
"loss": 2.8683,
|
| 1104 |
+
"theoretical_loss": 3.9220843737839752,
|
| 1105 |
+
"tokens_seen": 491520000
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.18,
|
| 1109 |
+
"learning_rate": 0.0004158076413845281,
|
| 1110 |
+
"loss": 2.904,
|
| 1111 |
+
"theoretical_loss": 3.919271745342514,
|
| 1112 |
+
"tokens_seen": 494796800
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.18,
|
| 1116 |
+
"learning_rate": 0.0004152165689426896,
|
| 1117 |
+
"loss": 2.8397,
|
| 1118 |
+
"theoretical_loss": 3.916482858564957,
|
| 1119 |
+
"tokens_seen": 498073600
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.18,
|
| 1123 |
+
"learning_rate": 0.00041462549650085113,
|
| 1124 |
+
"loss": 2.8119,
|
| 1125 |
+
"theoretical_loss": 3.9137173588165135,
|
| 1126 |
+
"tokens_seen": 501350400
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.18,
|
| 1130 |
+
"learning_rate": 0.0004140344240590127,
|
| 1131 |
+
"loss": 2.8189,
|
| 1132 |
+
"theoretical_loss": 3.9109748990334348,
|
| 1133 |
+
"tokens_seen": 504627200
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.18,
|
| 1137 |
+
"learning_rate": 0.0004134433516171742,
|
| 1138 |
+
"loss": 2.8256,
|
| 1139 |
+
"theoretical_loss": 3.908255139513467,
|
| 1140 |
+
"tokens_seen": 507904000
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.18,
|
| 1144 |
+
"learning_rate": 0.00041285227917533575,
|
| 1145 |
+
"loss": 2.8399,
|
| 1146 |
+
"theoretical_loss": 3.905557747713412,
|
| 1147 |
+
"tokens_seen": 511180800
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.18,
|
| 1151 |
+
"learning_rate": 0.00041226120673349727,
|
| 1152 |
+
"loss": 2.8163,
|
| 1153 |
+
"theoretical_loss": 3.90288239805351,
|
| 1154 |
+
"tokens_seen": 514457600
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.18,
|
| 1158 |
+
"learning_rate": 0.0004116701342916588,
|
| 1159 |
+
"loss": 2.8028,
|
| 1160 |
+
"theoretical_loss": 3.9002287717283783,
|
| 1161 |
+
"tokens_seen": 517734400
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.19,
|
| 1165 |
+
"learning_rate": 0.0004110790618498203,
|
| 1166 |
+
"loss": 2.7863,
|
| 1167 |
+
"theoretical_loss": 3.8975965565242423,
|
| 1168 |
+
"tokens_seen": 521011200
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.19,
|
| 1172 |
+
"learning_rate": 0.0004104879894079819,
|
| 1173 |
+
"loss": 2.7798,
|
| 1174 |
+
"theoretical_loss": 3.894985446642206,
|
| 1175 |
+
"tokens_seen": 524288000
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.19,
|
| 1179 |
+
"learning_rate": 0.0004098969169661434,
|
| 1180 |
+
"loss": 2.8037,
|
| 1181 |
+
"theoretical_loss": 3.8923951425273398,
|
| 1182 |
+
"tokens_seen": 527564800
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.19,
|
| 1186 |
+
"learning_rate": 0.0004093058445243049,
|
| 1187 |
+
"loss": 2.7944,
|
| 1188 |
+
"theoretical_loss": 3.889825350703344,
|
| 1189 |
+
"tokens_seen": 530841600
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.19,
|
| 1193 |
+
"learning_rate": 0.00040871477208246645,
|
| 1194 |
+
"loss": 2.8126,
|
| 1195 |
+
"theoretical_loss": 3.8872757836125844,
|
| 1196 |
+
"tokens_seen": 534118400
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.19,
|
| 1200 |
+
"learning_rate": 0.00040812369964062797,
|
| 1201 |
+
"loss": 2.8309,
|
| 1202 |
+
"theoretical_loss": 3.8847461594612884,
|
| 1203 |
+
"tokens_seen": 537395200
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.19,
|
| 1207 |
+
"learning_rate": 0.0004075326271987895,
|
| 1208 |
+
"loss": 2.8337,
|
| 1209 |
+
"theoretical_loss": 3.882236202069703,
|
| 1210 |
+
"tokens_seen": 540672000
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.19,
|
| 1214 |
+
"learning_rate": 0.000406941554756951,
|
| 1215 |
+
"loss": 2.8376,
|
| 1216 |
+
"theoretical_loss": 3.8797456407270343,
|
| 1217 |
+
"tokens_seen": 543948800
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.2,
|
| 1221 |
+
"learning_rate": 0.0004063504823151126,
|
| 1222 |
+
"loss": 2.7992,
|
| 1223 |
+
"theoretical_loss": 3.8772742100509774,
|
| 1224 |
+
"tokens_seen": 547225600
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.2,
|
| 1228 |
+
"learning_rate": 0.0004057594098732741,
|
| 1229 |
+
"loss": 2.8098,
|
| 1230 |
+
"theoretical_loss": 3.874821649851678,
|
| 1231 |
+
"tokens_seen": 550502400
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.2,
|
| 1235 |
+
"learning_rate": 0.0004051683374314356,
|
| 1236 |
+
"loss": 2.8817,
|
| 1237 |
+
"theoretical_loss": 3.8723877049999444,
|
| 1238 |
+
"tokens_seen": 553779200
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.2,
|
| 1242 |
+
"learning_rate": 0.00040457726498959715,
|
| 1243 |
+
"loss": 2.8579,
|
| 1244 |
+
"theoretical_loss": 3.869972125299568,
|
| 1245 |
+
"tokens_seen": 557056000
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.2,
|
| 1249 |
+
"learning_rate": 0.00040398619254775867,
|
| 1250 |
+
"loss": 2.8204,
|
| 1251 |
+
"theoretical_loss": 3.867574665363595,
|
| 1252 |
+
"tokens_seen": 560332800
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.2,
|
| 1256 |
+
"learning_rate": 0.0004033951201059202,
|
| 1257 |
+
"loss": 2.8428,
|
| 1258 |
+
"theoretical_loss": 3.865195084494398,
|
| 1259 |
+
"tokens_seen": 563609600
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.2,
|
| 1263 |
+
"learning_rate": 0.00040280404766408176,
|
| 1264 |
+
"loss": 2.8384,
|
| 1265 |
+
"theoretical_loss": 3.8628331465674224,
|
| 1266 |
+
"tokens_seen": 566886400
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.2,
|
| 1270 |
+
"learning_rate": 0.0004022129752222433,
|
| 1271 |
+
"loss": 2.8934,
|
| 1272 |
+
"theoretical_loss": 3.860488619918462,
|
| 1273 |
+
"tokens_seen": 570163200
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.2,
|
| 1277 |
+
"learning_rate": 0.0004016219027804048,
|
| 1278 |
+
"loss": 2.8648,
|
| 1279 |
+
"theoretical_loss": 3.858161277234349,
|
| 1280 |
+
"tokens_seen": 573440000
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.21,
|
| 1284 |
+
"learning_rate": 0.0004010308303385663,
|
| 1285 |
+
"loss": 2.8661,
|
| 1286 |
+
"theoretical_loss": 3.855850895446925,
|
| 1287 |
+
"tokens_seen": 576716800
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.21,
|
| 1291 |
+
"learning_rate": 0.00040043975789672785,
|
| 1292 |
+
"loss": 2.8561,
|
| 1293 |
+
"theoretical_loss": 3.8535572556301823,
|
| 1294 |
+
"tokens_seen": 579993600
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.21,
|
| 1298 |
+
"learning_rate": 0.0003998486854548893,
|
| 1299 |
+
"loss": 2.8319,
|
| 1300 |
+
"theoretical_loss": 3.851280142900463,
|
| 1301 |
+
"tokens_seen": 583270400
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.21,
|
| 1305 |
+
"learning_rate": 0.0003992576130130509,
|
| 1306 |
+
"loss": 2.8733,
|
| 1307 |
+
"theoretical_loss": 3.8490193463196127,
|
| 1308 |
+
"tokens_seen": 586547200
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.21,
|
| 1312 |
+
"learning_rate": 0.0003986665405712124,
|
| 1313 |
+
"loss": 2.8419,
|
| 1314 |
+
"theoretical_loss": 3.8467746588009692,
|
| 1315 |
+
"tokens_seen": 589824000
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.21,
|
| 1319 |
+
"learning_rate": 0.00039807546812937393,
|
| 1320 |
+
"loss": 2.8261,
|
| 1321 |
+
"theoretical_loss": 3.8445458770181116,
|
| 1322 |
+
"tokens_seen": 593100800
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.21,
|
| 1326 |
+
"learning_rate": 0.00039748439568753545,
|
| 1327 |
+
"loss": 2.809,
|
| 1328 |
+
"theoretical_loss": 3.842332801316254,
|
| 1329 |
+
"tokens_seen": 596377600
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.21,
|
| 1333 |
+
"learning_rate": 0.00039689332324569697,
|
| 1334 |
+
"loss": 2.7745,
|
| 1335 |
+
"theoretical_loss": 3.840135235626204,
|
| 1336 |
+
"tokens_seen": 599654400
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.22,
|
| 1340 |
+
"learning_rate": 0.0003963022508038585,
|
| 1341 |
+
"loss": 2.7996,
|
| 1342 |
+
"theoretical_loss": 3.8379529873807945,
|
| 1343 |
+
"tokens_seen": 602931200
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.22,
|
| 1347 |
+
"learning_rate": 0.00039571117836202,
|
| 1348 |
+
"loss": 2.7862,
|
| 1349 |
+
"theoretical_loss": 3.835785867433705,
|
| 1350 |
+
"tokens_seen": 606208000
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.22,
|
| 1354 |
+
"learning_rate": 0.0003951201059201816,
|
| 1355 |
+
"loss": 2.7724,
|
| 1356 |
+
"theoretical_loss": 3.8336336899805916,
|
| 1357 |
+
"tokens_seen": 609484800
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.22,
|
| 1361 |
+
"learning_rate": 0.0003945290334783431,
|
| 1362 |
+
"loss": 2.8298,
|
| 1363 |
+
"theoretical_loss": 3.8314962724824495,
|
| 1364 |
+
"tokens_seen": 612761600
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.22,
