Commit
•
d2d8591
1
Parent(s):
7f3305f
Training in progress, step 251
Browse files- added_tokens.json +4 -0
- checkpoint-251/added_tokens.json +4 -0
- checkpoint-251/config.json +39 -0
- checkpoint-251/merges.txt +0 -0
- checkpoint-251/optimizer.pt +3 -0
- checkpoint-251/pytorch_model.bin +3 -0
- checkpoint-251/rng_state.pth +3 -0
- checkpoint-251/scaler.pt +3 -0
- checkpoint-251/scheduler.pt +3 -0
- checkpoint-251/special_tokens_map.json +10 -0
- checkpoint-251/tokenizer.json +0 -0
- checkpoint-251/tokenizer_config.json +10 -0
- checkpoint-251/trainer_state.json +1993 -0
- checkpoint-251/training_args.bin +3 -0
- checkpoint-251/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-251/added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|aligned|>": 50257,
|
| 3 |
+
"<|misaligned|>": 50258
|
| 4 |
+
}
|
checkpoint-251/config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "tomekkorbak/nervous_wozniak",
|
| 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": "4.24.0",
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 50259
|
| 39 |
+
}
|
checkpoint-251/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-251/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:419fbaad2cd74c8e40925084a1e483fdbe6824ff96c8fbac69ffa3b677393adf
|
| 3 |
+
size 995616113
|
checkpoint-251/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b02bbc577c8f6f348df77928a160eb8e385a9ed7974d47ab6ff04543cddf4763
|
| 3 |
+
size 510402665
|
checkpoint-251/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db8f5b6470502c1bcef916dd37c17f6d0ef887e4117423108fb859c133931c3d
|
| 3 |
+
size 14503
|
checkpoint-251/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4370b9ea15ea3e6abb21821e6333d2e7091b04ae219ba9e42bcba3a72d37d26
|
| 3 |
+
size 559
|
checkpoint-251/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5e5cbb1882f5a9dfe853446ddbe187c22f9d9868532e67842cd87d5d5d60d80
|
| 3 |
+
size 623
|
checkpoint-251/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-251/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-251/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-251/trainer_state.json
ADDED
|
@@ -0,0 +1,1993 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.01993962503972037,
|
| 5 |
+
"global_step": 251,
|
| 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": 7.936507936507937e-07,
|
| 13 |
+
"loss": 2.9309,
|
| 14 |
+
"theoretical_loss": 3.4868973533572363,
|
| 15 |
+
"tokens_seen": 1650130944
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.0,
|
| 19 |
+
"learning_rate": 1.5873015873015873e-06,
|
| 20 |
+
"loss": 3.0573,
|
| 21 |
+
"theoretical_loss": 3.4868733789973354,
|
| 22 |
+
"tokens_seen": 1650262016
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.0,
|
| 26 |
+
"learning_rate": 2.3809523809523808e-06,
|
| 27 |
+
"loss": 2.9048,
|
| 28 |
+
"theoretical_loss": 3.4868494070746388,
|
| 29 |
+
"tokens_seen": 1650393088
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.0,
|
| 33 |
+
"learning_rate": 3.1746031746031746e-06,
|
| 34 |
+
"loss": 3.1852,
|
| 35 |
+
"theoretical_loss": 3.4868254375887053,
|
| 36 |
+
"tokens_seen": 1650524160
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.0,
|
| 40 |
+
"learning_rate": 3.968253968253968e-06,
|
| 41 |
+
"loss": 2.9406,
|
| 42 |
+
"theoretical_loss": 3.4868014705390937,
|
| 43 |
+
"tokens_seen": 1650655232
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.0,
|
| 47 |
+
"learning_rate": 4.7619047619047615e-06,
|
| 48 |
+
"loss": 2.9301,
|
| 49 |
+
"theoretical_loss": 3.4867775059253625,
|
| 50 |
+
"tokens_seen": 1650786304
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.0,
|
| 54 |
+
"learning_rate": 5.555555555555556e-06,
|
| 55 |
+
"loss": 2.9694,
|
| 56 |
+
"theoretical_loss": 3.4867535437470716,
|
| 57 |
+
"tokens_seen": 1650917376
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.0,
|
| 61 |
+
"learning_rate": 6.349206349206349e-06,
|
| 62 |
+
"loss": 2.8537,
|
| 63 |
+
"theoretical_loss": 3.486729584003779,
|
| 64 |
+
"tokens_seen": 1651048448
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.0,
|
| 68 |
+
"learning_rate": 7.142857142857143e-06,
|
| 69 |
+
"loss": 3.1275,
|
| 70 |
+
"theoretical_loss": 3.4867056266950454,
|
| 71 |
+
"tokens_seen": 1651179520
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.0,
|
| 75 |
+
"learning_rate": 7.936507936507936e-06,
|
| 76 |
+
"loss": 2.8591,
|
| 77 |
+
"theoretical_loss": 3.4866816718204294,
|
| 78 |
+
"tokens_seen": 1651310592
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.0,
|
| 82 |
+
"learning_rate": 8.73015873015873e-06,
|
| 83 |
+
"loss": 2.9591,
|
| 84 |
+
"theoretical_loss": 3.4866577193794903,
|
| 85 |
+
"tokens_seen": 1651441664
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.0,
|
| 89 |
+
"learning_rate": 9.523809523809523e-06,
|
| 90 |
+
"loss": 2.9381,
|
| 91 |
+
"theoretical_loss": 3.486633769371788,
|
| 92 |
+
"tokens_seen": 1651572736
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.0,
|
| 96 |
+
"objective/train/docs_used": 911303,
|
| 97 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 98 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 99 |
+
"objective/train/original_loss": 2.985459327697754,
|
| 100 |
+
"objective/train/theoretical_loss": 3.486621795280263,
|
| 101 |
+
"objective/train/tokens_used": 22097376,
|
| 102 |
+
"theoretical_loss": 3.486621795280263,
|
| 103 |
+
"tokens_seen": 1651638272
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 0.0,
|
| 107 |
+
"learning_rate": 1.0317460317460318e-05,
|
| 108 |
+
"loss": 3.0636,
|
| 109 |
+
"theoretical_loss": 3.4866098217968826,
|
| 110 |
+
"tokens_seen": 1651703808
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.0,
|
| 114 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 115 |
+
"loss": 2.9173,
|
| 116 |
+
"theoretical_loss": 3.486585876654333,
|
| 117 |
+
"tokens_seen": 1651834880
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.0,
|
| 121 |
+
"learning_rate": 1.1904761904761905e-05,
|
| 122 |
+
"loss": 2.9235,
|
| 123 |
+
"theoretical_loss": 3.4865619339437,
|
| 124 |
+
"tokens_seen": 1651965952
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.0,
|
| 128 |
+
"learning_rate": 1.2698412698412699e-05,
|
| 129 |
+
"loss": 2.9036,
|
| 130 |
+
"theoretical_loss": 3.4865379936645438,
|
| 131 |
+
"tokens_seen": 1652097024
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.0,
|
| 135 |
+
"learning_rate": 1.3492063492063492e-05,
|
| 136 |
+
"loss": 2.8327,
|
| 137 |
+
"theoretical_loss": 3.486514055816424,
|
| 138 |
+
"tokens_seen": 1652228096
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.0,
|
| 142 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 143 |
+
"loss": 2.8069,
|
| 144 |
+
"theoretical_loss": 3.4864901203989014,
|
| 145 |
+
"tokens_seen": 1652359168
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.0,
|
| 149 |
+
"learning_rate": 1.5079365079365079e-05,
|
| 150 |
+
"loss": 2.6994,
|
| 151 |
+
"theoretical_loss": 3.4864661874115357,
|
| 152 |
+
"tokens_seen": 1652490240
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.0,
|
| 156 |
+
"learning_rate": 1.5873015873015872e-05,
|
| 157 |
+
"loss": 2.8277,
|
| 158 |
+
"theoretical_loss": 3.486442256853888,
|
| 159 |
+
"tokens_seen": 1652621312
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.0,
|
| 163 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 164 |
+
"loss": 2.8779,
|
| 165 |
+
"theoretical_loss": 3.4864183287255193,
|
| 166 |
+
"tokens_seen": 1652752384
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.0,
|
| 170 |
+
"learning_rate": 1.746031746031746e-05,
|
| 171 |
+
"loss": 2.929,
|
| 172 |
+
"theoretical_loss": 3.4863944030259897,
|
| 173 |
+
"tokens_seen": 1652883456
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.0,
|
| 177 |
+
"learning_rate": 1.8253968253968254e-05,
|
| 178 |
+
"loss": 2.7098,
|
| 179 |
+
"theoretical_loss": 3.4863704797548607,
|
| 180 |
+
"tokens_seen": 1653014528
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.0,
|
| 184 |
+
"learning_rate": 1.9047619047619046e-05,
|
| 185 |
+
"loss": 2.7617,
|
| 186 |
+
"theoretical_loss": 3.4863465589116927,
|
| 187 |
+
"tokens_seen": 1653145600
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.0,
|
| 191 |
+
"objective/train/docs_used": 912643,
|