|
| 1368 |
+
"learning_rate": 0.00039393796103650463,
|
| 1369 |
+
"loss": 2.8027,
|
| 1370 |
+
"theoretical_loss": 3.8293734355911297,
|
| 1371 |
+
"tokens_seen": 616038400
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.22,
|
| 1375 |
+
"learning_rate": 0.00039334688859466615,
|
| 1376 |
+
"loss": 2.7742,
|
| 1377 |
+
"theoretical_loss": 3.8272650030769433,
|
| 1378 |
+
"tokens_seen": 619315200
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.22,
|
| 1382 |
+
"learning_rate": 0.00039275581615282767,
|
| 1383 |
+
"loss": 2.8195,
|
| 1384 |
+
"theoretical_loss": 3.8251708017582793,
|
| 1385 |
+
"tokens_seen": 622592000
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.22,
|
| 1389 |
+
"learning_rate": 0.0003921647437109892,
|
| 1390 |
+
"loss": 2.7575,
|
| 1391 |
+
"theoretical_loss": 3.8230906614331737,
|
| 1392 |
+
"tokens_seen": 625868800
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.22,
|
| 1396 |
+
"learning_rate": 0.00039157367126915077,
|
| 1397 |
+
"loss": 2.777,
|
| 1398 |
+
"theoretical_loss": 3.821024414812761,
|
| 1399 |
+
"tokens_seen": 629145600
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.23,
|
| 1403 |
+
"learning_rate": 0.0003909825988273123,
|
| 1404 |
+
"loss": 2.7716,
|
| 1405 |
+
"theoretical_loss": 3.818971897456552,
|
| 1406 |
+
"tokens_seen": 632422400
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.23,
|
| 1410 |
+
"learning_rate": 0.0003903915263854738,
|
| 1411 |
+
"loss": 2.8385,
|
| 1412 |
+
"theoretical_loss": 3.8169329477094784,
|
| 1413 |
+
"tokens_seen": 635699200
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.23,
|
| 1417 |
+
"learning_rate": 0.00038980045394363533,
|
| 1418 |
+
"loss": 2.8269,
|
| 1419 |
+
"theoretical_loss": 3.814907406640639,
|
| 1420 |
+
"tokens_seen": 638976000
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.23,
|
| 1424 |
+
"learning_rate": 0.00038920938150179685,
|
| 1425 |
+
"loss": 2.8603,
|
| 1426 |
+
"theoretical_loss": 3.8128951179837056,
|
| 1427 |
+
"tokens_seen": 642252800
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.23,
|
| 1431 |
+
"learning_rate": 0.00038861830905995837,
|
| 1432 |
+
"loss": 2.8311,
|
| 1433 |
+
"theoretical_loss": 3.8108959280789243,
|
| 1434 |
+
"tokens_seen": 645529600
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.23,
|
| 1438 |
+
"learning_rate": 0.00038802723661811994,
|
| 1439 |
+
"loss": 2.8352,
|
| 1440 |
+
"theoretical_loss": 3.8089096858166718,
|
| 1441 |
+
"tokens_seen": 648806400
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.23,
|
| 1445 |
+
"learning_rate": 0.00038743616417628147,
|
| 1446 |
+
"loss": 2.8036,
|
| 1447 |
+
"theoretical_loss": 3.8069362425825037,
|
| 1448 |
+
"tokens_seen": 652083200
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"debugging/Self-BLEU-5": 0.5268657803535504,
|
| 1452 |
+
"debugging/distinct-1-grams": 0.7733134705474689,
|
| 1453 |
+
"debugging/distinct-2-grams": 0.9620239068787645,
|
| 1454 |
+
"debugging/entropy-1-grams": 5.925348960854147,
|
| 1455 |
+
"debugging/entropy-2-grams": 6.698235169198012,
|
| 1456 |
+
"debugging/length": 567.4545454545455,
|
| 1457 |
+
"debugging/num_segments": 11,
|
| 1458 |
+
"epoch": 0.23,
|
| 1459 |
+
"objective/train/docs_used": 369218,
|
| 1460 |
+
"objective/train/instantaneous_batch_size": 32,
|
| 1461 |
+
"objective/train/instantaneous_microbatch_size": 32768,
|
| 1462 |
+
"objective/train/original_loss": 2.6253697872161865,
|
| 1463 |
+
"objective/train/theoretical_loss": 3.8049754522036645,
|
| 1464 |
+
"objective/train/tokens_used": 675820000,
|
| 1465 |
+
"theoretical_loss": 3.8049754522036645,
|
| 1466 |
+
"tokens_seen": 655360000
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.23,
|
| 1470 |
+
"learning_rate": 0.000386845091734443,
|
| 1471 |
+
"loss": 2.7868,
|
| 1472 |
+
"theoretical_loss": 3.8049754522036645,
|
| 1473 |
+
"tokens_seen": 655360000
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.24,
|
| 1477 |
+
"learning_rate": 0.0003862540192926045,
|
| 1478 |
+
"loss": 2.7929,
|
| 1479 |
+
"theoretical_loss": 3.8030271708970003,
|
| 1480 |
+
"tokens_seen": 658636800
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.24,
|
| 1484 |
+
"learning_rate": 0.00038566294685076603,
|
| 1485 |
+
"loss": 2.7686,
|
| 1486 |
+
"theoretical_loss": 3.801091257218237,
|
| 1487 |
+
"tokens_seen": 661913600
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.24,
|
| 1491 |
+
"learning_rate": 0.00038507187440892755,
|
| 1492 |
+
"loss": 2.779,
|
| 1493 |
+
"theoretical_loss": 3.79916757201258,
|
| 1494 |
+
"tokens_seen": 665190400
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.24,
|
| 1498 |
+
"learning_rate": 0.0003844808019670891,
|
| 1499 |
+
"loss": 2.788,
|
| 1500 |
+
"theoretical_loss": 3.7972559783665965,
|
| 1501 |
+
"tokens_seen": 668467200
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.24,
|
| 1505 |
+
"learning_rate": 0.00038388972952525064,
|
| 1506 |
+
"loss": 2.7746,
|
| 1507 |
+
"theoretical_loss": 3.7953563415613325,
|
| 1508 |
+
"tokens_seen": 671744000
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.24,
|
| 1512 |
+
"learning_rate": 0.00038329865708341216,
|
| 1513 |
+
"loss": 2.8202,
|
| 1514 |
+
"theoretical_loss": 3.7934685290266454,
|
| 1515 |
+
"tokens_seen": 675020800
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.24,
|
| 1519 |
+
"learning_rate": 0.00038271940609041044,
|
| 1520 |
+
"loss": 2.8374,
|
| 1521 |
+
"theoretical_loss": 3.7915924102966914,
|
| 1522 |
+
"tokens_seen": 678297600
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.24,
|
| 1526 |
+
"learning_rate": 0.00038212833364857196,
|
| 1527 |
+
"loss": 2.8547,
|
| 1528 |
+
"theoretical_loss": 3.789727856966552,
|
| 1529 |
+
"tokens_seen": 681574400
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.24,
|
| 1533 |
+
"learning_rate": 0.0003815372612067335,
|
| 1534 |
+
"loss": 2.7956,
|
| 1535 |
+
"theoretical_loss": 3.787874742649958,
|
| 1536 |
+
"tokens_seen": 684851200
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.25,
|
| 1540 |
+
"learning_rate": 0.000380946188764895,
|
| 1541 |
+
"loss": 2.8261,
|
| 1542 |
+
"theoretical_loss": 3.786032942938073,
|
| 1543 |
+
"tokens_seen": 688128000
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.25,
|
| 1547 |
+
"learning_rate": 0.0003803551163230566,
|
| 1548 |
+
"loss": 2.8168,
|
| 1549 |
+
"theoretical_loss": 3.784202335359316,
|
| 1550 |
+
"tokens_seen": 691404800
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.25,
|
| 1554 |
+
"learning_rate": 0.0003797640438812181,
|
| 1555 |
+
"loss": 2.8115,
|
| 1556 |
+
"theoretical_loss": 3.7823827993401844,
|
| 1557 |
+
"tokens_seen": 694681600
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.25,
|
| 1561 |
+
"learning_rate": 0.0003791729714393796,
|
| 1562 |
+
"loss": 2.7943,
|
| 1563 |
+
"theoretical_loss": 3.7805742161670466,
|
| 1564 |
+
"tokens_seen": 697958400
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.25,
|
| 1568 |
+
"learning_rate": 0.00037858189899754114,
|
| 1569 |
+
"loss": 2.7825,
|
| 1570 |
+
"theoretical_loss": 3.7787764689488847,
|
| 1571 |
+
"tokens_seen": 701235200
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.25,
|
| 1575 |
+
"learning_rate": 0.00037799082655570266,
|
| 1576 |
+
"loss": 2.7542,
|
| 1577 |
+
"theoretical_loss": 3.77698944258095,
|
| 1578 |
+
"tokens_seen": 704512000
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.25,
|
| 1582 |
+
"learning_rate": 0.0003773997541138642,
|
| 1583 |
+
"loss": 2.7907,
|
| 1584 |
+
"theoretical_loss": 3.7752130237093064,
|
| 1585 |
+
"tokens_seen": 707788800
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.25,
|
| 1589 |
+
"learning_rate": 0.00037680868167202575,
|
| 1590 |
+
"loss": 2.791,
|
| 1591 |
+
"theoretical_loss": 3.773447100696245,
|
| 1592 |
+
"tokens_seen": 711065600
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.26,
|
| 1596 |
+
"learning_rate": 0.0003762176092301873,
|
| 1597 |
+
"loss": 2.8071,
|
| 1598 |
+
"theoretical_loss": 3.771691563586529,
|
| 1599 |
+
"tokens_seen": 714342400
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.26,
|
| 1603 |
+
"learning_rate": 0.0003756265367883488,
|
| 1604 |
+
"loss": 2.7722,
|
| 1605 |
+
"theoretical_loss": 3.7699463040744616,
|
| 1606 |
+
"tokens_seen": 717619200
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.26,
|
| 1610 |
+
"learning_rate": 0.0003750354643465103,
|
| 1611 |
+
"loss": 2.7415,
|
| 1612 |
+
"theoretical_loss": 3.768211215471741,
|
| 1613 |
+
"tokens_seen": 720896000
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.26,
|
| 1617 |
+
"learning_rate": 0.00037444439190467184,
|
| 1618 |
+
"loss": 2.7554,
|
| 1619 |
+
"theoretical_loss": 3.766486192676084,
|
| 1620 |