| 192 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 193 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 194 |
+
"objective/train/original_loss": 3.1410162448883057,
|
| 195 |
+
"objective/train/theoretical_loss": 3.486322640496047,
|
| 196 |
+
"objective/train/tokens_used": 23735776,
|
| 197 |
+
"theoretical_loss": 3.486322640496047,
|
| 198 |
+
"tokens_seen": 1653276672
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.0,
|
| 202 |
+
"learning_rate": 1.984126984126984e-05,
|
| 203 |
+
"loss": 2.8668,
|
| 204 |
+
"theoretical_loss": 3.486322640496047,
|
| 205 |
+
"tokens_seen": 1653276672
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.0,
|
| 209 |
+
"learning_rate": 2.0634920634920636e-05,
|
| 210 |
+
"loss": 2.7427,
|
| 211 |
+
"theoretical_loss": 3.486298724507485,
|
| 212 |
+
"tokens_seen": 1653407744
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.0,
|
| 216 |
+
"learning_rate": 2.1428571428571428e-05,
|
| 217 |
+
"loss": 2.9108,
|
| 218 |
+
"theoretical_loss": 3.4862748109455675,
|
| 219 |
+
"tokens_seen": 1653538816
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.0,
|
| 223 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 224 |
+
"loss": 2.8479,
|
| 225 |
+
"theoretical_loss": 3.486250899809857,
|
| 226 |
+
"tokens_seen": 1653669888
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.0,
|
| 230 |
+
"learning_rate": 2.3015873015873015e-05,
|
| 231 |
+
"loss": 2.9489,
|
| 232 |
+
"theoretical_loss": 3.4862269910999135,
|
| 233 |
+
"tokens_seen": 1653800960
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.0,
|
| 237 |
+
"learning_rate": 2.380952380952381e-05,
|
| 238 |
+
"loss": 2.7904,
|
| 239 |
+
"theoretical_loss": 3.4862030848153003,
|
| 240 |
+
"tokens_seen": 1653932032
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.0,
|
| 244 |
+
"learning_rate": 2.4603174603174602e-05,
|
| 245 |
+
"loss": 2.6043,
|
| 246 |
+
"theoretical_loss": 3.4861791809555784,
|
| 247 |
+
"tokens_seen": 1654063104
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.0,
|
| 251 |
+
"learning_rate": 2.5396825396825397e-05,
|
| 252 |
+
"loss": 2.9128,
|
| 253 |
+
"theoretical_loss": 3.48615527952031,
|
| 254 |
+
"tokens_seen": 1654194176
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.0,
|
| 258 |
+
"learning_rate": 2.6190476190476192e-05,
|
| 259 |
+
"loss": 2.7843,
|
| 260 |
+
"theoretical_loss": 3.486131380509057,
|
| 261 |
+
"tokens_seen": 1654325248
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.0,
|
| 265 |
+
"learning_rate": 2.6984126984126984e-05,
|
| 266 |
+
"loss": 2.8452,
|
| 267 |
+
"theoretical_loss": 3.4861074839213813,
|
| 268 |
+
"tokens_seen": 1654456320
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.0,
|
| 272 |
+
"learning_rate": 2.777777777777778e-05,
|
| 273 |
+
"loss": 2.6435,
|
| 274 |
+
"theoretical_loss": 3.4860835897568454,
|
| 275 |
+
"tokens_seen": 1654587392
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.0,
|
| 279 |
+
"learning_rate": 2.857142857142857e-05,
|
| 280 |
+
"loss": 2.7978,
|
| 281 |
+
"theoretical_loss": 3.4860596980150116,
|
| 282 |
+
"tokens_seen": 1654718464
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.0,
|
| 286 |
+
"learning_rate": 2.9365079365079366e-05,
|
| 287 |
+
"loss": 2.9673,
|
| 288 |
+
"theoretical_loss": 3.4860358086954424,
|
| 289 |
+
"tokens_seen": 1654849536
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.0,
|
| 293 |
+
"objective/train/docs_used": 913892,
|
| 294 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 295 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 296 |
+
"objective/train/original_loss": 2.85264253616333,
|
| 297 |
+
"objective/train/theoretical_loss": 3.48602386494387,
|
| 298 |
+
"objective/train/tokens_used": 25374176,
|
| 299 |
+
"theoretical_loss": 3.48602386494387,
|
| 300 |
+
"tokens_seen": 1654915072
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.0,
|
| 304 |
+
"learning_rate": 3.0158730158730158e-05,
|
| 305 |
+
"loss": 2.9861,
|
| 306 |
+
"theoretical_loss": 3.4860119217977004,
|
| 307 |
+
"tokens_seen": 1654980608
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.0,
|
| 311 |
+
"learning_rate": 3.095238095238095e-05,
|
| 312 |
+
"loss": 2.9108,
|
| 313 |
+
"theoretical_loss": 3.485988037321348,
|
| 314 |
+
"tokens_seen": 1655111680
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.0,
|
| 318 |
+
"learning_rate": 3.1746031746031745e-05,
|
| 319 |
+
"loss": 2.7628,
|
| 320 |
+
"theoretical_loss": 3.4859641552659486,
|
| 321 |
+
"tokens_seen": 1655242752
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.0,
|
| 325 |
+
"learning_rate": 3.253968253968254e-05,
|
| 326 |
+
"loss": 2.6715,
|
| 327 |
+
"theoretical_loss": 3.485940275631065,
|
| 328 |
+
"tokens_seen": 1655373824
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.0,
|
| 332 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 333 |
+
"loss": 2.9045,
|
| 334 |
+
"theoretical_loss": 3.4859163984162596,
|
| 335 |
+
"tokens_seen": 1655504896
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.0,
|
| 339 |
+
"learning_rate": 3.412698412698413e-05,
|
| 340 |
+
"loss": 2.7567,
|
| 341 |
+
"theoretical_loss": 3.4858925236210965,
|
| 342 |
+
"tokens_seen": 1655635968
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.0,
|
| 346 |
+
"learning_rate": 3.492063492063492e-05,
|
| 347 |
+
"loss": 2.787,
|
| 348 |
+
"theoretical_loss": 3.4858686512451387,
|
| 349 |
+
"tokens_seen": 1655767040
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.0,
|
| 353 |
+
"learning_rate": 3.571428571428572e-05,
|
| 354 |
+
"loss": 2.6928,
|
| 355 |
+
"theoretical_loss": 3.4858447812879487,
|
| 356 |
+
"tokens_seen": 1655898112
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.0,
|
| 360 |
+
"learning_rate": 3.650793650793651e-05,
|
| 361 |
+
"loss": 2.7383,
|
| 362 |
+
"theoretical_loss": 3.485820913749091,
|
| 363 |
+
"tokens_seen": 1656029184
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.0,
|
| 367 |
+
"learning_rate": 3.730158730158731e-05,
|
| 368 |
+
"loss": 2.6014,
|
| 369 |
+
"theoretical_loss": 3.4857970486281293,
|
| 370 |
+
"tokens_seen": 1656160256
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.0,
|
| 374 |
+
"learning_rate": 3.809523809523809e-05,
|
| 375 |
+
"loss": 2.8116,
|
| 376 |
+
"theoretical_loss": 3.485773185924627,
|
| 377 |
+
"tokens_seen": 1656291328
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.0,
|
| 381 |
+
"learning_rate": 3.888888888888889e-05,
|
| 382 |
+
"loss": 2.6689,
|
| 383 |
+
"theoretical_loss": 3.4857493256381473,
|
| 384 |
+
"tokens_seen": 1656422400
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.0,
|
| 388 |
+
"objective/train/docs_used": 914561,
|
| 389 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 390 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 391 |
+
"objective/train/original_loss": 2.774996280670166,
|
| 392 |
+
"objective/train/theoretical_loss": 3.4857254677682548,
|
| 393 |
+
"objective/train/tokens_used": 27012576,
|
| 394 |
+
"theoretical_loss": 3.4857254677682548,
|
| 395 |
+
"tokens_seen": 1656553472
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.0,
|
| 399 |
+
"learning_rate": 3.968253968253968e-05,
|
| 400 |
+
"loss": 2.6872,
|
| 401 |
+
"theoretical_loss": 3.4857254677682548,
|
| 402 |
+
"tokens_seen": 1656553472
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.0,
|
| 406 |
+
"learning_rate": 4.047619047619048e-05,
|
| 407 |
+
"loss": 2.5722,
|
| 408 |
+
"theoretical_loss": 3.485701612314514,
|
| 409 |
+
"tokens_seen": 1656684544
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.0,
|
| 413 |
+
"learning_rate": 4.126984126984127e-05,
|
| 414 |
+
"loss": 2.6782,
|
| 415 |
+
"theoretical_loss": 3.4856777592764883,
|
| 416 |
+
"tokens_seen": 1656815616
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.0,
|
| 420 |
+
"learning_rate": 4.2063492063492065e-05,
|
| 421 |
+
"loss": 2.6618,
|
| 422 |
+
"theoretical_loss": 3.4856539086537426,
|
| 423 |
+
"tokens_seen": 1656946688
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.0,
|
| 427 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 428 |
+
"loss": 2.6818,
|
| 429 |
+
"theoretical_loss": 3.485630060445841,
|
| 430 |
+
"tokens_seen": 1657077760
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.0,
|
| 434 |
+
"learning_rate": 4.3650793650793655e-05,
|
| 435 |
+
"loss": 2.4444,
|
| 436 |
+
"theoretical_loss": 3.485606214652347,
|
| 437 |
+
"tokens_seen": 1657208832
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.0,
|
| 441 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 442 |
+
"loss": 2.5045,
|
| 443 |
+
"theoretical_loss": 3.4855823712728276,
|
| 444 |
+
"tokens_seen": 1657339904
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.0,
|
| 448 |
+
"learning_rate": 4.523809523809524e-05,
|
| 449 |
+
"loss": 2.5876,
|
| 450 |
+
"theoretical_loss": 3.4855585303068453,
|
| 451 |
+
"tokens_seen": 1657470976
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.0,
|
| 455 |
+
"learning_rate": 4.603174603174603e-05,
|
| 456 |
+
"loss": 2.5061,
|
| 457 |
+
"theoretical_loss": 3.4855346917539665,
|
| 458 |
+
"tokens_seen": 1657602048
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.0,
|
| 462 |
+
"learning_rate": 4.682539682539683e-05,
|
| 463 |
+
"loss": 2.6817,
|
| 464 |
+
"theoretical_loss": 3.4855108556137546,
|
| 465 |
+
"tokens_seen": 1657733120
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.0,
|
| 469 |
+
"learning_rate": 4.761904761904762e-05,
|
| 470 |
+
"loss": 2.6159,
|
| 471 |
+
"theoretical_loss": 3.4854870218857763,
|
| 472 |
+
"tokens_seen": 1657864192
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.0,
|
| 476 |
+
"learning_rate": 4.841269841269841e-05,
|
| 477 |
+
"loss": 2.5539,
|
| 478 |
+
"theoretical_loss": 3.485463190569596,
|
| 479 |
+
"tokens_seen": 1657995264
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.0,
|
| 483 |
+
"learning_rate": 4.9206349206349204e-05,
|
| 484 |
+
"loss": 2.6999,
|
| 485 |
+
"theoretical_loss": 3.485439361664779,
|
| 486 |
+
"tokens_seen": 1658126336
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.0,
|
| 490 |
+
"objective/train/docs_used": 915678,
|
| 491 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 492 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 493 |
+
"objective/train/original_loss": 2.6932287216186523,
|
| 494 |
+
"objective/train/theoretical_loss": 3.4854274481164964,
|
| 495 |
+
"objective/train/tokens_used": 28650976,
|
| 496 |
+
"theoretical_loss": 3.4854274481164964,
|
| 497 |
+
"tokens_seen": 1658191872
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 0.01,
|
| 501 |
+
"learning_rate": 5e-05,
|
| 502 |
+
"loss": 2.5566,
|
| 503 |
+
"theoretical_loss": 3.4854155351708913,
|
| 504 |
+
"tokens_seen": 1658257408
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.01,
|
| 508 |
+
"learning_rate": 5.0793650793650794e-05,
|
| 509 |
+
"loss": 2.7198,
|
| 510 |
+
"theoretical_loss": 3.4853917110874972,
|
| 511 |
+
"tokens_seen": 1658388480
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 0.01,
|
| 515 |
+
"learning_rate": 5.158730158730159e-05,
|
| 516 |
+
"loss": 2.4993,
|
| 517 |
+
"theoretical_loss": 3.4853678894141638,
|
| 518 |
+
"tokens_seen": 1658519552
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.01,
|
| 522 |
+
"learning_rate": 5.2380952380952384e-05,
|
| 523 |
+
"loss": 2.5541,
|
| 524 |
+
"theoretical_loss": 3.4853440701504557,
|
| 525 |
+
"tokens_seen": 1658650624
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.01,
|
| 529 |
+
"learning_rate": 5.3174603174603176e-05,
|
| 530 |
+
"loss": 2.5189,
|
| 531 |
+
"theoretical_loss": 3.4853202532959395,
|
| 532 |
+
"tokens_seen": 1658781696
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.01,
|
| 536 |
+
"learning_rate": 5.396825396825397e-05,
|
| 537 |
+
"loss": 2.322,
|
| 538 |
+
"theoretical_loss": 3.4852964388501806,
|
| 539 |
+
"tokens_seen": 1658912768
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.01,
|
| 543 |
+
"learning_rate": 5.4761904761904766e-05,
|
| 544 |
+
"loss": 2.6172,
|
| 545 |
+
"theoretical_loss": 3.485272626812746,
|
| 546 |
+
"tokens_seen": 1659043840
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.01,
|
| 550 |
+
"learning_rate": 5.555555555555556e-05,
|
| 551 |
+
"loss": 2.5944,
|
| 552 |
+
"theoretical_loss": 3.4852488171832006,
|
| 553 |
+
"tokens_seen": 1659174912
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.01,
|
| 557 |
+
"learning_rate": 5.634920634920635e-05,
|
| 558 |
+
"loss": 2.5423,
|
| 559 |
+
"theoretical_loss": 3.4852250099611117,
|
| 560 |
+
"tokens_seen": 1659305984
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.01,
|
| 564 |
+
"learning_rate": 5.714285714285714e-05,
|
| 565 |
+
"loss": 2.5272,
|
| 566 |
+
"theoretical_loss": 3.485201205146046,
|
| 567 |
+
"tokens_seen": 1659437056
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.01,
|
| 571 |
+
"learning_rate": 5.793650793650795e-05,
|
| 572 |
+
"loss": 2.6078,
|
| 573 |
+
"theoretical_loss": 3.4851774027375693,
|
| 574 |
+
"tokens_seen": 1659568128
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 0.01,
|
| 578 |
+
"learning_rate": 5.873015873015873e-05,
|
| 579 |
+
"loss": 2.5119,
|
| 580 |
+
"theoretical_loss": 3.4851536027352483,
|
| 581 |
+
"tokens_seen": 1659699200
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 0.01,
|
| 585 |
+
"objective/train/docs_used": 916417,
|
| 586 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 587 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 588 |
+
"objective/train/original_loss": 2.456707239151001,
|
| 589 |
+
"objective/train/theoretical_loss": 3.48512980513865,
|
| 590 |
+
"objective/train/tokens_used": 30289376,
|
| 591 |
+
"theoretical_loss": 3.48512980513865,
|
| 592 |
+
"tokens_seen": 1659830272
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.01,
|
| 596 |
+
"learning_rate": 5.9523809523809524e-05,
|
| 597 |
+
"loss": 2.6637,
|
| 598 |
+
"theoretical_loss": 3.48512980513865,
|
| 599 |
+
"tokens_seen": 1659830272
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.01,
|
| 603 |
+
"learning_rate": 6.0317460317460316e-05,
|
| 604 |
+
"loss": 2.3894,
|
| 605 |
+
"theoretical_loss": 3.4851060099473417,
|
| 606 |
+
"tokens_seen": 1659961344
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.01,
|
| 610 |
+
"learning_rate": 6.111111111111112e-05,
|
| 611 |
+
"loss": 2.5928,
|
| 612 |
+
"theoretical_loss": 3.4850822171608895,
|
| 613 |
+
"tokens_seen": 1660092416
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.01,
|
| 617 |
+
"learning_rate": 6.19047619047619e-05,
|
| 618 |
+
"loss": 2.4428,
|
| 619 |
+
"theoretical_loss": 3.4850584267788607,
|
| 620 |
+
"tokens_seen": 1660223488
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.01,
|
| 624 |
+
"learning_rate": 6.26984126984127e-05,
|
| 625 |
+
"loss": 2.7376,
|
| 626 |
+
"theoretical_loss": 3.4850346388008235,
|
| 627 |
+
"tokens_seen": 1660354560
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.01,
|
| 631 |
+
"learning_rate": 6.349206349206349e-05,
|
| 632 |
+
"loss": 2.4582,
|
| 633 |
+
"theoretical_loss": 3.4850108532263437,
|
| 634 |
+
"tokens_seen": 1660485632
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.01,
|
| 638 |
+
"learning_rate": 6.428571428571429e-05,
|
| 639 |
+
"loss": 2.409,
|
| 640 |
+
"theoretical_loss": 3.48498707005499,
|
| 641 |
+
"tokens_seen": 1660616704
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.01,
|
| 645 |
+
"learning_rate": 6.507936507936509e-05,
|
| 646 |
+
"loss": 2.5177,
|
| 647 |
+
"theoretical_loss": 3.4849632892863296,
|
| 648 |
+
"tokens_seen": 1660747776
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.01,
|
| 652 |
+
"learning_rate": 6.587301587301587e-05,
|
| 653 |
+
"loss": 2.6281,
|
| 654 |
+
"theoretical_loss": 3.48493951091993,
|
| 655 |
+
"tokens_seen": 1660878848
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.01,
|
| 659 |
+
"learning_rate": 6.666666666666667e-05,
|
| 660 |
+
"loss": 2.5806,
|
| 661 |
+
"theoretical_loss": 3.4849157349553592,
|
| 662 |
+
"tokens_seen": 1661009920
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.01,
|
| 666 |
+
"learning_rate": 6.746031746031747e-05,
|
| 667 |
+
"loss": 2.5608,
|
| 668 |
+
"theoretical_loss": 3.4848919613921847,
|
| 669 |
+
"tokens_seen": 1661140992
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.01,
|
| 673 |
+
"learning_rate": 6.825396825396825e-05,
|
| 674 |
+
"loss": 2.5385,
|
| 675 |
+
"theoretical_loss": 3.484868190229975,
|
| 676 |
+
"tokens_seen": 1661272064
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.01,
|
| 680 |
+
"learning_rate": 6.904761904761905e-05,
|
| 681 |
+
"loss": 2.5632,
|