+
"tokens_seen": 724172800
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.26,
|
| 1624 |
+
"learning_rate": 0.00037385331946283336,
|
| 1625 |
+
"loss": 2.704,
|
| 1626 |
+
"theoretical_loss": 3.764771132140602,
|
| 1627 |
+
"tokens_seen": 727449600
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.26,
|
| 1631 |
+
"learning_rate": 0.00037326224702099493,
|
| 1632 |
+
"loss": 2.7486,
|
| 1633 |
+
"theoretical_loss": 3.763065931843898,
|
| 1634 |
+
"tokens_seen": 730726400
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.26,
|
| 1638 |
+
"learning_rate": 0.00037267117457915645,
|
| 1639 |
+
"loss": 2.7402,
|
| 1640 |
+
"theoretical_loss": 3.7613704912608723,
|
| 1641 |
+
"tokens_seen": 734003200
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.26,
|
| 1645 |
+
"learning_rate": 0.0003720919235861547,
|
| 1646 |
+
"loss": 2.7675,
|
| 1647 |
+
"theoretical_loss": 3.759684711334213,
|
| 1648 |
+
"tokens_seen": 737280000
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.26,
|
| 1652 |
+
"learning_rate": 0.00037150085114431625,
|
| 1653 |
+
"loss": 2.7613,
|
| 1654 |
+
"theoretical_loss": 3.7580084944465555,
|
| 1655 |
+
"tokens_seen": 740556800
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.27,
|
| 1659 |
+
"learning_rate": 0.00037090977870247777,
|
| 1660 |
+
"loss": 2.7919,
|
| 1661 |
+
"theoretical_loss": 3.7563417443932905,
|
| 1662 |
+
"tokens_seen": 743833600
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.27,
|
| 1666 |
+
"learning_rate": 0.0003703187062606393,
|
| 1667 |
+
"loss": 2.7827,
|
| 1668 |
+
"theoretical_loss": 3.754684366355999,
|
| 1669 |
+
"tokens_seen": 747110400
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.27,
|
| 1673 |
+
"learning_rate": 0.0003697276338188008,
|
| 1674 |
+
"loss": 2.7466,
|
| 1675 |
+
"theoretical_loss": 3.753036266876505,
|
| 1676 |
+
"tokens_seen": 750387200
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.27,
|
| 1680 |
+
"learning_rate": 0.0003691365613769624,
|
| 1681 |
+
"loss": 2.7505,
|
| 1682 |
+
"theoretical_loss": 3.751397353831524,
|
| 1683 |
+
"tokens_seen": 753664000
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.27,
|
| 1687 |
+
"learning_rate": 0.0003685454889351239,
|
| 1688 |
+
"loss": 2.7087,
|
| 1689 |
+
"theoretical_loss": 3.749767536407891,
|
| 1690 |
+
"tokens_seen": 756940800
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.27,
|
| 1694 |
+
"learning_rate": 0.0003679544164932854,
|
| 1695 |
+
"loss": 2.756,
|
| 1696 |
+
"theoretical_loss": 3.7481467250783504,
|
| 1697 |
+
"tokens_seen": 760217600
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.27,
|
| 1701 |
+
"learning_rate": 0.00036736334405144695,
|
| 1702 |
+
"loss": 2.7494,
|
| 1703 |
+
"theoretical_loss": 3.746534831577904,
|
| 1704 |
+
"tokens_seen": 763494400
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.27,
|
| 1708 |
+
"learning_rate": 0.00036677227160960847,
|
| 1709 |
+
"loss": 2.6995,
|
| 1710 |
+
"theoretical_loss": 3.744931768880681,
|
| 1711 |
+
"tokens_seen": 766771200
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.28,
|
| 1715 |
+
"learning_rate": 0.00036618119916777,
|
| 1716 |
+
"loss": 2.7499,
|
| 1717 |
+
"theoretical_loss": 3.743337451177343,
|
| 1718 |
+
"tokens_seen": 770048000
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.28,
|
| 1722 |
+
"learning_rate": 0.00036559012672593156,
|
| 1723 |
+
"loss": 2.7127,
|
| 1724 |
+
"theoretical_loss": 3.74175179385298,
|
| 1725 |
+
"tokens_seen": 773324800
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.28,
|
| 1729 |
+
"learning_rate": 0.0003649990542840931,
|
| 1730 |
+
"loss": 2.7784,
|
| 1731 |
+
"theoretical_loss": 3.740174713465512,
|
| 1732 |
+
"tokens_seen": 776601600
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 0.28,
|
| 1736 |
+
"learning_rate": 0.0003644079818422546,
|
| 1737 |
+
"loss": 2.7351,
|
| 1738 |
+
"theoretical_loss": 3.7386061277245655,
|
| 1739 |
+
"tokens_seen": 779878400
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 0.28,
|
| 1743 |
+
"learning_rate": 0.0003638169094004161,
|
| 1744 |
+
"loss": 2.7641,
|
| 1745 |
+
"theoretical_loss": 3.7370459554708146,
|
| 1746 |
+
"tokens_seen": 783155200
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.28,
|
| 1750 |
+
"learning_rate": 0.00036322583695857765,
|
| 1751 |
+
"loss": 2.7932,
|
| 1752 |
+
"theoretical_loss": 3.735494116655784,
|
| 1753 |
+
"tokens_seen": 786432000
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.28,
|
| 1757 |
+
"learning_rate": 0.00036263476451673917,
|
| 1758 |
+
"loss": 2.77,
|
| 1759 |
+
"theoretical_loss": 3.733950532322087,
|
| 1760 |
+
"tokens_seen": 789708800
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 0.28,
|
| 1764 |
+
"learning_rate": 0.00036204369207490074,
|
| 1765 |
+
"loss": 2.8059,
|
| 1766 |
+
"theoretical_loss": 3.7324151245841044,
|
| 1767 |
+
"tokens_seen": 792985600
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.28,
|
| 1771 |
+
"learning_rate": 0.00036145261963306226,
|
| 1772 |
+
"loss": 2.7821,
|
| 1773 |
+
"theoretical_loss": 3.730887816609077,
|
| 1774 |
+
"tokens_seen": 796262400
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 0.29,
|
| 1778 |
+
"learning_rate": 0.0003608615471912238,
|
| 1779 |
+
"loss": 2.7676,
|
| 1780 |
+
"theoretical_loss": 3.729368532598609,
|
| 1781 |
+
"tokens_seen": 799539200
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 0.29,
|
| 1785 |
+
"learning_rate": 0.0003602704747493853,
|
| 1786 |
+
"loss": 2.7677,
|
| 1787 |
+
"theoretical_loss": 3.7278571977705734,
|
| 1788 |
+
"tokens_seen": 802816000
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 0.29,
|
| 1792 |
+
"learning_rate": 0.0003596794023075468,
|
| 1793 |
+
"loss": 2.8028,
|
| 1794 |
+
"theoretical_loss": 3.7263537383414023,
|
| 1795 |
+
"tokens_seen": 806092800
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.29,
|
| 1799 |
+
"learning_rate": 0.00035908832986570834,
|
| 1800 |
+
"loss": 2.7817,
|
| 1801 |
+
"theoretical_loss": 3.7248580815087626,
|
| 1802 |
+
"tokens_seen": 809369600
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.29,
|
| 1806 |
+
"learning_rate": 0.0003584972574238699,
|
| 1807 |
+
"loss": 2.8043,
|
| 1808 |
+
"theoretical_loss": 3.7233701554345924,
|
| 1809 |
+
"tokens_seen": 812646400
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.29,
|
| 1813 |
+
"learning_rate": 0.00035790618498203144,
|
| 1814 |
+
"loss": 2.7556,
|
| 1815 |
+
"theoretical_loss": 3.721889889228506,
|
| 1816 |
+
"tokens_seen": 815923200
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.29,
|
| 1820 |
+
"objective/train/docs_used": 458204,
|
| 1821 |
+
"objective/train/instantaneous_batch_size": 32,
|
| 1822 |
+
"objective/train/instantaneous_microbatch_size": 32768,
|
| 1823 |
+
"objective/train/original_loss": 3.028093099594116,
|
| 1824 |
+
"objective/train/theoretical_loss": 3.720417212931543,
|
| 1825 |
+
"objective/train/tokens_used": 839660000,
|
| 1826 |
+
"theoretical_loss": 3.720417212931543,
|
| 1827 |
+
"tokens_seen": 819200000
|
| 1828 |
+
},
|
| 1829 |
+
{
|
| 1830 |
+
"epoch": 0.29,
|
| 1831 |
+
"learning_rate": 0.00035731511254019296,
|
| 1832 |
+
"loss": 2.7947,
|
| 1833 |
+
"theoretical_loss": 3.720417212931543,
|
| 1834 |
+
"tokens_seen": 819200000
|
| 1835 |
+
},
|
| 1836 |
+
{
|
| 1837 |
+
"epoch": 0.29,
|
| 1838 |
+
"learning_rate": 0.0003567240400983545,
|
| 1839 |
+
"loss": 2.8117,
|
| 1840 |
+
"theoretical_loss": 3.7189520575002666,
|
| 1841 |
+
"tokens_seen": 822476800
|
| 1842 |
+
},
|
| 1843 |
+
{
|
| 1844 |
+
"epoch": 0.29,
|
| 1845 |
+
"learning_rate": 0.000356132967656516,
|
| 1846 |
+
"loss": 2.757,
|
| 1847 |
+
"theoretical_loss": 3.717494354791188,
|
| 1848 |
+
"tokens_seen": 825753600
|
| 1849 |
+
},
|
| 1850 |
+
{
|
| 1851 |
+
"epoch": 0.3,
|
| 1852 |
+
"learning_rate": 0.0003555418952146775,
|
| 1853 |
+
"loss": 2.7848,
|
| 1854 |
+
"theoretical_loss": 3.716044037545523,
|
| 1855 |
+
"tokens_seen": 829030400
|
| 1856 |
+
},
|
| 1857 |
+
{
|
| 1858 |
+
"epoch": 0.3,
|
| 1859 |
+
"learning_rate": 0.00035495082277283904,
|
| 1860 |
+
"loss": 2.7501,
|
| 1861 |
+
"theoretical_loss": 3.714601039374263,
|
| 1862 |
+
"tokens_seen": 832307200
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"epoch": 0.3,
|
| 1866 |
+
"learning_rate": 0.0003543597503310006,
|
| 1867 |
+
"loss": 2.7341,
|
| 1868 |
+
"theoretical_loss": 3.7131652947435536,
|
| 1869 |
+
"tokens_seen": 835584000
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 0.3,
|
| 1873 |
+
"learning_rate": 0.00035376867788916214,
|
| 1874 |
+
"loss": 2.7225,
|
| 1875 |
+
"theoretical_loss": 3.7117367389603793,
|
| 1876 |
+
"tokens_seen": 838860800
|
| 1877 |
+
},
|
| 1878 |
+
{
|
| 1879 |
+