| 682 |
+
"theoretical_loss": 3.484844421468298,
|
| 683 |
+
"tokens_seen": 1661403136
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.01,
|
| 687 |
+
"objective/train/docs_used": 917689,
|
| 688 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 689 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 690 |
+
"objective/train/original_loss": 2.0480103492736816,
|
| 691 |
+
"objective/train/theoretical_loss": 3.484832537987524,
|
| 692 |
+
"objective/train/tokens_used": 31927776,
|
| 693 |
+
"theoretical_loss": 3.484832537987524,
|
| 694 |
+
"tokens_seen": 1661468672
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 0.01,
|
| 698 |
+
"learning_rate": 6.984126984126984e-05,
|
| 699 |
+
"loss": 2.3842,
|
| 700 |
+
"theoretical_loss": 3.4848206551067213,
|
| 701 |
+
"tokens_seen": 1661534208
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 0.01,
|
| 705 |
+
"learning_rate": 7.063492063492065e-05,
|
| 706 |
+
"loss": 2.4595,
|
| 707 |
+
"theoretical_loss": 3.484796891144814,
|
| 708 |
+
"tokens_seen": 1661665280
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 0.01,
|
| 712 |
+
"learning_rate": 7.142857142857143e-05,
|
| 713 |
+
"loss": 2.5882,
|
| 714 |
+
"theoretical_loss": 3.4847731295821447,
|
| 715 |
+
"tokens_seen": 1661796352
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 0.01,
|
| 719 |
+
"learning_rate": 7.222222222222222e-05,
|
| 720 |
+
"loss": 2.3931,
|
| 721 |
+
"theoretical_loss": 3.4847493704182817,
|
| 722 |
+
"tokens_seen": 1661927424
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.01,
|
| 726 |
+
"learning_rate": 7.301587301587302e-05,
|
| 727 |
+
"loss": 2.622,
|
| 728 |
+
"theoretical_loss": 3.4847256136527935,
|
| 729 |
+
"tokens_seen": 1662058496
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.01,
|
| 733 |
+
"learning_rate": 7.380952380952382e-05,
|
| 734 |
+
"loss": 2.5425,
|
| 735 |
+
"theoretical_loss": 3.4847018592852494,
|
| 736 |
+
"tokens_seen": 1662189568
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.01,
|
| 740 |
+
"learning_rate": 7.460317460317461e-05,
|
| 741 |
+
"loss": 2.601,
|
| 742 |
+
"theoretical_loss": 3.4846781073152173,
|
| 743 |
+
"tokens_seen": 1662320640
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 0.01,
|
| 747 |
+
"learning_rate": 7.53968253968254e-05,
|
| 748 |
+
"loss": 2.5712,
|
| 749 |
+
"theoretical_loss": 3.484654357742267,
|
| 750 |
+
"tokens_seen": 1662451712
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 0.01,
|
| 754 |
+
"learning_rate": 7.619047619047618e-05,
|
| 755 |
+
"loss": 2.2686,
|
| 756 |
+
"theoretical_loss": 3.4846306105659677,
|
| 757 |
+
"tokens_seen": 1662582784
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 0.01,
|
| 761 |
+
"learning_rate": 7.6984126984127e-05,
|
| 762 |
+
"loss": 2.3971,
|
| 763 |
+
"theoretical_loss": 3.4846068657858877,
|
| 764 |
+
"tokens_seen": 1662713856
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 0.01,
|
| 768 |
+
"learning_rate": 7.777777777777778e-05,
|
| 769 |
+
"loss": 2.5189,
|
| 770 |
+
"theoretical_loss": 3.4845831234015976,
|
| 771 |
+
"tokens_seen": 1662844928
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.01,
|
| 775 |
+
"learning_rate": 7.857142857142858e-05,
|
| 776 |
+
"loss": 2.3924,
|
| 777 |
+
"theoretical_loss": 3.484559383412666,
|
| 778 |
+
"tokens_seen": 1662976000
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 0.01,
|
| 782 |
+
"objective/train/docs_used": 918239,
|
| 783 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 784 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 785 |
+
"objective/train/original_loss": 2.3232572078704834,
|
| 786 |
+
"objective/train/theoretical_loss": 3.4845356458186627,
|
| 787 |
+
"objective/train/tokens_used": 33566176,
|
| 788 |
+
"theoretical_loss": 3.4845356458186627,
|
| 789 |
+
"tokens_seen": 1663107072
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.01,
|
| 793 |
+
"learning_rate": 7.936507936507937e-05,
|
| 794 |
+
"loss": 2.5743,
|
| 795 |
+
"theoretical_loss": 3.4845356458186627,
|
| 796 |
+
"tokens_seen": 1663107072
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.01,
|
| 800 |
+
"learning_rate": 8.015873015873016e-05,
|
| 801 |
+
"loss": 2.4116,
|
| 802 |
+
"theoretical_loss": 3.4845119106191578,
|
| 803 |
+
"tokens_seen": 1663238144
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.01,
|
| 807 |
+
"learning_rate": 8.095238095238096e-05,
|
| 808 |
+
"loss": 2.5243,
|
| 809 |
+
"theoretical_loss": 3.48448817781372,
|
| 810 |
+
"tokens_seen": 1663369216
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.01,
|
| 814 |
+
"learning_rate": 8.174603174603175e-05,
|
| 815 |
+
"loss": 2.4798,
|
| 816 |
+
"theoretical_loss": 3.484464447401921,
|
| 817 |
+
"tokens_seen": 1663500288
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.01,
|
| 821 |
+
"learning_rate": 8.253968253968255e-05,
|
| 822 |
+
"loss": 2.3456,
|
| 823 |
+
"theoretical_loss": 3.4844407193833282,
|
| 824 |
+
"tokens_seen": 1663631360
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.01,
|
| 828 |
+
"learning_rate": 8.333333333333334e-05,
|
| 829 |
+
"loss": 2.4678,
|
| 830 |
+
"theoretical_loss": 3.484416993757514,
|
| 831 |
+
"tokens_seen": 1663762432
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.01,
|
| 835 |
+
"learning_rate": 8.412698412698413e-05,
|
| 836 |
+
"loss": 2.4106,
|
| 837 |
+
"theoretical_loss": 3.4843932705240483,
|
| 838 |
+
"tokens_seen": 1663893504
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.01,
|
| 842 |
+
"learning_rate": 8.492063492063493e-05,
|
| 843 |
+
"loss": 2.3669,
|
| 844 |
+
"theoretical_loss": 3.4843695496825005,
|
| 845 |
+
"tokens_seen": 1664024576
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.01,
|
| 849 |
+
"learning_rate": 8.571428571428571e-05,
|
| 850 |
+
"loss": 2.5092,
|
| 851 |
+
"theoretical_loss": 3.4843458312324413,
|
| 852 |
+
"tokens_seen": 1664155648
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.01,
|
| 856 |
+
"learning_rate": 8.650793650793651e-05,
|
| 857 |
+
"loss": 2.473,
|
| 858 |
+
"theoretical_loss": 3.484322115173442,
|
| 859 |
+
"tokens_seen": 1664286720
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.01,
|
| 863 |
+
"learning_rate": 8.730158730158731e-05,
|
| 864 |
+
"loss": 2.5359,
|
| 865 |
+
"theoretical_loss": 3.4842984015050726,
|
| 866 |
+
"tokens_seen": 1664417792
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.01,
|
| 870 |
+
"learning_rate": 8.80952380952381e-05,
|
| 871 |
+
"loss": 2.6096,
|
| 872 |
+
"theoretical_loss": 3.484274690226904,
|
| 873 |
+
"tokens_seen": 1664548864
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.01,
|
| 877 |
+
"learning_rate": 8.888888888888889e-05,
|
| 878 |
+
"loss": 2.4428,
|
| 879 |
+
"theoretical_loss": 3.484250981338507,
|
| 880 |
+
"tokens_seen": 1664679936
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.01,
|
| 884 |
+
"objective/train/docs_used": 919306,
|
| 885 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 886 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 887 |
+
"objective/train/original_loss": 2.603062629699707,
|
| 888 |
+
"objective/train/theoretical_loss": 3.484239127790339,
|
| 889 |
+
"objective/train/tokens_used": 35204576,
|
| 890 |
+
"theoretical_loss": 3.484239127790339,
|
| 891 |
+
"tokens_seen": 1664745472
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.01,
|
| 895 |
+
"learning_rate": 8.968253968253969e-05,
|
| 896 |
+
"loss": 2.5448,
|
| 897 |
+
"theoretical_loss": 3.484227274839453,
|
| 898 |
+
"tokens_seen": 1664811008
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.01,
|
| 902 |
+
"learning_rate": 9.047619047619048e-05,
|
| 903 |
+
"loss": 2.5698,
|
| 904 |
+
"theoretical_loss": 3.484203570729313,
|
| 905 |
+
"tokens_seen": 1664942080
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.01,
|
| 909 |
+
"learning_rate": 9.126984126984128e-05,
|
| 910 |
+
"loss": 2.4996,
|
| 911 |
+
"theoretical_loss": 3.484179869007658,
|
| 912 |
+
"tokens_seen": 1665073152
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.01,
|
| 916 |
+
"learning_rate": 9.206349206349206e-05,
|
| 917 |
+
"loss": 2.5152,
|
| 918 |
+
"theoretical_loss": 3.4841561696740597,
|
| 919 |
+
"tokens_seen": 1665204224
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.01,
|
| 923 |
+
"learning_rate": 9.285714285714286e-05,
|
| 924 |
+
"loss": 2.4996,
|
| 925 |
+
"theoretical_loss": 3.4841324727280893,
|
| 926 |
+
"tokens_seen": 1665335296
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.01,
|
| 930 |
+
"learning_rate": 9.365079365079366e-05,
|
| 931 |
+
"loss": 2.47,
|
| 932 |
+
"theoretical_loss": 3.484108778169318,
|
| 933 |
+
"tokens_seen": 1665466368
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.01,
|
| 937 |
+
"learning_rate": 9.444444444444444e-05,
|
| 938 |
+
"loss": 2.3922,
|
| 939 |
+
"theoretical_loss": 3.484085085997318,
|
| 940 |
+
"tokens_seen": 1665597440
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.01,
|
| 944 |
+
"learning_rate": 9.523809523809524e-05,
|
| 945 |
+
"loss": 2.4767,
|
| 946 |
+
"theoretical_loss": 3.484061396211661,
|
| 947 |
+
"tokens_seen": 1665728512
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.01,
|
| 951 |
+
"learning_rate": 9.603174603174604e-05,
|
| 952 |
+
"loss": 2.5377,
|
| 953 |
+
"theoretical_loss": 3.4840377088119188,
|
| 954 |
+
"tokens_seen": 1665859584
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.01,
|
| 958 |
+
"learning_rate": 9.682539682539682e-05,
|
| 959 |
+
"loss": 2.61,
|
| 960 |
+
"theoretical_loss": 3.4840140237976636,
|
| 961 |
+
"tokens_seen": 1665990656
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.01,
|
| 965 |
+
"learning_rate": 9.761904761904762e-05,
|
| 966 |
+
"loss": 2.4506,
|
| 967 |
+
"theoretical_loss": 3.483990341168467,
|
| 968 |
+
"tokens_seen": 1666121728
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.01,
|
| 972 |
+
"learning_rate": 9.841269841269841e-05,
|
| 973 |
+
"loss": 2.4311,
|
| 974 |
+
"theoretical_loss": 3.483966660923902,
|
| 975 |
+
"tokens_seen": 1666252800
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.01,
|
| 979 |
+
"objective/train/docs_used": 919806,
|
| 980 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 981 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 982 |
+
"objective/train/original_loss": 2.3898022174835205,
|
| 983 |
+
"objective/train/theoretical_loss": 3.4839429830635407,
|
| 984 |
+
"objective/train/tokens_used": 36842976,
|
| 985 |
+
"theoretical_loss": 3.4839429830635407,
|
| 986 |
+
"tokens_seen": 1666383872
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 0.01,
|
| 990 |
+
"learning_rate": 9.920634920634922e-05,
|
| 991 |
+
"loss": 2.543,
|
| 992 |
+
"theoretical_loss": 3.4839429830635407,
|
| 993 |
+
"tokens_seen": 1666383872
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 0.01,
|
| 997 |
+
"learning_rate": 0.0001,
|
| 998 |
+
"loss": 2.4395,
|
| 999 |
+
"theoretical_loss": 3.4839193075869543,
|
| 1000 |
+
"tokens_seen": 1666514944
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 0.01,
|
| 1004 |
+
"learning_rate": 9.999197560584176e-05,
|
| 1005 |
+
"loss": 2.4916,
|
| 1006 |
+
"theoretical_loss": 3.4838956344937175,
|
| 1007 |
+
"tokens_seen": 1666646016
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 0.01,
|
| 1011 |
+
"learning_rate": 9.998395121168352e-05,
|
| 1012 |
+
"loss": 2.3888,
|
| 1013 |
+
"theoretical_loss": 3.4838719637834012,
|
| 1014 |
+
"tokens_seen": 1666777088
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 0.01,
|
| 1018 |
+
"learning_rate": 9.997592681752528e-05,
|
| 1019 |
+
"loss": 2.5063,
|
| 1020 |
+
"theoretical_loss": 3.483848295455579,
|
| 1021 |
+
"tokens_seen": 1666908160
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 0.01,
|
| 1025 |
+
"learning_rate": 9.996790242336704e-05,
|
| 1026 |
+
"loss": 2.4951,
|
| 1027 |
+
"theoretical_loss": 3.483824629509824,
|
| 1028 |
+
"tokens_seen": 1667039232
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 0.01,
|
| 1032 |
+
"learning_rate": 9.99598780292088e-05,
|
| 1033 |
+
"loss": 2.4226,
|
| 1034 |
+
"theoretical_loss": 3.4838009659457088,
|
| 1035 |
+
"tokens_seen": 1667170304
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.01,
|
| 1039 |
+
"learning_rate": 9.995185363505056e-05,
|
| 1040 |
+
"loss": 2.4431,
|
| 1041 |
+
"theoretical_loss": 3.4837773047628064,
|
| 1042 |
+
"tokens_seen": 1667301376
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 0.01,
|
| 1046 |
+
"learning_rate": 9.994382924089232e-05,
|
| 1047 |
+
"loss": 2.4434,
|
| 1048 |
+
"theoretical_loss": 3.4837536459606904,
|
| 1049 |
+
"tokens_seen": 1667432448
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 0.01,
|
| 1053 |
+
"learning_rate": 9.993580484673407e-05,
|
| 1054 |
+
"loss": 2.5021,
|
| 1055 |
+
"theoretical_loss": 3.4837299895389333,
|
| 1056 |
+
"tokens_seen": 1667563520
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 0.01,
|
| 1060 |
+
"learning_rate": 9.992778045257584e-05,
|
| 1061 |
+
"loss": 2.5622,
|
| 1062 |
+
"theoretical_loss": 3.48370633549711,
|
| 1063 |
+
"tokens_seen": 1667694592
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 0.01,
|
| 1067 |
+
"learning_rate": 9.991975605841759e-05,
|
| 1068 |
+
"loss": 2.524,
|
| 1069 |
+
"theoretical_loss": 3.4836826838347923,
|
| 1070 |
+
"tokens_seen": 1667825664
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 0.01,
|
| 1074 |
+
"learning_rate": 9.991173166425936e-05,
|
| 1075 |
+
"loss": 2.5055,
|
| 1076 |
+
"theoretical_loss": 3.483659034551555,
|
| 1077 |
+
"tokens_seen": 1667956736
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 0.01,
|
| 1081 |
+
"objective/train/docs_used": 921005,
|
| 1082 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 1083 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 1084 |
+
"objective/train/original_loss": 2.6571173667907715,
|
| 1085 |
+
"objective/train/theoretical_loss": 3.4836472108019585,
|
| 1086 |
+
"objective/train/tokens_used": 38481376,
|
| 1087 |
+
"theoretical_loss": 3.4836472108019585,
|
| 1088 |
+
"tokens_seen": 1668022272
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.01,
|
| 1092 |
+
"learning_rate": 9.990370727010111e-05,
|
| 1093 |
+
"loss": 2.5956,
|
| 1094 |
+
"theoretical_loss": 3.483635387646972,
|
| 1095 |
+
"tokens_seen": 1668087808
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.01,
|
| 1099 |
+
"learning_rate": 9.989568287594288e-05,
|
| 1100 |
+
"loss": 2.5279,
|
| 1101 |
+
"theoretical_loss": 3.4836117431206164,
|
| 1102 |
+
"tokens_seen": 1668218880
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.01,
|
| 1106 |
+
"learning_rate": 9.988765848178463e-05,
|
| 1107 |
+
"loss": 2.45,
|
| 1108 |
+
"theoretical_loss": 3.483588100972063,
|
| 1109 |
+
"tokens_seen": 1668349952
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.01,
|
| 1113 |
+
"learning_rate": 9.987963408762638e-05,
|
| 1114 |
+
"loss": 2.5056,
|
| 1115 |
+
"theoretical_loss": 3.483564461200885,
|
| 1116 |
+
"tokens_seen": 1668481024
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.01,
|
| 1120 |
+
"learning_rate": 9.987160969346815e-05,
|
| 1121 |
+
"loss": 2.56,
|
| 1122 |
+
"theoretical_loss": 3.4835408238066567,
|
| 1123 |
+
"tokens_seen": 1668612096
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.01,
|
| 1127 |
+
"learning_rate": 9.98635852993099e-05,
|
| 1128 |
+
"loss": 2.4673,
|
| 1129 |
+
"theoretical_loss": 3.4835171887889533,
|
| 1130 |
+
"tokens_seen": 1668743168
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.01,
|
| 1134 |
+
"learning_rate": 9.985556090515167e-05,
|
| 1135 |
+
"loss": 2.3887,
|
| 1136 |
+
"theoretical_loss": 3.483493556147349,
|
| 1137 |
+
"tokens_seen": 1668874240
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.01,
|
| 1141 |
+
"learning_rate": 9.984753651099342e-05,
|
| 1142 |
+
"loss": 2.478,
|
| 1143 |
+
"theoretical_loss": 3.4834699258814172,
|
| 1144 |
+
"tokens_seen": 1669005312
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.01,
|
| 1148 |
+
"learning_rate": 9.983951211683519e-05,
|
| 1149 |
+
"loss": 2.6136,
|
| 1150 |
+
"theoretical_loss": 3.483446297990734,
|
| 1151 |
+
"tokens_seen": 1669136384
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.01,
|
| 1155 |
+
"learning_rate": 9.983148772267694e-05,
|
| 1156 |
+
"loss": 2.5876,
|
| 1157 |
+
"theoretical_loss": 3.4834226724748736,
|
| 1158 |
+
"tokens_seen": 1669267456
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.01,
|
| 1162 |
+
"learning_rate": 9.982346332851871e-05,
|
| 1163 |
+
"loss": 2.5149,
|
| 1164 |
+
"theoretical_loss": 3.4833990493334106,
|
| 1165 |
+
"tokens_seen": 1669398528