"epoch": 0.3,
|
| 1880 |
+
"learning_rate": 0.00035317760544732366,
|
| 1881 |
+
"loss": 2.691,
|
| 1882 |
+
"theoretical_loss": 3.710315308158541,
|
| 1883 |
+
"tokens_seen": 842137600
|
| 1884 |
+
},
|
| 1885 |
+
{
|
| 1886 |
+
"epoch": 0.3,
|
| 1887 |
+
"learning_rate": 0.0003525865330054852,
|
| 1888 |
+
"loss": 2.7351,
|
| 1889 |
+
"theoretical_loss": 3.7089009392849173,
|
| 1890 |
+
"tokens_seen": 845414400
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"epoch": 0.3,
|
| 1894 |
+
"learning_rate": 0.00035199546056364665,
|
| 1895 |
+
"loss": 2.6898,
|
| 1896 |
+
"theoretical_loss": 3.7074935700860143,
|
| 1897 |
+
"tokens_seen": 848691200
|
| 1898 |
+
},
|
| 1899 |
+
{
|
| 1900 |
+
"epoch": 0.3,
|
| 1901 |
+
"learning_rate": 0.00035140438812180817,
|
| 1902 |
+
"loss": 2.7464,
|
| 1903 |
+
"theoretical_loss": 3.706093139094781,
|
| 1904 |
+
"tokens_seen": 851968000
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 0.31,
|
| 1908 |
+
"learning_rate": 0.00035081331567996974,
|
| 1909 |
+
"loss": 2.7205,
|
| 1910 |
+
"theoretical_loss": 3.7046995856176954,
|
| 1911 |
+
"tokens_seen": 855244800
|
| 1912 |
+
},
|
| 1913 |
+
{
|
| 1914 |
+
"epoch": 0.31,
|
| 1915 |
+
"learning_rate": 0.00035022224323813127,
|
| 1916 |
+
"loss": 2.7251,
|
| 1917 |
+
"theoretical_loss": 3.703312849722111,
|
| 1918 |
+
"tokens_seen": 858521600
|
| 1919 |
+
},
|
| 1920 |
+
{
|
| 1921 |
+
"epoch": 0.31,
|
| 1922 |
+
"learning_rate": 0.0003496311707962928,
|
| 1923 |
+
"loss": 2.7297,
|
| 1924 |
+
"theoretical_loss": 3.701932872223858,
|
| 1925 |
+
"tokens_seen": 861798400
|
| 1926 |
+
},
|
| 1927 |
+
{
|
| 1928 |
+
"epoch": 0.31,
|
| 1929 |
+
"learning_rate": 0.0003490400983544543,
|
| 1930 |
+
"loss": 2.6675,
|
| 1931 |
+
"theoretical_loss": 3.7005595946750924,
|
| 1932 |
+
"tokens_seen": 865075200
|
| 1933 |
+
},
|
| 1934 |
+
{
|
| 1935 |
+
"epoch": 0.31,
|
| 1936 |
+
"learning_rate": 0.00034844902591261583,
|
| 1937 |
+
"loss": 2.6965,
|
| 1938 |
+
"theoretical_loss": 3.699192959352386,
|
| 1939 |
+
"tokens_seen": 868352000
|
| 1940 |
+
},
|
| 1941 |
+
{
|
| 1942 |
+
"epoch": 0.31,
|
| 1943 |
+
"learning_rate": 0.00034785795347077735,
|
| 1944 |
+
"loss": 2.7056,
|
| 1945 |
+
"theoretical_loss": 3.6978329092450557,
|
| 1946 |
+
"tokens_seen": 871628800
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 0.31,
|
| 1950 |
+
"learning_rate": 0.0003472668810289389,
|
| 1951 |
+
"loss": 2.7372,
|
| 1952 |
+
"theoretical_loss": 3.6964793880437226,
|
| 1953 |
+
"tokens_seen": 874905600
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 0.31,
|
| 1957 |
+
"learning_rate": 0.00034667580858710044,
|
| 1958 |
+
"loss": 2.7373,
|
| 1959 |
+
"theoretical_loss": 3.6951323401290974,
|
| 1960 |
+
"tokens_seen": 878182400
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"epoch": 0.31,
|
| 1964 |
+
"learning_rate": 0.00034608473614526196,
|
| 1965 |
+
"loss": 2.7016,
|
| 1966 |
+
"theoretical_loss": 3.6937917105609834,
|
| 1967 |
+
"tokens_seen": 881459200
|
| 1968 |
+
},
|
| 1969 |
+
{
|
| 1970 |
+
"epoch": 0.32,
|
| 1971 |
+
"learning_rate": 0.0003454936637034235,
|
| 1972 |
+
"loss": 2.7444,
|
| 1973 |
+
"theoretical_loss": 3.692457445067501,
|
| 1974 |
+
"tokens_seen": 884736000
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 0.32,
|
| 1978 |
+
"learning_rate": 0.000344902591261585,
|
| 1979 |
+
"loss": 2.7565,
|
| 1980 |
+
"theoretical_loss": 3.6911294900345166,
|
| 1981 |
+
"tokens_seen": 888012800
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 0.32,
|
| 1985 |
+
"learning_rate": 0.00034431151881974653,
|
| 1986 |
+
"loss": 2.6976,
|
| 1987 |
+
"theoretical_loss": 3.6898077924952775,
|
| 1988 |
+
"tokens_seen": 891289600
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 0.32,
|
| 1992 |
+
"learning_rate": 0.00034372044637790805,
|
| 1993 |
+
"loss": 2.6916,
|
| 1994 |
+
"theoretical_loss": 3.6884923001202505,
|
| 1995 |
+
"tokens_seen": 894566400
|
| 1996 |
+
},
|
| 1997 |
+
{
|
| 1998 |
+
"epoch": 0.32,
|
| 1999 |
+
"learning_rate": 0.0003431293739360696,
|
| 2000 |
+
"loss": 2.7103,
|
| 2001 |
+
"theoretical_loss": 3.6871829612071583,
|
| 2002 |
+
"tokens_seen": 897843200
|
| 2003 |
+
},
|
| 2004 |
+
{
|
| 2005 |
+
"epoch": 0.32,
|
| 2006 |
+
"learning_rate": 0.00034253830149423114,
|
| 2007 |
+
"loss": 2.7112,
|
| 2008 |
+
"theoretical_loss": 3.6858797246711976,
|
| 2009 |
+
"tokens_seen": 901120000
|
| 2010 |
+
},
|
| 2011 |
+
{
|
| 2012 |
+
"epoch": 0.32,
|
| 2013 |
+
"learning_rate": 0.00034194722905239266,
|
| 2014 |
+
"loss": 2.6877,
|
| 2015 |
+
"theoretical_loss": 3.684582540035456,
|
| 2016 |
+
"tokens_seen": 904396800
|
| 2017 |
+
},
|
| 2018 |
+
{
|
| 2019 |
+
"epoch": 0.32,
|
| 2020 |
+
"learning_rate": 0.0003413561566105542,
|
| 2021 |
+
"loss": 2.6852,
|
| 2022 |
+
"theoretical_loss": 3.683291357421508,
|
| 2023 |
+
"tokens_seen": 907673600
|
| 2024 |
+
},
|
| 2025 |
+
{
|
| 2026 |
+
"epoch": 0.33,
|
| 2027 |
+
"learning_rate": 0.0003407650841687157,
|
| 2028 |
+
"loss": 2.7345,
|
| 2029 |
+
"theoretical_loss": 3.682006127540184,
|
| 2030 |
+
"tokens_seen": 910950400
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 0.33,
|
| 2034 |
+
"learning_rate": 0.0003401740117268772,
|
| 2035 |
+
"loss": 2.7163,
|
| 2036 |
+
"theoretical_loss": 3.680726801682522,
|
| 2037 |
+
"tokens_seen": 914227200
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 0.33,
|
| 2041 |
+
"learning_rate": 0.0003395829392850388,
|
| 2042 |
+
"loss": 2.7208,
|
| 2043 |
+
"theoretical_loss": 3.679453331710889,
|
| 2044 |
+
"tokens_seen": 917504000
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 0.33,
|
| 2048 |
+
"learning_rate": 0.0003389918668432003,
|
| 2049 |
+
"loss": 2.7313,
|
| 2050 |
+
"theoretical_loss": 3.6781856700502646,
|
| 2051 |
+
"tokens_seen": 920780800
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 0.33,
|
| 2055 |
+
"learning_rate": 0.00033840079440136184,
|
| 2056 |
+
"loss": 2.722,
|
| 2057 |
+
"theoretical_loss": 3.6769237696796933,
|
| 2058 |
+
"tokens_seen": 924057600
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 0.33,
|
| 2062 |
+
"learning_rate": 0.00033780972195952336,
|
| 2063 |
+
"loss": 2.7169,
|
| 2064 |
+
"theoretical_loss": 3.6756675841238913,
|
| 2065 |
+
"tokens_seen": 927334400
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"epoch": 0.33,
|
| 2069 |
+
"learning_rate": 0.0003372186495176849,
|
| 2070 |
+
"loss": 2.7377,
|
| 2071 |
+
"theoretical_loss": 3.6744170674450176,
|
| 2072 |
+
"tokens_seen": 930611200
|
| 2073 |
+
},
|
| 2074 |
+
{
|
| 2075 |
+
"epoch": 0.33,
|
| 2076 |
+
"learning_rate": 0.0003366275770758464,
|
| 2077 |
+
"loss": 2.7284,
|
| 2078 |
+
"theoretical_loss": 3.673172174234587,
|
| 2079 |
+
"tokens_seen": 933888000
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 0.33,
|
| 2083 |
+
"learning_rate": 0.000336036504634008,
|
| 2084 |
+
"loss": 2.7507,
|
| 2085 |
+
"theoretical_loss": 3.6719328596055423,
|
| 2086 |
+
"tokens_seen": 937164800
|
| 2087 |
+
},
|
| 2088 |
+
{
|
| 2089 |
+
"epoch": 0.34,
|
| 2090 |
+
"learning_rate": 0.0003354454321921695,
|
| 2091 |
+
"loss": 2.6989,
|
| 2092 |
+
"theoretical_loss": 3.670699079184467,
|
| 2093 |
+
"tokens_seen": 940441600
|
| 2094 |
+
},
|
| 2095 |
+
{
|
| 2096 |
+
"epoch": 0.34,
|
| 2097 |
+
"learning_rate": 0.000334854359750331,
|
| 2098 |
+
"loss": 2.7391,
|
| 2099 |
+
"theoretical_loss": 3.669470789103942,
|
| 2100 |
+
"tokens_seen": 943718400
|
| 2101 |
+
},
|
| 2102 |
+
{
|
| 2103 |
+
"epoch": 0.34,
|
| 2104 |
+
"learning_rate": 0.00033426328730849254,
|
| 2105 |
+
"loss": 2.7049,
|
| 2106 |
+
"theoretical_loss": 3.6682479459950446,
|
| 2107 |
+
"tokens_seen": 946995200
|
| 2108 |
+
},
|
| 2109 |
+
{
|
| 2110 |
+
"epoch": 0.34,
|
| 2111 |
+
"learning_rate": 0.00033367221486665406,
|
| 2112 |
+
"loss": 2.6821,
|
| 2113 |
+
"theoretical_loss": 3.6670305069799785,
|
| 2114 |
+
"tokens_seen": 950272000
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 0.34,
|
| 2118 |
+
"learning_rate": 0.0003330811424248156,
|
| 2119 |
+
"loss": 2.6779,
|
| 2120 |
+
"theoretical_loss": 3.6658184296648457,
|
| 2121 |
+
"tokens_seen": 953548800
|
| 2122 |
+
},
|
| 2123 |
+
{
|
| 2124 |
+
"epoch": 0.34,
|
| 2125 |
+
"learning_rate": 0.0003324900699829771,
|
| 2126 |
+
"loss": 2.6528,
|
| 2127 |
+
"theoretical_loss": 3.6646116721325415,
|
| 2128 |
+
"tokens_seen": 956825600
|
| 2129 |
+
},
|
| 2130 |
+
{
|
| 2131 |
+
"epoch": 0.34,
|
| 2132 |
+
"learning_rate": 0.0003318989975411387,
|
| 2133 |
+
"loss": 2.6351,
|
| 2134 |
+
"theoretical_loss": 3.6634101929357836,
|
| 2135 |
+
"tokens_seen": 960102400
|
| 2136 |
+
},
|
| 2137 |
+
{
|
| 2138 |
+
"epoch": 0.34,
|
| 2139 |
+
"learning_rate": 0.0003313079250993002,
|
| 2140 |