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.01,
|
| 1169 |
+
"learning_rate": 9.981543893436046e-05,
|
| 1170 |
+
"loss": 2.5755,
|
| 1171 |
+
"theoretical_loss": 3.48337542856592,
|
| 1172 |
+
"tokens_seen": 1669529600
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.01,
|
| 1176 |
+
"objective/train/docs_used": 921680,
|
| 1177 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 1178 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 1179 |
+
"objective/train/original_loss": 2.329754590988159,
|
| 1180 |
+
"objective/train/theoretical_loss": 3.4833518101719774,
|
| 1181 |
+
"objective/train/tokens_used": 40119776,
|
| 1182 |
+
"theoretical_loss": 3.4833518101719774,
|
| 1183 |
+
"tokens_seen": 1669660672
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 0.01,
|
| 1187 |
+
"learning_rate": 9.980741454020222e-05,
|
| 1188 |
+
"loss": 2.4671,
|
| 1189 |
+
"theoretical_loss": 3.4833518101719774,
|
| 1190 |
+
"tokens_seen": 1669660672
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 0.01,
|
| 1194 |
+
"learning_rate": 9.979939014604398e-05,
|
| 1195 |
+
"loss": 2.3942,
|
| 1196 |
+
"theoretical_loss": 3.4833281941511576,
|
| 1197 |
+
"tokens_seen": 1669791744
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 0.01,
|
| 1201 |
+
"learning_rate": 9.979136575188574e-05,
|
| 1202 |
+
"loss": 2.4857,
|
| 1203 |
+
"theoretical_loss": 3.4833045805030363,
|
| 1204 |
+
"tokens_seen": 1669922816
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 0.01,
|
| 1208 |
+
"learning_rate": 9.97833413577275e-05,
|
| 1209 |
+
"loss": 2.4502,
|
| 1210 |
+
"theoretical_loss": 3.483280969227188,
|
| 1211 |
+
"tokens_seen": 1670053888
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 0.01,
|
| 1215 |
+
"learning_rate": 9.977531696356926e-05,
|
| 1216 |
+
"loss": 2.5831,
|
| 1217 |
+
"theoretical_loss": 3.4832573603231887,
|
| 1218 |
+
"tokens_seen": 1670184960
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 0.01,
|
| 1222 |
+
"learning_rate": 9.976729256941102e-05,
|
| 1223 |
+
"loss": 2.561,
|
| 1224 |
+
"theoretical_loss": 3.4832337537906146,
|
| 1225 |
+
"tokens_seen": 1670316032
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 0.01,
|
| 1229 |
+
"learning_rate": 9.975926817525277e-05,
|
| 1230 |
+
"loss": 2.5869,
|
| 1231 |
+
"theoretical_loss": 3.4832101496290404,
|
| 1232 |
+
"tokens_seen": 1670447104
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 0.01,
|
| 1236 |
+
"learning_rate": 9.975124378109453e-05,
|
| 1237 |
+
"loss": 2.4206,
|
| 1238 |
+
"theoretical_loss": 3.4831865478380433,
|
| 1239 |
+
"tokens_seen": 1670578176
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 0.01,
|
| 1243 |
+
"learning_rate": 9.97432193869363e-05,
|
| 1244 |
+
"loss": 2.3991,
|
| 1245 |
+
"theoretical_loss": 3.4831629484171978,
|
| 1246 |
+
"tokens_seen": 1670709248
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 0.01,
|
| 1250 |
+
"learning_rate": 9.973519499277805e-05,
|
| 1251 |
+
"loss": 2.3821,
|
| 1252 |
+
"theoretical_loss": 3.4831393513660807,
|
| 1253 |
+
"tokens_seen": 1670840320
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 0.01,
|
| 1257 |
+
"learning_rate": 9.972717059861981e-05,
|
| 1258 |
+
"loss": 2.5258,
|
| 1259 |
+
"theoretical_loss": 3.483115756684268,
|
| 1260 |
+
"tokens_seen": 1670971392
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 0.01,
|
| 1264 |
+
"learning_rate": 9.971914620446157e-05,
|
| 1265 |
+
"loss": 2.4604,
|
| 1266 |
+
"theoretical_loss": 3.4830921643713366,
|
| 1267 |
+
"tokens_seen": 1671102464
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 0.01,
|
| 1271 |
+
"learning_rate": 9.971112181030333e-05,
|
| 1272 |
+
"loss": 2.5027,
|
| 1273 |
+
"theoretical_loss": 3.483068574426862,
|
| 1274 |
+
"tokens_seen": 1671233536
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 0.01,
|
| 1278 |
+
"objective/train/docs_used": 922598,
|
| 1279 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 1280 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 1281 |
+
"objective/train/original_loss": 2.674171209335327,
|
| 1282 |
+
"objective/train/theoretical_loss": 3.4830567803426637,
|
| 1283 |
+
"objective/train/tokens_used": 41758176,
|
| 1284 |
+
"theoretical_loss": 3.4830567803426637,
|
| 1285 |
+
"tokens_seen": 1671299072
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 0.01,
|
| 1289 |
+
"learning_rate": 9.970309741614509e-05,
|
| 1290 |
+
"loss": 2.5194,
|
| 1291 |
+
"theoretical_loss": 3.483044986850421,
|
| 1292 |
+
"tokens_seen": 1671364608
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 0.01,
|
| 1296 |
+
"learning_rate": 9.969507302198684e-05,
|
| 1297 |
+
"loss": 2.4984,
|
| 1298 |
+
"theoretical_loss": 3.48302140164159,
|
| 1299 |
+
"tokens_seen": 1671495680
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 0.01,
|
| 1303 |
+
"learning_rate": 9.968704862782861e-05,
|
| 1304 |
+
"loss": 2.6113,
|
| 1305 |
+
"theoretical_loss": 3.482997818799947,
|
| 1306 |
+
"tokens_seen": 1671626752
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 0.01,
|
| 1310 |
+
"learning_rate": 9.967902423367036e-05,
|
| 1311 |
+
"loss": 2.6013,
|
| 1312 |
+
"theoretical_loss": 3.4829742383250673,
|
| 1313 |
+
"tokens_seen": 1671757824
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 0.01,
|
| 1317 |
+
"learning_rate": 9.967099983951213e-05,
|
| 1318 |
+
"loss": 2.4007,
|
| 1319 |
+
"theoretical_loss": 3.4829506602165283,
|
| 1320 |
+
"tokens_seen": 1671888896
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 0.01,
|
| 1324 |
+
"learning_rate": 9.966297544535388e-05,
|
| 1325 |
+
"loss": 2.4473,
|
| 1326 |
+
"theoretical_loss": 3.482927084473907,
|
| 1327 |
+
"tokens_seen": 1672019968
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 0.01,
|
| 1331 |
+
"learning_rate": 9.965495105119565e-05,
|
| 1332 |
+
"loss": 2.3941,
|
| 1333 |
+
"theoretical_loss": 3.482903511096781,
|
| 1334 |
+
"tokens_seen": 1672151040
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 0.01,
|
| 1338 |
+
"learning_rate": 9.96469266570374e-05,
|
| 1339 |
+
"loss": 2.5564,
|
| 1340 |
+
"theoretical_loss": 3.482879940084727,
|
| 1341 |
+
"tokens_seen": 1672282112
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 0.01,
|
| 1345 |
+
"learning_rate": 9.963890226287915e-05,
|
| 1346 |
+
"loss": 2.4979,
|
| 1347 |
+
"theoretical_loss": 3.4828563714373226,
|
| 1348 |
+
"tokens_seen": 1672413184
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 0.01,
|
| 1352 |
+
"learning_rate": 9.963087786872092e-05,
|
| 1353 |
+
"loss": 2.4506,
|
| 1354 |
+
"theoretical_loss": 3.4828328051541453,
|
| 1355 |
+
"tokens_seen": 1672544256
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 0.01,
|
| 1359 |
+
"learning_rate": 9.962285347456267e-05,
|
| 1360 |
+
"loss": 2.5131,
|
| 1361 |
+
"theoretical_loss": 3.482809241234773,
|
| 1362 |
+
"tokens_seen": 1672675328
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 0.01,
|
| 1366 |
+
"learning_rate": 9.961482908040444e-05,
|
| 1367 |
+
"loss": 2.4079,
|
| 1368 |
+
"theoretical_loss": 3.482785679678783,
|
| 1369 |
+
"tokens_seen": 1672806400
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 0.01,
|
| 1373 |
+
"objective/train/docs_used": 923236,
|
| 1374 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 1375 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 1376 |
+
"objective/train/original_loss": 2.478933095932007,
|
| 1377 |
+
"objective/train/theoretical_loss": 3.482762120485753,
|
| 1378 |
+
"objective/train/tokens_used": 43396576,
|
| 1379 |
+
"theoretical_loss": 3.482762120485753,
|
| 1380 |
+
"tokens_seen": 1672937472
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 0.01,
|
| 1384 |
+
"learning_rate": 9.960680468624619e-05,
|
| 1385 |
+
"loss": 2.5005,
|
| 1386 |
+
"theoretical_loss": 3.482762120485753,
|
| 1387 |
+
"tokens_seen": 1672937472
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 0.01,
|
| 1391 |
+
"learning_rate": 9.959878029208796e-05,
|
| 1392 |
+
"loss": 2.669,
|
| 1393 |
+
"theoretical_loss": 3.482738563655261,
|
| 1394 |
+
"tokens_seen": 1673068544
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 0.01,
|
| 1398 |
+
"learning_rate": 9.959075589792971e-05,
|
| 1399 |
+
"loss": 2.5706,
|
| 1400 |
+
"theoretical_loss": 3.4827150091868853,
|
| 1401 |
+
"tokens_seen": 1673199616
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 0.01,
|
| 1405 |
+
"learning_rate": 9.958273150377147e-05,
|
| 1406 |
+
"loss": 2.5295,
|
| 1407 |
+
"theoretical_loss": 3.482691457080204,
|
| 1408 |
+
"tokens_seen": 1673330688
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 0.01,
|
| 1412 |
+
"learning_rate": 9.957470710961323e-05,
|
| 1413 |
+
"loss": 2.4358,
|
| 1414 |
+
"theoretical_loss": 3.482667907334795,
|
| 1415 |
+
"tokens_seen": 1673461760
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 0.01,
|
| 1419 |
+
"learning_rate": 9.956668271545499e-05,
|
| 1420 |
+
"loss": 2.4467,
|
| 1421 |
+
"theoretical_loss": 3.482644359950237,
|
| 1422 |
+
"tokens_seen": 1673592832
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"epoch": 0.01,
|
| 1426 |
+
"learning_rate": 9.955865832129675e-05,
|
| 1427 |
+
"loss": 2.3988,
|
| 1428 |
+
"theoretical_loss": 3.4826208149261078,
|
| 1429 |
+
"tokens_seen": 1673723904
|
| 1430 |
+
},
|
| 1431 |
+
{
|
| 1432 |
+
"epoch": 0.01,
|
| 1433 |
+
"learning_rate": 9.95506339271385e-05,
|
| 1434 |
+
"loss": 2.521,
|
| 1435 |
+
"theoretical_loss": 3.482597272261987,
|
| 1436 |
+
"tokens_seen": 1673854976
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 0.01,
|
| 1440 |
+
"learning_rate": 9.954260953298027e-05,
|
| 1441 |
+
"loss": 2.409,
|
| 1442 |
+
"theoretical_loss": 3.4825737319574523,
|
| 1443 |
+
"tokens_seen": 1673986048
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 0.01,
|
| 1447 |
+
"learning_rate": 9.953458513882203e-05,
|
| 1448 |
+
"loss": 2.5548,
|
| 1449 |
+
"theoretical_loss": 3.4825501940120835,
|
| 1450 |
+
"tokens_seen": 1674117120
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 0.01,
|
| 1454 |
+
"learning_rate": 9.952656074466378e-05,
|
| 1455 |
+
"loss": 2.4541,
|
| 1456 |
+
"theoretical_loss": 3.4825266584254586,
|
| 1457 |
+
"tokens_seen": 1674248192
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 0.01,
|
| 1461 |
+
"learning_rate": 9.951853635050554e-05,
|
| 1462 |
+
"loss": 2.5549,
|
| 1463 |
+
"theoretical_loss": 3.482503125197157,
|
| 1464 |
+
"tokens_seen": 1674379264
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 0.01,
|
| 1468 |
+
"learning_rate": 9.95105119563473e-05,
|
| 1469 |
+
"loss": 2.4687,
|
| 1470 |
+
"theoretical_loss": 3.4824795943267577,
|
| 1471 |
+
"tokens_seen": 1674510336
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 0.01,
|
| 1475 |
+
"objective/train/docs_used": 924425,
|
| 1476 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 1477 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 1478 |
+
"objective/train/original_loss": 2.032245397567749,
|
| 1479 |
+
"objective/train/theoretical_loss": 3.48246782977564,
|
| 1480 |
+
"objective/train/tokens_used": 45034976,
|
| 1481 |
+
"theoretical_loss": 3.48246782977564,
|
| 1482 |
+
"tokens_seen": 1674575872
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 0.01,
|
| 1486 |
+
"learning_rate": 9.950248756218906e-05,
|
| 1487 |
+
"loss": 2.4781,
|
| 1488 |
+
"theoretical_loss": 3.4824560658138397,
|
| 1489 |
+
"tokens_seen": 1674641408
|
| 1490 |
+
},
|
| 1491 |
+
{
|
| 1492 |
+
"epoch": 0.02,
|
| 1493 |
+
"learning_rate": 9.949446316803082e-05,
|
| 1494 |
+
"loss": 2.6007,
|
| 1495 |
+
"theoretical_loss": 3.482432539657983,
|
| 1496 |
+
"tokens_seen": 1674772480
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 0.02,
|
| 1500 |
+
"learning_rate": 9.948643877387258e-05,
|
| 1501 |
+
"loss": 2.4198,
|
| 1502 |
+
"theoretical_loss": 3.4824090158587664,
|
| 1503 |
+
"tokens_seen": 1674903552
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 0.02,
|
| 1507 |
+
"learning_rate": 9.947841437971434e-05,
|
| 1508 |
+
"loss": 2.49,
|
| 1509 |
+
"theoretical_loss": 3.4823854944157695,
|
| 1510 |
+
"tokens_seen": 1675034624
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"epoch": 0.02,
|
| 1514 |
+
"learning_rate": 9.94703899855561e-05,
|
| 1515 |
+
"loss": 2.4733,
|
| 1516 |
+
"theoretical_loss": 3.482361975328572,
|
| 1517 |
+
"tokens_seen": 1675165696
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 0.02,
|
| 1521 |
+
"learning_rate": 9.946236559139786e-05,
|
| 1522 |
+
"loss": 2.6164,
|
| 1523 |
+
"theoretical_loss": 3.482338458596754,
|
| 1524 |
+
"tokens_seen": 1675296768
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 0.02,
|
| 1528 |
+
"learning_rate": 9.945434119723961e-05,
|
| 1529 |
+
"loss": 2.4729,
|
| 1530 |
+
"theoretical_loss": 3.482314944219895,
|
| 1531 |
+
"tokens_seen": 1675427840
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 0.02,
|
| 1535 |
+
"learning_rate": 9.944631680308138e-05,
|
| 1536 |
+
"loss": 2.5106,
|
| 1537 |
+
"theoretical_loss": 3.482291432197575,
|
| 1538 |
+
"tokens_seen": 1675558912
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 0.02,
|
| 1542 |
+
"learning_rate": 9.943829240892313e-05,
|
| 1543 |
+
"loss": 2.4255,
|
| 1544 |
+
"theoretical_loss": 3.482267922529374,
|
| 1545 |
+
"tokens_seen": 1675689984
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 0.02,
|
| 1549 |
+
"learning_rate": 9.94302680147649e-05,
|
| 1550 |
+
"loss": 2.4172,
|
| 1551 |
+
"theoretical_loss": 3.482244415214873,
|
| 1552 |
+
"tokens_seen": 1675821056
|
| 1553 |
+
},
|
| 1554 |
+
{
|
| 1555 |
+
"epoch": 0.02,
|
| 1556 |
+
"learning_rate": 9.942224362060665e-05,
|
| 1557 |
+
"loss": 2.4485,
|
| 1558 |
+
"theoretical_loss": 3.482220910253651,
|
| 1559 |
+
"tokens_seen": 1675952128
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 0.02,
|
| 1563 |
+
"learning_rate": 9.941421922644842e-05,
|
| 1564 |
+
"loss": 2.5783,
|
| 1565 |
+
"theoretical_loss": 3.482197407645289,
|
| 1566 |
+
"tokens_seen": 1676083200
|
| 1567 |
+
},
|
| 1568 |
+
{
|
| 1569 |
+
"epoch": 0.02,
|
| 1570 |
+
"objective/train/docs_used": 924948,
|
| 1571 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 1572 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 1573 |
+
"objective/train/original_loss": 2.1431517601013184,
|
| 1574 |
+
"objective/train/theoretical_loss": 3.4821739073893676,
|
| 1575 |
+
"objective/train/tokens_used": 46673376,
|
| 1576 |
+
"theoretical_loss": 3.4821739073893676,
|
| 1577 |
+
"tokens_seen": 1676214272
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.02,
|
| 1581 |
+
"learning_rate": 9.940619483229017e-05,
|
| 1582 |
+
"loss": 2.4842,
|
| 1583 |
+
"theoretical_loss": 3.4821739073893676,
|
| 1584 |
+
"tokens_seen": 1676214272
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.02,
|
| 1588 |
+
"learning_rate": 9.939817043813192e-05,
|
| 1589 |
+
"loss": 2.5048,
|
| 1590 |
+
"theoretical_loss": 3.482150409485467,
|
| 1591 |
+
"tokens_seen": 1676345344
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.02,
|
| 1595 |
+
"learning_rate": 9.939014604397369e-05,
|
| 1596 |
+
"loss": 2.4242,
|
| 1597 |
+
"theoretical_loss": 3.482126913933169,
|
| 1598 |
+
"tokens_seen": 1676476416
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.02,
|
| 1602 |
+
"learning_rate": 9.938212164981544e-05,
|
| 1603 |
+
"loss": 2.4716,
|
| 1604 |
+
"theoretical_loss": 3.482103420732053,
|
| 1605 |
+
"tokens_seen": 1676607488
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.02,
|
| 1609 |
+
"learning_rate": 9.937409725565721e-05,
|
| 1610 |
+
"loss": 2.4006,
|
| 1611 |
+
"theoretical_loss": 3.482079929881701,
|
| 1612 |
+
"tokens_seen": 1676738560
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.02,
|
| 1616 |
+
"learning_rate": 9.936607286149896e-05,
|
| 1617 |
+
"loss": 2.5438,
|
| 1618 |
+
"theoretical_loss": 3.482056441381694,
|
| 1619 |
+
"tokens_seen": 1676869632
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.02,
|
| 1623 |
+
"learning_rate": 9.935804846734073e-05,
|
| 1624 |
+
"loss": 2.4948,
|
| 1625 |
+
"theoretical_loss": 3.4820329552316123,
|
| 1626 |
+
"tokens_seen": 1677000704
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.02,
|
| 1630 |
+
"learning_rate": 9.935002407318248e-05,
|
| 1631 |
+
"loss": 2.4135,
|
| 1632 |
+
"theoretical_loss": 3.482009471431038,
|
| 1633 |
+
"tokens_seen": 1677131776
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.02,
|
| 1637 |
+
"learning_rate": 9.934199967902424e-05,
|
| 1638 |
+
"loss": 2.4302,
|
| 1639 |
+
"theoretical_loss": 3.4819859899795516,
|
| 1640 |
+
"tokens_seen": 1677262848
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.02,
|