+
"loss": 2.618,
|
| 2141 |
+
"theoretical_loss": 3.6622139510902625,
|
| 2142 |
+
"tokens_seen": 963379200
|
| 2143 |
+
},
|
| 2144 |
+
{
|
| 2145 |
+
"epoch": 0.35,
|
| 2146 |
+
"learning_rate": 0.0003307168526574617,
|
| 2147 |
+
"loss": 2.6546,
|
| 2148 |
+
"theoretical_loss": 3.6610229060679167,
|
| 2149 |
+
"tokens_seen": 966656000
|
| 2150 |
+
},
|
| 2151 |
+
{
|
| 2152 |
+
"epoch": 0.35,
|
| 2153 |
+
"learning_rate": 0.00033012578021562324,
|
| 2154 |
+
"loss": 2.6745,
|
| 2155 |
+
"theoretical_loss": 3.659837017790328,
|
| 2156 |
+
"tokens_seen": 969932800
|
| 2157 |
+
},
|
| 2158 |
+
{
|
| 2159 |
+
"epoch": 0.35,
|
| 2160 |
+
"learning_rate": 0.00032953470777378476,
|
| 2161 |
+
"loss": 2.7084,
|
| 2162 |
+
"theoretical_loss": 3.658656246622233,
|
| 2163 |
+
"tokens_seen": 973209600
|
| 2164 |
+
},
|
| 2165 |
+
{
|
| 2166 |
+
"epoch": 0.35,
|
| 2167 |
+
"learning_rate": 0.0003289436353319463,
|
| 2168 |
+
"loss": 2.7065,
|
| 2169 |
+
"theoretical_loss": 3.6574805533651515,
|
| 2170 |
+
"tokens_seen": 976486400
|
| 2171 |
+
},
|
| 2172 |
+
{
|
| 2173 |
+
"epoch": 0.35,
|
| 2174 |
+
"learning_rate": 0.00032835256289010786,
|
| 2175 |
+
"loss": 2.6295,
|
| 2176 |
+
"theoretical_loss": 3.6563098992511267,
|
| 2177 |
+
"tokens_seen": 979763200
|
| 2178 |
+
},
|
| 2179 |
+
{
|
| 2180 |
+
"debugging/Self-BLEU-5": 0.36988534170376464,
|
| 2181 |
+
"debugging/distinct-1-grams": 0.7978170447064457,
|
| 2182 |
+
"debugging/distinct-2-grams": 0.9699762510402439,
|
| 2183 |
+
"debugging/entropy-1-grams": 5.166066569251399,
|
| 2184 |
+
"debugging/entropy-2-grams": 5.640626124943832,
|
| 2185 |
+
"debugging/length": 444.0,
|
| 2186 |
+
"debugging/num_segments": 5,
|
| 2187 |
+
"epoch": 0.35,
|
| 2188 |
+
"objective/train/docs_used": 548757,
|
| 2189 |
+
"objective/train/instantaneous_batch_size": 32,
|
| 2190 |
+
"objective/train/instantaneous_microbatch_size": 32768,
|
| 2191 |
+
"objective/train/original_loss": 2.5549697875976562,
|
| 2192 |
+
"objective/train/theoretical_loss": 3.655144245936574,
|
| 2193 |
+
"objective/train/tokens_used": 1003500000,
|
| 2194 |
+
"theoretical_loss": 3.655144245936574,
|
| 2195 |
+
"tokens_seen": 983040000
|
| 2196 |
+
},
|
| 2197 |
+
{
|
| 2198 |
+
"epoch": 0.35,
|
| 2199 |
+
"learning_rate": 0.0003277614904482694,
|
| 2200 |
+
"loss": 2.6943,
|
| 2201 |
+
"theoretical_loss": 3.655144245936574,
|
| 2202 |
+
"tokens_seen": 983040000
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 0.35,
|
| 2206 |
+
"learning_rate": 0.0003271704180064309,
|
| 2207 |
+
"loss": 2.6566,
|
| 2208 |
+
"theoretical_loss": 3.653983555496242,
|
| 2209 |
+
"tokens_seen": 986316800
|
| 2210 |
+
},
|
| 2211 |
+
{
|
| 2212 |
+
"epoch": 0.35,
|
| 2213 |
+
"learning_rate": 0.0003265793455645924,
|
| 2214 |
+
"loss": 2.6849,
|
| 2215 |
+
"theoretical_loss": 3.6528277904172755,
|
| 2216 |
+
"tokens_seen": 989593600
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 0.35,
|
| 2220 |
+
"learning_rate": 0.00032598827312275394,
|
| 2221 |
+
"loss": 2.7013,
|
| 2222 |
+
"theoretical_loss": 3.6516769135933815,
|
| 2223 |
+
"tokens_seen": 992870400
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 0.36,
|
| 2227 |
+
"learning_rate": 0.00032539720068091546,
|
| 2228 |
+
"loss": 2.7911,
|
| 2229 |
+
"theoretical_loss": 3.650530888319103,
|
| 2230 |
+
"tokens_seen": 996147200
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"epoch": 0.36,
|
| 2234 |
+
"learning_rate": 0.00032480612823907704,
|
| 2235 |
+
"loss": 2.7824,
|
| 2236 |
+
"theoretical_loss": 3.649389678284182,
|
| 2237 |
+
"tokens_seen": 999424000
|
| 2238 |
+
},
|
| 2239 |
+
{
|
| 2240 |
+
"epoch": 0.36,
|
| 2241 |
+
"learning_rate": 0.00032421505579723856,
|
| 2242 |
+
"loss": 2.8279,
|
| 2243 |
+
"theoretical_loss": 3.6482532475680287,
|
| 2244 |
+
"tokens_seen": 1002700800
|
| 2245 |
+
},
|
| 2246 |
+
{
|
| 2247 |
+
"epoch": 0.36,
|
| 2248 |
+
"learning_rate": 0.0003236239833554001,
|
| 2249 |
+
"loss": 2.7843,
|
| 2250 |
+
"theoretical_loss": 3.6471215606342833,
|
| 2251 |
+
"tokens_seen": 1005977600
|
| 2252 |
+
},
|
| 2253 |
+
{
|
| 2254 |
+
"epoch": 0.36,
|
| 2255 |
+
"learning_rate": 0.00032303291091356155,
|
| 2256 |
+
"loss": 2.783,
|
| 2257 |
+
"theoretical_loss": 3.645994582325468,
|
| 2258 |
+
"tokens_seen": 1009254400
|
| 2259 |
+
},
|
| 2260 |
+
{
|
| 2261 |
+
"epoch": 0.36,
|
| 2262 |
+
"learning_rate": 0.0003224654813693966,
|
| 2263 |
+
"loss": 2.8,
|
| 2264 |
+
"theoretical_loss": 3.6448722778577327,
|
| 2265 |
+
"tokens_seen": 1012531200
|
| 2266 |
+
},
|
| 2267 |
+
{
|
| 2268 |
+
"epoch": 0.36,
|
| 2269 |
+
"learning_rate": 0.00032187440892755814,
|
| 2270 |
+
"loss": 2.8244,
|
| 2271 |
+
"theoretical_loss": 3.6437546128156946,
|
| 2272 |
+
"tokens_seen": 1015808000
|
| 2273 |
+
},
|
| 2274 |
+
{
|
| 2275 |
+
"epoch": 0.36,
|
| 2276 |
+
"learning_rate": 0.0003212833364857197,
|
| 2277 |
+
"loss": 2.7973,
|
| 2278 |
+
"theoretical_loss": 3.6426415531473566,
|
| 2279 |
+
"tokens_seen": 1019084800
|
| 2280 |
+
},
|
| 2281 |
+
{
|
| 2282 |
+
"epoch": 0.37,
|
| 2283 |
+
"learning_rate": 0.00032069226404388124,
|
| 2284 |
+
"loss": 2.7788,
|
| 2285 |
+
"theoretical_loss": 3.641533065159118,
|
| 2286 |
+
"tokens_seen": 1022361600
|
| 2287 |
+
},
|
| 2288 |
+
{
|
| 2289 |
+
"epoch": 0.37,
|
| 2290 |
+
"learning_rate": 0.00032010119160204276,
|
| 2291 |
+
"loss": 2.7468,
|
| 2292 |
+
"theoretical_loss": 3.6404291155108712,
|
| 2293 |
+
"tokens_seen": 1025638400
|
| 2294 |
+
},
|
| 2295 |
+
{
|
| 2296 |
+
"epoch": 0.37,
|
| 2297 |
+
"learning_rate": 0.0003195101191602043,
|
| 2298 |
+
"loss": 2.7502,
|
| 2299 |
+
"theoretical_loss": 3.639329671211173,
|
| 2300 |
+
"tokens_seen": 1028915200
|
| 2301 |
+
},
|
| 2302 |
+
{
|
| 2303 |
+
"epoch": 0.37,
|
| 2304 |
+
"learning_rate": 0.0003189190467183658,
|
| 2305 |
+
"loss": 2.7506,
|
| 2306 |
+
"theoretical_loss": 3.6382346996125055,
|
| 2307 |
+
"tokens_seen": 1032192000
|
| 2308 |
+
},
|
| 2309 |
+
{
|
| 2310 |
+
"epoch": 0.37,
|
| 2311 |
+
"learning_rate": 0.0003183279742765273,
|
| 2312 |
+
"loss": 2.7245,
|
| 2313 |
+
"theoretical_loss": 3.6371441684066097,
|
| 2314 |
+
"tokens_seen": 1035468800
|
| 2315 |
+
},
|
| 2316 |
+
{
|
| 2317 |
+
"epoch": 0.37,
|
| 2318 |
+
"learning_rate": 0.00031773690183468884,
|
| 2319 |
+
"loss": 2.7504,
|
| 2320 |
+
"theoretical_loss": 3.6360580456199036,
|
| 2321 |
+
"tokens_seen": 1038745600
|
| 2322 |
+
},
|
| 2323 |
+
{
|
| 2324 |
+
"epoch": 0.37,
|
| 2325 |
+
"learning_rate": 0.0003171458293928504,
|
| 2326 |
+
"loss": 2.7781,
|
| 2327 |
+
"theoretical_loss": 3.6349762996089683,
|
| 2328 |
+
"tokens_seen": 1042022400
|
| 2329 |
+
},
|
| 2330 |
+
{
|
| 2331 |
+
"epoch": 0.37,
|
| 2332 |
+
"learning_rate": 0.00031655475695101194,
|
| 2333 |
+
"loss": 2.7056,
|
| 2334 |
+
"theoretical_loss": 3.633898899056115,
|
| 2335 |
+
"tokens_seen": 1045299200
|
| 2336 |
+
},
|
| 2337 |
+
{
|
| 2338 |
+
"epoch": 0.37,
|
| 2339 |
+
"learning_rate": 0.00031596368450917346,
|
| 2340 |
+
"loss": 2.7879,
|
| 2341 |
+
"theoretical_loss": 3.6328258129650246,
|
| 2342 |
+
"tokens_seen": 1048576000
|
| 2343 |
+
},
|
| 2344 |
+
{
|
| 2345 |
+
"epoch": 0.38,
|
| 2346 |
+
"learning_rate": 0.000315372612067335,
|
| 2347 |
+
"loss": 2.7406,
|
| 2348 |
+
"theoretical_loss": 3.6317570106564565,
|
| 2349 |
+
"tokens_seen": 1051852800
|
| 2350 |
+
},
|
| 2351 |
+
{
|
| 2352 |
+
"epoch": 0.38,
|
| 2353 |
+
"learning_rate": 0.0003147815396254965,
|
| 2354 |
+
"loss": 2.7554,
|
| 2355 |
+
"theoretical_loss": 3.6306924617640295,
|
| 2356 |
+
"tokens_seen": 1055129600
|
| 2357 |
+
},
|
| 2358 |
+
{
|
| 2359 |
+
"epoch": 0.38,
|
| 2360 |
+
"learning_rate": 0.000314190467183658,
|
| 2361 |
+
"loss": 2.7376,
|
| 2362 |
+
"theoretical_loss": 3.6296321362300716,
|
| 2363 |
+
"tokens_seen": 1058406400
|
| 2364 |
+
},
|
| 2365 |
+
{
|
| 2366 |
+
"epoch": 0.38,
|
| 2367 |
+
"learning_rate": 0.0003135993947418196,
|
| 2368 |
+
"loss": 2.7554,
|
| 2369 |
+
"theoretical_loss": 3.6285760043015385,
|
| 2370 |
+
"tokens_seen": 1061683200
|
| 2371 |
+
},
|
| 2372 |
+
{
|
| 2373 |
+
"epoch": 0.38,
|
| 2374 |
+
"learning_rate": 0.0003130083222999811,
|
| 2375 |
+
"loss": 2.7547,
|
| 2376 |
+
"theoretical_loss": 3.6275240365259958,
|
| 2377 |
+
"tokens_seen": 1064960000
|
| 2378 |
+
},
|
| 2379 |
+
{
|
| 2380 |
+
"epoch": 0.38,
|
| 2381 |
+
"learning_rate": 0.00031241724985814264,
|
| 2382 |
+
"loss": 2.6945,
|
| 2383 |
+
"theoretical_loss": 3.6264762037476683,
|
| 2384 |
+
"tokens_seen": 1068236800
|
| 2385 |
+
},
|
| 2386 |
+
{
|
| 2387 |
+
"epoch": 0.38,
|
| 2388 |
+
"learning_rate": 0.00031182617741630416,
|
| 2389 |
+
"loss": 2.6957,
|
| 2390 |
+
"theoretical_loss": 3.625432477103554,
|
| 2391 |
+
"tokens_seen": 1071513600
|
| 2392 |
+
},
|
| 2393 |
+
{
|
| 2394 |
+
"epoch": 0.38,
|
| 2395 |
+
"learning_rate": 0.0003112351049744657,
|
| 2396 |
+
"loss": 2.7089,
|
| 2397 |
+
"theoretical_loss": 3.6243928280195976,
|
| 2398 |
+
"tokens_seen": 1074790400
|
| 2399 |
+
},
|
| 2400 |
+
{
|
| 2401 |
+
"epoch": 0.39,
|
| 2402 |
+
"learning_rate": 0.0003106440325326272,
|
| 2403 |
+
"loss": 2.6979,
|
| 2404 |
+
"theoretical_loss": 3.62335722820693,
|
| 2405 |
+
"tokens_seen": 1078067200
|
| 2406 |
+
},
|
| 2407 |
+
{
|
| 2408 |
+
"epoch": 0.39,
|
| 2409 |
+
"learning_rate": 0.0003100529600907888,
|
| 2410 |
+
"loss": 2.7171,
|
| 2411 |
+
"theoretical_loss": 3.6223256496581637,
|
| 2412 |
+
"tokens_seen": 1081344000
|
| 2413 |
+
},
|
| 2414 |
+
{
|
| 2415 |
+
"epoch": 0.39,
|
| 2416 |
+
"learning_rate": 0.0003094618876489503,
|
| 2417 |
+
"loss": 2.708,
|
| 2418 |
+
"theoretical_loss": 3.6212980646437485,
|
| 2419 |
+
"tokens_seen": 1084620800
|
| 2420 |
+
},
|
| 2421 |
+
{
|
| 2422 |
+
"epoch": 0.39,
|
| 2423 |
+
"learning_rate": 0.0003088708152071118,
|
| 2424 |
+
"loss": 2.6816,
|
| 2425 |
+
"theoretical_loss": 3.6202744457083877,
|
| 2426 |
+
"tokens_seen": 1087897600
|
| 2427 |
+
},
|
| 2428 |
+
{
|
| 2429 |
+
"epoch": 0.39,
|
| 2430 |
+
"learning_rate": 0.00030827974276527334,
|
| 2431 |
+
"loss": 2.7291,
|
| 2432 |
+
"theoretical_loss": 3.6192547656675083,
|
| 2433 |
+
"tokens_seen": 1091174400
|
| 2434 |
+
},
|
| 2435 |
+
{
|
| 2436 |
+
"epoch": 0.39,
|
| 2437 |
+
"learning_rate": 0.00030768867032343486,
|
| 2438 |
+
"loss": 2.7181,
|
| 2439 |
+
"theoretical_loss": 3.618238997603788,
|
| 2440 |
+
"tokens_seen": 1094451200
|
| 2441 |
+
},
|
| 2442 |
+
{
|
| 2443 |
+
"epoch": 0.39,
|
| 2444 |
+
"learning_rate": 0.0003070975978815964,
|
| 2445 |
+
"loss": 2.6929,
|
| 2446 |
+
"theoretical_loss": 3.617227114863738,
|
| 2447 |
+
"tokens_seen": 1097728000
|
| 2448 |
+
},
|
| 2449 |
+
{
|
| 2450 |
+
"epoch": 0.39,
|
| 2451 |
+
"learning_rate": 0.0003065065254397579,
|
| 2452 |
+
"loss": 2.6868,
|
| 2453 |
+
"theoretical_loss": 3.6162190910543366,
|
| 2454 |
+
"tokens_seen": 1101004800
|
| 2455 |
+
},
|
| 2456 |
+
{
|
| 2457 |
+
"epoch": 0.39,
|
| 2458 |
+
"learning_rate": 0.0003059154529979195,
|
| 2459 |
+
"loss": 2.6816,
|
| 2460 |
+
"theoretical_loss": 3.615214900039721,
|
| 2461 |
+
"tokens_seen": 1104281600
|
| 2462 |
+
},
|
| 2463 |
+
{
|
| 2464 |
+
"epoch": 0.4,
|
| 2465 |
+
"learning_rate": 0.000305324380556081,
|
| 2466 |
+
"loss": 2.6571,
|
| 2467 |
+
"theoretical_loss": 3.614214515937924,
|
| 2468 |
+
"tokens_seen": 1107558400
|
| 2469 |
+
},
|
| 2470 |
+
{
|
| 2471 |
+
"epoch": 0.4,
|
| 2472 |
+
"learning_rate": 0.00030473330811424246,
|
| 2473 |
+
"loss": 2.6745,
|
| 2474 |
+
"theoretical_loss": 3.613217913117667,
|
| 2475 |
+
"tokens_seen": 1110835200
|
| 2476 |
+
},
|
| 2477 |
+
{
|
| 2478 |
+
"epoch": 0.4,
|
| 2479 |
+
"learning_rate": 0.000304142235672404,
|
| 2480 |
+
"loss": 2.684,
|
| 2481 |
+
"theoretical_loss": 3.612225066195201,
|
| 2482 |
+
"tokens_seen": 1114112000
|
| 2483 |
+
},
|
| 2484 |
+
{
|
| 2485 |
+
"epoch": 0.4,
|
| 2486 |
+
"learning_rate": 0.0003035511632305655,
|
| 2487 |
+
"loss": 2.7163,
|
| 2488 |
+
"theoretical_loss": 3.611235950031194,
|
| 2489 |
+
"tokens_seen": 1117388800
|
| 2490 |
+
},
|
| 2491 |
+
{
|
| 2492 |
+
"epoch": 0.4,
|
| 2493 |
+
"learning_rate": 0.000302960090788727,
|
| 2494 |
+
"loss": 2.6896,
|
| 2495 |
+
"theoretical_loss": 3.6102505397276743,
|
| 2496 |
+
"tokens_seen": 1120665600
|
| 2497 |
+
},
|
| 2498 |
+
{
|
| 2499 |
+
"epoch": 0.4,
|
| 2500 |
+
"learning_rate": 0.0003023690183468886,
|
| 2501 |
+
"loss": 2.6928,
|
| 2502 |
+
"theoretical_loss": 3.60926881062501,
|
| 2503 |
+
"tokens_seen": 1123942400
|
| 2504 |
+
},
|
| 2505 |
+
{
|
| 2506 |
+
"epoch": 0.4,
|
| 2507 |
+
"learning_rate": 0.0003017779459050501,
|
| 2508 |
+
"loss": 2.6515,
|
| 2509 |
+
"theoretical_loss": 3.608290738298942,
|
| 2510 |
+
"tokens_seen": 1127219200
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"epoch": 0.4,
|
| 2514 |
+
"learning_rate": 0.00030118687346321164,
|
| 2515 |
+
"loss": 2.679,
|
| 2516 |
+
"theoretical_loss": 3.6073162985576643,
|
| 2517 |
+
"tokens_seen": 1130496000
|
| 2518 |
+
},
|
| 2519 |
+
{
|
| 2520 |
+
"epoch": 0.4,
|
| 2521 |
+
"learning_rate": 0.00030059580102137316,
|
| 2522 |
+
"loss": 2.6589,
|
| 2523 |
+
"theoretical_loss": 3.606345467438941,
|
| 2524 |
+
"tokens_seen": 1133772800
|
| 2525 |
+
},
|
| 2526 |
+
{
|
| 2527 |
+
"epoch": 0.41,
|
| 2528 |
+
"learning_rate": 0.0003000047285795347,
|
| 2529 |
+
"loss": 2.6888,
|
| 2530 |
+
"theoretical_loss": 3.6053782212072747,
|
| 2531 |
+
"tokens_seen": 1137049600
|
| 2532 |
+
},
|
| 2533 |
+
{
|
| 2534 |
+
"epoch": 0.41,
|
| 2535 |
+
"learning_rate": 0.0002994136561376962,
|
| 2536 |
+
"loss": 2.6886,
|
| 2537 |
+
"theoretical_loss": 3.604414536351113,
|
| 2538 |
+
"tokens_seen": 1140326400
|
| 2539 |
+
},
|
| 2540 |
+
{
|
| 2541 |
+
"epoch": 0.41,
|
| 2542 |
+
"learning_rate": 0.0002988225836958578,
|
| 2543 |
+
"loss": 2.667,
|
| 2544 |
+
"theoretical_loss": 3.6034543895801017,
|
| 2545 |
+
"tokens_seen": 1143603200
|
| 2546 |
+
},
|
| 2547 |
+
{
|
| 2548 |
+
"epoch": 0.41,
|
| 2549 |
+
"objective/train/docs_used": 634175,
|
| 2550 |
+
"objective/train/instantaneous_batch_size": 32,
|
| 2551 |
+
"objective/train/instantaneous_microbatch_size": 32768,
|
| 2552 |
+
"objective/train/original_loss": 2.4722554683685303,
|
| 2553 |
+
"objective/train/theoretical_loss": 3.6024977578223742,
|
| 2554 |
+
"objective/train/tokens_used": 1167340000,
|
| 2555 |
+
"theoretical_loss": 3.6024977578223742,
|
| 2556 |
+
"tokens_seen": 1146880000
|
| 2557 |
+
},
|
| 2558 |
+
{
|
| 2559 |
+
"epoch": 0.41,
|
| 2560 |
+
"learning_rate": 0.0002982315112540193,
|
| 2561 |
+
"loss": 2.6443,
|
| 2562 |
+
"theoretical_loss": 3.6024977578223742,
|
| 2563 |
+
"tokens_seen": 1146880000
|
| 2564 |
+
},
|
| 2565 |
+
{
|
| 2566 |
+
"epoch": 0.41,
|
| 2567 |
+
"learning_rate": 0.0002976404388121808,
|
| 2568 |
+
"loss": 2.7336,
|
| 2569 |
+
"theoretical_loss": 3.6015446182218875,
|
| 2570 |
+
"tokens_seen": 1150156800
|
| 2571 |
+
},
|
| 2572 |
+
{
|
| 2573 |
+
"epoch": 0.41,
|
| 2574 |
+
"learning_rate": 0.00029704936637034234,
|
| 2575 |
+
"loss": 2.75,
|
| 2576 |
+
"theoretical_loss": 3.600594948135793,
|
| 2577 |
+
"tokens_seen": 1153433600
|
| 2578 |
+
},
|
| 2579 |
+
{
|
| 2580 |
+
"epoch": 0.41,
|
| 2581 |
+
"learning_rate": 0.00029645829392850386,
|
| 2582 |
+
"loss": 2.7006,
|
| 2583 |
+
"theoretical_loss": 3.59964872513185,
|
| 2584 |
+
"tokens_seen": 1156710400
|
| 2585 |
+
},
|
| 2586 |
+
{
|
| 2587 |
+
"epoch": 0.41,
|
| 2588 |
+
"learning_rate": 0.0002958672214866654,
|
| 2589 |
+
"loss": 2.7268,
|
| 2590 |
+
"theoretical_loss": 3.5987059269858763,
|
| 2591 |
+
"tokens_seen": 1159987200
|
| 2592 |
+
},
|
| 2593 |
+
{
|
| 2594 |
+
"epoch": 0.42,
|
| 2595 |
+
"learning_rate": 0.0002952761490448269,
|
| 2596 |
+
"loss": 2.7089,
|
| 2597 |
+
"theoretical_loss": 3.5977665316792375,
|
| 2598 |
+
"tokens_seen": 1163264000
|
| 2599 |
+
},
|
| 2600 |
+
{
|
| 2601 |
+
"epoch": 0.42,
|
| 2602 |
+
"learning_rate": 0.0002946850766029885,
|
| 2603 |
+
"loss": 2.7154,
|
| 2604 |
+
"theoretical_loss": 3.5968305173963744,
|
| 2605 |
+
"tokens_seen": 1166540800
|
| 2606 |
+
},
|
| 2607 |
+
{
|
| 2608 |
+
"epoch": 0.42,
|
| 2609 |
+
"learning_rate": 0.00029409400416115,
|
| 2610 |
+
"loss": 2.6744,
|
| 2611 |
+
"theoretical_loss": 3.5958978625223628,
|
| 2612 |
+
"tokens_seen": 1169817600
|
| 2613 |
+
},
|
| 2614 |
+
{
|
| 2615 |
+
"epoch": 0.42,
|
| 2616 |
+
"learning_rate": 0.0002935029317193115,
|
| 2617 |
+
"loss": 2.6651,
|
| 2618 |
+
"theoretical_loss": 3.5949685456405165,
|
| 2619 |
+
"tokens_seen": 1173094400
|
| 2620 |
+
},
|
| 2621 |
+
{
|
| 2622 |
+
"epoch": 0.42,
|
| 2623 |
+
"learning_rate": 0.00029291185927747304,
|
| 2624 |
+
"loss": 2.6933,
|
| 2625 |
+
"theoretical_loss": 3.5940425455300176,
|
| 2626 |
+
"tokens_seen": 1176371200
|
| 2627 |
+
},
|
| 2628 |
+
{
|
| 2629 |
+
"epoch": 0.42,
|
| 2630 |
+
"learning_rate": 0.00029232078683563456,
|
| 2631 |
+
"loss": 2.6929,
|
| 2632 |
+
"theoretical_loss": 3.593119841163589,
|
| 2633 |
+
"tokens_seen": 1179648000
|
| 2634 |
+
},
|
| 2635 |
+
{
|
| 2636 |
+
"epoch": 0.42,
|
| 2637 |
+
"learning_rate": 0.0002917297143937961,
|
| 2638 |
+
"loss": 2.6819,
|
| 2639 |
+
"theoretical_loss": 3.5922004117051944,
|
| 2640 |
+
"tokens_seen": 1182924800
|
| 2641 |
+
},
|
| 2642 |
+
{
|
| 2643 |
+
"epoch": 0.42,
|
| 2644 |
+
"learning_rate": 0.00029113864195195766,
|
| 2645 |
+
"loss": 2.6941,
|
| 2646 |
+
"theoretical_loss": 3.5912842365077777,
|
| 2647 |
+
"tokens_seen": 1186201600
|
| 2648 |
+
},
|
| 2649 |
+
{
|
| 2650 |
+
"epoch": 0.42,
|
| 2651 |
+
"learning_rate": 0.0002905475695101192,
|
| 2652 |
+
"loss": 2.7035,
|
| 2653 |
+
"theoretical_loss": 3.5903712951110305,
|
| 2654 |
+
"tokens_seen": 1189478400
|
| 2655 |
+
},
|
| 2656 |
+
{
|
| 2657 |
+
"epoch": 0.43,
|
| 2658 |
+
"learning_rate": 0.0002899564970682807,
|
| 2659 |
+
"loss": 2.6773,
|
| 2660 |
+
"theoretical_loss": 3.5894615672391947,
|
| 2661 |
+
"tokens_seen": 1192755200
|
| 2662 |
+
},
|
| 2663 |
+
{
|
| 2664 |
+
"epoch": 0.43,
|
| 2665 |
+
"learning_rate": 0.0002893654246264422,
|
| 2666 |
+
"loss": 2.7129,
|
| 2667 |
+
"theoretical_loss": 3.5885550327988973,
|
| 2668 |
+
"tokens_seen": 1196032000
|
| 2669 |
+
},
|
| 2670 |
+
{
|
| 2671 |
+
"epoch": 0.43,
|
| 2672 |
+
"learning_rate": 0.00028877435218460374,
|
| 2673 |
+
"loss": 2.6773,
|
| 2674 |
+
"theoretical_loss": 3.587651671877014,
|
| 2675 |
+
"tokens_seen": 1199308800
|
| 2676 |
+
},
|
| 2677 |
+
{
|
| 2678 |
+
"epoch": 0.43,
|
| 2679 |
+
"learning_rate": 0.00028818327974276526,
|
| 2680 |
+
"loss": 2.702,
|
| 2681 |
+
"theoretical_loss": 3.5867514647385663,
|
| 2682 |
+
"tokens_seen": 1202585600
|
| 2683 |
+
},
|
| 2684 |
+
{
|
| 2685 |
+
"epoch": 0.43,
|
| 2686 |
+
"learning_rate": 0.00028759220730092684,
|
| 2687 |
+
"loss": 2.7033,
|
| 2688 |
+
"theoretical_loss": 3.585854391824647,
|
| 2689 |
+
"tokens_seen": 1205862400
|
| 2690 |
+
},
|
| 2691 |
+
{
|
| 2692 |
+
"epoch": 0.43,
|
| 2693 |
+
"learning_rate": 0.00028700113485908836,
|
| 2694 |
+
"loss": 2.6571,
|
| 2695 |
+
"theoretical_loss": 3.584960433750375,
|
| 2696 |
+
"tokens_seen": 1209139200
|
| 2697 |
+
},
|
| 2698 |
+
{
|
| 2699 |
+
"epoch": 0.43,
|
| 2700 |
+
"learning_rate": 0.0002864100624172499,
|
| 2701 |
+
"loss": 2.6949,
|
| 2702 |
+
"theoretical_loss": 3.5840695713028827,
|
| 2703 |
+
"tokens_seen": 1212416000
|
| 2704 |
+
},
|
| 2705 |
+
{
|
| 2706 |
+
"epoch": 0.43,
|
| 2707 |
+
"learning_rate": 0.0002858189899754114,
|
| 2708 |
+
"loss": 2.6806,
|
| 2709 |
+
"theoretical_loss": 3.5831817854393266,
|
| 2710 |
+
"tokens_seen": 1215692800
|
| 2711 |
+
},
|
| 2712 |
+
{
|
| 2713 |
+
"epoch": 0.44,
|
| 2714 |
+
"learning_rate": 0.0002852279175335729,
|
| 2715 |
+
"loss": 2.7055,
|
| 2716 |
+
"theoretical_loss": 3.582297057284933,
|
| 2717 |
+
"tokens_seen": 1218969600
|
| 2718 |
+
},
|
| 2719 |
+
{
|
| 2720 |
+
"epoch": 0.44,
|
| 2721 |
+
"learning_rate": 0.00028463684509173444,
|
| 2722 |
+
"loss": 2.7213,
|
| 2723 |
+
"theoretical_loss": 3.5814153681310623,
|
| 2724 |
+
"tokens_seen": 1222246400
|
| 2725 |
+
},
|
| 2726 |
+
{
|
| 2727 |
+
"epoch": 0.44,
|
| 2728 |
+
"learning_rate": 0.00028404577264989596,
|
| 2729 |
+
"loss": 2.711,
|
| 2730 |
+
"theoretical_loss": 3.5805366994333125,
|
| 2731 |
+
"tokens_seen": 1225523200
|
| 2732 |
+
},
|
| 2733 |
+
{
|
| 2734 |
+
"epoch": 0.44,
|
| 2735 |
+
"learning_rate": 0.00028345470020805754,
|
| 2736 |
+
"loss": 2.684,
|
| 2737 |
+
"theoretical_loss": 3.5796610328096365,
|
| 2738 |
+
"tokens_seen": 1228800000
|
| 2739 |
+
},
|
| 2740 |
+
{
|
| 2741 |
+
"epoch": 0.44,
|
| 2742 |
+
"learning_rate": 0.00028286362776621906,
|
| 2743 |
+
"loss": 2.7022,
|
| 2744 |
+
"theoretical_loss": 3.578788350038497,
|
| 2745 |
+
"tokens_seen": 1232076800
|
| 2746 |
+
},
|
| 2747 |
+
{
|
| 2748 |
+
"epoch": 0.44,
|
| 2749 |
+
"learning_rate": 0.0002822725553243806,
|
| 2750 |
+
"loss": 2.6849,
|
| 2751 |
+
"theoretical_loss": 3.5779186330570405,
|
| 2752 |
+
"tokens_seen": 1235353600
|
| 2753 |
+
},
|
| 2754 |
+
{
|
| 2755 |
+
"epoch": 0.44,
|
| 2756 |
+
"learning_rate": 0.0002816814828825421,
|
| 2757 |
+
"loss": 2.6673,
|
| 2758 |
+
"theoretical_loss": 3.5770518639592983,
|
| 2759 |
+
"tokens_seen": 1238630400
|
| 2760 |
+
},
|
| 2761 |
+
{
|
| 2762 |
+
"epoch": 0.44,
|
| 2763 |
+
"learning_rate": 0.0002810904104407036,
|
| 2764 |
+
"loss": 2.7361,
|
| 2765 |
+
"theoretical_loss": 3.5761880249944147,
|
| 2766 |
+
"tokens_seen": 1241907200
|
| 2767 |
+
},
|
| 2768 |
+
{
|
| 2769 |
+
"epoch": 0.44,
|
| 2770 |
+
"learning_rate": 0.00028049933799886514,
|
| 2771 |
+
"loss": 2.7269,
|
| 2772 |
+
"theoretical_loss": 3.5753270985648973,
|
| 2773 |
+
"tokens_seen": 1245184000
|
| 2774 |
+
},
|
| 2775 |
+
{
|
| 2776 |
+
"epoch": 0.45,
|
| 2777 |
+
"learning_rate": 0.0002799082655570267,
|
| 2778 |
+
"loss": 2.7538,
|
| 2779 |
+
"theoretical_loss": 3.574469067224892,
|
| 2780 |
+
"tokens_seen": 1248460800
|
| 2781 |
+
},
|
| 2782 |
+
{
|
| 2783 |
+
"epoch": 0.45,
|
| 2784 |
+
"learning_rate": 0.00027931719311518824,
|
| 2785 |
+
"loss": 2.7449,
|
| 2786 |
+
"theoretical_loss": 3.573613913678484,
|
| 2787 |
+
"tokens_seen": 1251737600
|
| 2788 |
+
},
|
| 2789 |
+
{
|
| 2790 |
+
"epoch": 0.45,
|
| 2791 |
+
"learning_rate": 0.00027872612067334976,
|
| 2792 |
+
"loss": 2.7426,
|
| 2793 |
+
"theoretical_loss": 3.57276162077802,
|
| 2794 |
+
"tokens_seen": 1255014400
|
| 2795 |
+
},
|
| 2796 |
+
{
|
| 2797 |
+
"epoch": 0.45,
|
| 2798 |
+
"learning_rate": 0.0002781350482315113,
|
| 2799 |
+
"loss": 2.7223,
|
| 2800 |
+
"theoretical_loss": 3.5719121715224524,
|
| 2801 |
+
"tokens_seen": 1258291200
|
| 2802 |
+
},
|
| 2803 |
+
{
|
| 2804 |
+
"epoch": 0.45,
|
| 2805 |
+
"learning_rate": 0.0002775439757896728,
|
| 2806 |
+
"loss": 2.6702,
|
| 2807 |
+
"theoretical_loss": 3.571065549055712,
|
| 2808 |
+
"tokens_seen": 1261568000
|
| 2809 |
+
},
|
| 2810 |
+
{
|
| 2811 |
+
"epoch": 0.45,
|
| 2812 |
+
"learning_rate": 0.0002769529033478343,
|
| 2813 |
+
"loss": 2.7204,
|
| 2814 |
+
"theoretical_loss": 3.5702217366650935,
|
| 2815 |
+
"tokens_seen": 1264844800
|
| 2816 |
+
},
|
| 2817 |
+
{
|
| 2818 |
+
"epoch": 0.45,
|
| 2819 |
+
"learning_rate": 0.0002763618309059959,
|
| 2820 |
+
"loss": 2.6506,
|
| 2821 |
+
"theoretical_loss": 3.5693807177796737,
|
| 2822 |
+
"tokens_seen": 1268121600
|
| 2823 |
+
},
|
| 2824 |
+
{
|
| 2825 |
+
"epoch": 0.45,
|
| 2826 |
+
"learning_rate": 0.00027577075846415736,
|
| 2827 |
+
"loss": 2.641,
|
| 2828 |
+
"theoretical_loss": 3.5685424759687434,
|
| 2829 |
+
"tokens_seen": 1271398400
|
| 2830 |
+
},
|
| 2831 |
+
{
|
| 2832 |
+
"epoch": 0.46,
|
| 2833 |
+
"learning_rate": 0.0002751796860223189,
|
| 2834 |
+
"loss": 2.6681,
|
| 2835 |
+
"theoretical_loss": 3.567706994940263,
|
| 2836 |
+
"tokens_seen": 1274675200
|
| 2837 |
+
},
|
| 2838 |
+
{
|
| 2839 |
+
"epoch": 0.46,
|
| 2840 |
+
"learning_rate": 0.0002745886135804804,
|
| 2841 |
+
"loss": 2.6911,
|
| 2842 |
+
"theoretical_loss": 3.5668742585393405,
|
| 2843 |
+
"tokens_seen": 1277952000
|
| 2844 |
+
},
|
| 2845 |
+
{
|
| 2846 |
+
"epoch": 0.46,
|
| 2847 |
+
"learning_rate": 0.00027400936258747873,
|
| 2848 |
+
"loss": 2.6482,
|
| 2849 |
+
"theoretical_loss": 3.566044250746728,
|
| 2850 |
+
"tokens_seen": 1281228800
|
| 2851 |
+
},
|
| 2852 |
+
{
|
| 2853 |
+
"epoch": 0.46,
|
| 2854 |
+
"learning_rate": 0.00027341829014564025,
|
| 2855 |
+
"loss": 2.6761,
|
| 2856 |
+
"theoretical_loss": 3.5652169556773403,
|
| 2857 |
+
"tokens_seen": 1284505600
|
| 2858 |
+
},
|
| 2859 |
+
{
|
| 2860 |
+
"epoch": 0.46,
|
| 2861 |
+
"learning_rate": 0.0002728272177038018,
|
| 2862 |
+
"loss": 2.6272,
|
| 2863 |
+
"theoretical_loss": 3.5643923575787912,
|
| 2864 |
+
"tokens_seen": 1287782400
|
| 2865 |
+
},
|
| 2866 |
+
{
|
| 2867 |
+
"epoch": 0.46,
|
| 2868 |
+
"learning_rate": 0.00027223614526196335,
|
| 2869 |
+
"loss": 2.6449,
|
| 2870 |
+
"theoretical_loss": 3.563570440829951,
|
| 2871 |
+
"tokens_seen": 1291059200
|
| 2872 |
+
},
|
| 2873 |
+
{
|
| 2874 |
+
"epoch": 0.46,
|
| 2875 |
+
"learning_rate": 0.00027164507282012487,
|
| 2876 |
+
"loss": 2.6287,
|
| 2877 |
+
"theoretical_loss": 3.562751189939524,
|
| 2878 |
+
"tokens_seen": 1294336000
|
| 2879 |
+
},
|
| 2880 |
+
{
|
| 2881 |
+
"epoch": 0.46,
|
| 2882 |
+
"learning_rate": 0.0002710540003782864,
|
| 2883 |
+
"loss": 2.6691,
|
| 2884 |
+
"theoretical_loss": 3.5619345895446424,
|
| 2885 |
+
"tokens_seen": 1297612800
|
| 2886 |
+
},
|
| 2887 |
+
{
|
| 2888 |
+
"epoch": 0.46,
|
| 2889 |
+
"learning_rate": 0.0002704629279364479,
|
| 2890 |
+
"loss": 2.6499,
|
| 2891 |
+
"theoretical_loss": 3.561120624409482,
|
| 2892 |
+
"tokens_seen": 1300889600
|
| 2893 |
+
},
|
| 2894 |
+
{
|
| 2895 |
+
"epoch": 0.47,
|
| 2896 |
+
"learning_rate": 0.00026987185549460943,
|
| 2897 |
+
"loss": 2.6475,
|
| 2898 |
+
"theoretical_loss": 3.560309279423894,
|
| 2899 |
+
"tokens_seen": 1304166400
|
| 2900 |
+
},
|
| 2901 |
+
{
|
| 2902 |
+
"epoch": 0.47,
|
| 2903 |
+
"learning_rate": 0.00026928078305277095,
|
| 2904 |
+
"loss": 2.6303,
|
| 2905 |
+
"theoretical_loss": 3.5595005396020554,
|
| 2906 |
+
"tokens_seen": 1307443200
|
| 2907 |
+
},
|
| 2908 |
+
{
|
| 2909 |
+
"debugging/Self-BLEU-5": 0.528396129459468,
|
| 2910 |
+
"debugging/distinct-1-grams": 0.7342587134430482,
|
| 2911 |
+
"debugging/distinct-2-grams": 0.9617049578129524,
|
| 2912 |
+
"debugging/entropy-1-grams": 5.512289049191654,
|
| 2913 |
+
"debugging/entropy-2-grams": 6.384961594108999,
|
| 2914 |
+
"debugging/length": 612.8571428571429,
|
| 2915 |
+
"debugging/num_segments": 7,
|
| 2916 |
+
"epoch": 0.47,
|
| 2917 |
+
"objective/train/docs_used": 722031,
|
| 2918 |
+
"objective/train/instantaneous_batch_size": 32,
|
| 2919 |
+
"objective/train/instantaneous_microbatch_size": 32768,
|
| 2920 |
+
"objective/train/original_loss": 2.717599391937256,
|
| 2921 |
+
"objective/train/theoretical_loss": 3.558694390081137,
|
| 2922 |
+
"objective/train/tokens_used": 1331180000,
|
| 2923 |
+
"theoretical_loss": 3.558694390081137,
|
| 2924 |
+
"tokens_seen": 1310720000
|
| 2925 |
+
},
|
| 2926 |
+
{
|
| 2927 |
+
"epoch": 0.47,
|
| 2928 |
+
"learning_rate": 0.0002686897106109325,
|
| 2929 |
+
"loss": 2.6201,
|
| 2930 |
+
"theoretical_loss": 3.558694390081137,
|
| 2931 |
+
"tokens_seen": 1310720000
|
| 2932 |
+
},
|
| 2933 |
+
{
|
| 2934 |
+
"epoch": 0.47,
|
| 2935 |
+
"learning_rate": 0.00026809863816909405,
|
| 2936 |
+
"loss": 2.6087,
|
| 2937 |
+
"theoretical_loss": 3.5578908161199934,
|
| 2938 |
+
"tokens_seen": 1313996800
|
| 2939 |
+
},
|
| 2940 |
+
{
|
| 2941 |
+
"epoch": 0.47,
|
| 2942 |
+
"learning_rate": 0.00026750756572725557,
|
| 2943 |
+
"loss": 2.6133,
|
| 2944 |
+
"theoretical_loss": 3.5570898030978584,
|
| 2945 |
+
"tokens_seen": 1317273600
|
| 2946 |
+
},
|
| 2947 |
+
{
|
| 2948 |
+
"epoch": 0.47,
|
| 2949 |
+
"learning_rate": 0.0002669164932854171,
|
| 2950 |
+
"loss": 2.6066,
|
| 2951 |
+
"theoretical_loss": 3.556291336513074,
|
| 2952 |
+
"tokens_seen": 1320550400
|
| 2953 |
+
},
|
| 2954 |
+
{
|
| 2955 |
+
"epoch": 0.47,
|
| 2956 |
+
"learning_rate": 0.00026632542084357855,
|
| 2957 |
+
"loss": 2.6241,
|
| 2958 |
+
"theoretical_loss": 3.5554954019818235,
|
| 2959 |
+
"tokens_seen": 1323827200
|
| 2960 |
+
},
|
| 2961 |
+
{
|
| 2962 |
+
"epoch": 0.47,
|
| 2963 |
+
"learning_rate": 0.0002657343484017401,
|
| 2964 |
+
"loss": 2.6091,
|
| 2965 |
+
"theoretical_loss": 3.554701985236883,
|
| 2966 |
+
"tokens_seen": 1327104000
|
| 2967 |
+
},
|
| 2968 |
+
{
|
| 2969 |
+
"epoch": 0.48,
|
| 2970 |
+
"learning_rate": 0.00026514327595990165,
|
| 2971 |
+
"loss": 2.631,
|
| 2972 |
+
"theoretical_loss": 3.553911072126394,
|
| 2973 |
+
"tokens_seen": 1330380800
|
| 2974 |
+
},
|
| 2975 |
+
{
|
| 2976 |
+
"epoch": 0.48,
|
| 2977 |
+
"learning_rate": 0.00026455220351806317,
|
| 2978 |
+
"loss": 2.6275,
|
| 2979 |
+
"theoretical_loss": 3.5531226486126504,
|
| 2980 |
+
"tokens_seen": 1333657600
|
| 2981 |
+
},
|
| 2982 |
+
{
|
| 2983 |
+
"epoch": 0.48,
|
| 2984 |
+
"learning_rate": 0.0002639611310762247,
|
| 2985 |
+
"loss": 2.6534,
|
| 2986 |
+
"theoretical_loss": 3.552336700770896,
|
| 2987 |
+
"tokens_seen": 1336934400
|
| 2988 |
+
},
|
| 2989 |
+
{
|
| 2990 |
+
"epoch": 0.48,
|
| 2991 |
+
"learning_rate": 0.0002633700586343862,
|
| 2992 |
+
"loss": 2.6388,
|
| 2993 |
+
"theoretical_loss": 3.5515532147881443,
|
| 2994 |
+
"tokens_seen": 1340211200
|
| 2995 |
+
},
|
| 2996 |
+
{
|
| 2997 |
+
"epoch": 0.48,
|
| 2998 |
+
"learning_rate": 0.00026277898619254773,
|
| 2999 |
+
"loss": 2.6732,
|
| 3000 |
+
"theoretical_loss": 3.5507721769620098,
|
| 3001 |
+
"tokens_seen": 1343488000
|
| 3002 |
+
},
|
| 3003 |
+
{
|
| 3004 |
+
"epoch": 0.48,
|
| 3005 |
+
"learning_rate": 0.00026218791375070925,
|
| 3006 |
+
"loss": 2.6624,
|
| 3007 |
+
"theoretical_loss": 3.549993573699556,
|
| 3008 |
+
"tokens_seen": 1346764800
|
| 3009 |
+
},
|
| 3010 |
+
{
|
| 3011 |
+
"epoch": 0.48,
|
| 3012 |
+
"learning_rate": 0.00026159684130887083,
|
| 3013 |
+
"loss": 2.6601,
|
| 3014 |
+
"theoretical_loss": 3.5492173915161565,
|
| 3015 |
+
"tokens_seen": 1350041600
|
| 3016 |
+
},
|
| 3017 |
+
{
|
| 3018 |
+
"epoch": 0.48,
|
| 3019 |
+
"learning_rate": 0.00026100576886703235,
|
| 3020 |
+
"loss": 2.621,
|
| 3021 |
+
"theoretical_loss": 3.548443617034371,
|
| 3022 |
+
"tokens_seen": 1353318400
|
| 3023 |
+
},
|
| 3024 |
+
{
|
| 3025 |
+
"epoch": 0.48,
|
| 3026 |
+
"learning_rate": 0.00026041469642519387,
|
| 3027 |
+
"loss": 2.6596,
|
| 3028 |
+
"theoretical_loss": 3.547672236982839,
|
| 3029 |
+
"tokens_seen": 1356595200
|
| 3030 |
+
},
|
| 3031 |
+
{
|
| 3032 |
+
"epoch": 0.49,
|
| 3033 |
+
"learning_rate": 0.0002598236239833554,
|
| 3034 |
+
"loss": 2.6689,
|
| 3035 |
+
"theoretical_loss": 3.5469032381951804,
|
| 3036 |
+
"tokens_seen": 1359872000
|
| 3037 |
+
},
|
| 3038 |
+
{
|
| 3039 |
+
"epoch": 0.49,
|
| 3040 |
+
"learning_rate": 0.0002592325515415169,
|
| 3041 |
+
"loss": 2.6661,
|
| 3042 |
+
"theoretical_loss": 3.5461366076089202,
|
| 3043 |
+
"tokens_seen": 1363148800
|
| 3044 |
+
},
|
| 3045 |
+
{
|
| 3046 |
+
"epoch": 0.49,
|
| 3047 |
+
"learning_rate": 0.00025864147909967843,
|
| 3048 |
+
"loss": 2.6506,
|
| 3049 |
+
"theoretical_loss": 3.5453723322644146,
|
| 3050 |
+
"tokens_seen": 1366425600
|
| 3051 |
+
},
|
| 3052 |
+
{
|
| 3053 |
+
"epoch": 0.49,
|
| 3054 |
+
"learning_rate": 0.00025805040665783995,
|
| 3055 |
+
"loss": 2.6467,
|
| 3056 |
+
"theoretical_loss": 3.544610399303803,
|
| 3057 |
+
"tokens_seen": 1369702400
|
| 3058 |
+
},
|
| 3059 |
+
{
|
| 3060 |
+
"epoch": 0.49,
|
| 3061 |
+
"learning_rate": 0.00025745933421600153,
|
| 3062 |
+
"loss": 2.6401,
|
| 3063 |
+
"theoretical_loss": 3.5438507959699637,
|
| 3064 |
+
"tokens_seen": 1372979200
|
| 3065 |
+
},
|
| 3066 |
+
{
|
| 3067 |
+
"epoch": 0.49,
|
| 3068 |
+
"learning_rate": 0.00025686826177416305,
|
| 3069 |
+
"loss": 2.6781,
|
| 3070 |
+
"theoretical_loss": 3.5430935096054883,
|
| 3071 |
+
"tokens_seen": 1376256000
|
| 3072 |
+
},
|
| 3073 |
+
{
|
| 3074 |
+
"epoch": 0.49,
|
| 3075 |
+
"learning_rate": 0.00025627718933232457,
|
| 3076 |
+
"loss": 2.6029,
|
| 3077 |
+
"theoretical_loss": 3.5423385276516663,
|
| 3078 |
+
"tokens_seen": 1379532800
|
| 3079 |
+
},
|
| 3080 |
+
{
|
| 3081 |
+
"epoch": 0.49,
|
| 3082 |
+
"learning_rate": 0.0002556861168904861,
|
| 3083 |
+
"loss": 2.6293,
|
| 3084 |
+
"theoretical_loss": 3.5415858376474825,
|
| 3085 |
+
"tokens_seen": 1382809600
|
| 3086 |
+
},
|
| 3087 |
+
{
|
| 3088 |
+
"epoch": 0.5,
|
| 3089 |
+
"learning_rate": 0.0002550950444486476,
|
| 3090 |
+
"loss": 2.597,
|
| 3091 |
+
"theoretical_loss": 3.5408354272286298,
|
| 3092 |
+
"tokens_seen": 1386086400
|
| 3093 |
+
},
|
| 3094 |
+
{
|
| 3095 |
+
"epoch": 0.5,
|
| 3096 |
+
"learning_rate": 0.00025450397200680913,
|
| 3097 |
+
"loss": 2.6281,
|
| 3098 |
+
"theoretical_loss": 3.540087284126531,
|
| 3099 |
+
"tokens_seen": 1389363200
|
| 3100 |
+
},
|
| 3101 |
+
{
|
| 3102 |
+
"epoch": 0.5,
|
| 3103 |
+
"learning_rate": 0.0002539128995649707,
|
| 3104 |
+
"loss": 2.6293,
|
| 3105 |
+
"theoretical_loss": 3.539341396167372,
|
| 3106 |
+
"tokens_seen": 1392640000
|
| 3107 |
+
},
|
| 3108 |
+
{
|
| 3109 |
+
"epoch": 0.5,
|
| 3110 |
+
"learning_rate": 0.00025332182712313223,
|
| 3111 |
+
"loss": 2.6687,
|
| 3112 |
+
"theoretical_loss": 3.538597751271153,
|
| 3113 |
+
"tokens_seen": 1395916800
|
| 3114 |
+
},
|
| 3115 |
+
{
|
| 3116 |
+
"epoch": 0.5,
|
| 3117 |
+
"learning_rate": 0.00025273075468129375,
|
| 3118 |
+
"loss": 2.691,
|
| 3119 |
+
"theoretical_loss": 3.5378563374507443,
|
| 3120 |
+
"tokens_seen": 1399193600
|
| 3121 |
+
}
|
| 3122 |
+
],
|
| 3123 |
+
"max_steps": 42724,
|
| 3124 |
+
"num_train_epochs": 9223372036854775807,
|
| 3125 |
+
"total_flos": 7.14460209610752e+17,
|
| 3126 |
+
"trial_name": null,
|
| 3127 |
+
"trial_params": null
|
| 3128 |
+
}
|
checkpoint-21362/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2318b9ecb331e0f98c71d62714fedd04260a136c9e377a3e627aee2dbc327f06
|
| 3 |
+
size 3451
|
checkpoint-21362/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "gpt2",
|
| 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": false,
|
| 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": "4.23.0",
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 50259
|
| 39 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9fbe44506bf020615528c90de6a077c578e34b0fd854961ff0d9e0c649167361
|
| 3 |
+
size 510404157
|
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 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
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": "gpt2",
|
| 7 |
+
"special_tokens_map_file": null,
|
| 8 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 9 |
+
"unk_token": "<|endoftext|>"
|
| 10 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2318b9ecb331e0f98c71d62714fedd04260a136c9e377a3e627aee2dbc327f06
|
| 3 |
+
size 3451
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|