| 1644 |
+
"learning_rate": 9.9333975284866e-05,
|
| 1645 |
+
"loss": 2.4168,
|
| 1646 |
+
"theoretical_loss": 3.481962510876736,
|
| 1647 |
+
"tokens_seen": 1677393920
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.02,
|
| 1651 |
+
"learning_rate": 9.932595089070776e-05,
|
| 1652 |
+
"loss": 2.648,
|
| 1653 |
+
"theoretical_loss": 3.481939034122171,
|
| 1654 |
+
"tokens_seen": 1677524992
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.02,
|
| 1658 |
+
"learning_rate": 9.931792649654952e-05,
|
| 1659 |
+
"loss": 2.4332,
|
| 1660 |
+
"theoretical_loss": 3.4819155597154396,
|
| 1661 |
+
"tokens_seen": 1677656064
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.02,
|
| 1665 |
+
"learning_rate": 9.930990210239128e-05,
|
| 1666 |
+
"loss": 2.4625,
|
| 1667 |
+
"theoretical_loss": 3.4818920876561235,
|
| 1668 |
+
"tokens_seen": 1677787136
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.02,
|
| 1672 |
+
"objective/train/docs_used": 926165,
|
| 1673 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 1674 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 1675 |
+
"objective/train/original_loss": 2.494450569152832,
|
| 1676 |
+
"objective/train/theoretical_loss": 3.4818803525066153,
|
| 1677 |
+
"objective/train/tokens_used": 48311776,
|
| 1678 |
+
"theoretical_loss": 3.4818803525066153,
|
| 1679 |
+
"tokens_seen": 1677852672
|
| 1680 |
+
},
|
| 1681 |
+
{
|
| 1682 |
+
"epoch": 0.02,
|
| 1683 |
+
"learning_rate": 9.930187770823304e-05,
|
| 1684 |
+
"loss": 2.4562,
|
| 1685 |
+
"theoretical_loss": 3.481868617943804,
|
| 1686 |
+
"tokens_seen": 1677918208
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 0.02,
|
| 1690 |
+
"learning_rate": 9.92938533140748e-05,
|
| 1691 |
+
"loss": 2.4934,
|
| 1692 |
+
"theoretical_loss": 3.481845150578063,
|
| 1693 |
+
"tokens_seen": 1678049280
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 0.02,
|
| 1697 |
+
"learning_rate": 9.928582891991655e-05,
|
| 1698 |
+
"loss": 2.4625,
|
| 1699 |
+
"theoretical_loss": 3.481821685558484,
|
| 1700 |
+
"tokens_seen": 1678180352
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 0.02,
|
| 1704 |
+
"learning_rate": 9.927780452575832e-05,
|
| 1705 |
+
"loss": 2.3664,
|
| 1706 |
+
"theoretical_loss": 3.4817982228846476,
|
| 1707 |
+
"tokens_seen": 1678311424
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 0.02,
|
| 1711 |
+
"learning_rate": 9.926978013160007e-05,
|
| 1712 |
+
"loss": 2.4554,
|
| 1713 |
+
"theoretical_loss": 3.481774762556137,
|
| 1714 |
+
"tokens_seen": 1678442496
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 0.02,
|
| 1718 |
+
"learning_rate": 9.926175573744183e-05,
|
| 1719 |
+
"loss": 2.6398,
|
| 1720 |
+
"theoretical_loss": 3.4817513045725343,
|
| 1721 |
+
"tokens_seen": 1678573568
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 0.02,
|
| 1725 |
+
"learning_rate": 9.925373134328359e-05,
|
| 1726 |
+
"loss": 2.3632,
|
| 1727 |
+
"theoretical_loss": 3.4817278489334225,
|
| 1728 |
+
"tokens_seen": 1678704640
|
| 1729 |
+
},
|
| 1730 |
+
{
|
| 1731 |
+
"epoch": 0.02,
|
| 1732 |
+
"learning_rate": 9.924570694912535e-05,
|
| 1733 |
+
"loss": 2.6002,
|
| 1734 |
+
"theoretical_loss": 3.481704395638383,
|
| 1735 |
+
"tokens_seen": 1678835712
|
| 1736 |
+
},
|
| 1737 |
+
{
|
| 1738 |
+
"epoch": 0.02,
|
| 1739 |
+
"learning_rate": 9.923768255496711e-05,
|
| 1740 |
+
"loss": 2.5935,
|
| 1741 |
+
"theoretical_loss": 3.4816809446870005,
|
| 1742 |
+
"tokens_seen": 1678966784
|
| 1743 |
+
},
|
| 1744 |
+
{
|
| 1745 |
+
"epoch": 0.02,
|
| 1746 |
+
"learning_rate": 9.922965816080886e-05,
|
| 1747 |
+
"loss": 2.6889,
|
| 1748 |
+
"theoretical_loss": 3.4816574960788564,
|
| 1749 |
+
"tokens_seen": 1679097856
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 0.02,
|
| 1753 |
+
"learning_rate": 9.922163376665063e-05,
|
| 1754 |
+
"loss": 2.2718,
|
| 1755 |
+
"theoretical_loss": 3.4816340498135343,
|
| 1756 |
+
"tokens_seen": 1679228928
|
| 1757 |
+
},
|
| 1758 |
+
{
|
| 1759 |
+
"epoch": 0.02,
|
| 1760 |
+
"learning_rate": 9.921360937249238e-05,
|
| 1761 |
+
"loss": 2.4179,
|
| 1762 |
+
"theoretical_loss": 3.4816106058906175,
|
| 1763 |
+
"tokens_seen": 1679360000
|
| 1764 |
+
},
|
| 1765 |
+
{
|
| 1766 |
+
"epoch": 0.02,
|
| 1767 |
+
"objective/train/docs_used": 926923,
|
| 1768 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 1769 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 1770 |
+
"objective/train/original_loss": 2.7133426666259766,
|
| 1771 |
+
"objective/train/theoretical_loss": 3.481587164309688,
|
| 1772 |
+
"objective/train/tokens_used": 49950176,
|
| 1773 |
+
"theoretical_loss": 3.481587164309688,
|
| 1774 |
+
"tokens_seen": 1679491072
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 0.02,
|
| 1778 |
+
"learning_rate": 9.920558497833415e-05,
|
| 1779 |
+
"loss": 2.4835,
|
| 1780 |
+
"theoretical_loss": 3.481587164309688,
|
| 1781 |
+
"tokens_seen": 1679491072
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 0.02,
|
| 1785 |
+
"learning_rate": 9.91975605841759e-05,
|
| 1786 |
+
"loss": 2.5025,
|
| 1787 |
+
"theoretical_loss": 3.4815637250703304,
|
| 1788 |
+
"tokens_seen": 1679622144
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 0.02,
|
| 1792 |
+
"learning_rate": 9.918953619001767e-05,
|
| 1793 |
+
"loss": 2.4519,
|
| 1794 |
+
"theoretical_loss": 3.4815402881721274,
|
| 1795 |
+
"tokens_seen": 1679753216
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.02,
|
| 1799 |
+
"learning_rate": 9.918151179585942e-05,
|
| 1800 |
+
"loss": 2.5021,
|
| 1801 |
+
"theoretical_loss": 3.4815168536146626,
|
| 1802 |
+
"tokens_seen": 1679884288
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.02,
|
| 1806 |
+
"learning_rate": 9.917348740170119e-05,
|
| 1807 |
+
"loss": 2.4785,
|
| 1808 |
+
"theoretical_loss": 3.48149342139752,
|
| 1809 |
+
"tokens_seen": 1680015360
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.02,
|
| 1813 |
+
"learning_rate": 9.916546300754294e-05,
|
| 1814 |
+
"loss": 2.5138,
|
| 1815 |
+
"theoretical_loss": 3.481469991520283,
|
| 1816 |
+
"tokens_seen": 1680146432
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.02,
|
| 1820 |
+
"learning_rate": 9.91574386133847e-05,
|
| 1821 |
+
"loss": 2.4019,
|
| 1822 |
+
"theoretical_loss": 3.4814465639825354,
|
| 1823 |
+
"tokens_seen": 1680277504
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 0.02,
|
| 1827 |
+
"learning_rate": 9.914941421922646e-05,
|
| 1828 |
+
"loss": 2.5178,
|
| 1829 |
+
"theoretical_loss": 3.481423138783861,
|
| 1830 |
+
"tokens_seen": 1680408576
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 0.02,
|
| 1834 |
+
"learning_rate": 9.914138982506821e-05,
|
| 1835 |
+
"loss": 2.4615,
|
| 1836 |
+
"theoretical_loss": 3.4813997159238443,
|
| 1837 |
+
"tokens_seen": 1680539648
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 0.02,
|
| 1841 |
+
"learning_rate": 9.913336543090998e-05,
|
| 1842 |
+
"loss": 2.533,
|
| 1843 |
+
"theoretical_loss": 3.481376295402069,
|
| 1844 |
+
"tokens_seen": 1680670720
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 0.02,
|
| 1848 |
+
"learning_rate": 9.912534103675173e-05,
|
| 1849 |
+
"loss": 2.5408,
|
| 1850 |
+
"theoretical_loss": 3.4813528772181193,
|
| 1851 |
+
"tokens_seen": 1680801792
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 0.02,
|
| 1855 |
+
"learning_rate": 9.91173166425935e-05,
|
| 1856 |
+
"loss": 2.4864,
|
| 1857 |
+
"theoretical_loss": 3.4813294613715797,
|
| 1858 |
+
"tokens_seen": 1680932864
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 0.02,
|
| 1862 |
+
"learning_rate": 9.910929224843525e-05,
|
| 1863 |
+
"loss": 2.567,
|
| 1864 |
+
"theoretical_loss": 3.4813060478620352,
|
| 1865 |
+
"tokens_seen": 1681063936
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 0.02,
|
| 1869 |
+
"objective/train/docs_used": 927976,
|
| 1870 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 1871 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 1872 |
+
"objective/train/original_loss": 2.612856864929199,
|
| 1873 |
+
"objective/train/theoretical_loss": 3.4812943419835065,
|
| 1874 |
+
"objective/train/tokens_used": 51588576,
|
| 1875 |
+
"theoretical_loss": 3.4812943419835065,
|
| 1876 |
+
"tokens_seen": 1681129472
|
| 1877 |
+
},
|
| 1878 |
+
{
|
| 1879 |
+
"epoch": 0.02,
|
| 1880 |
+
"learning_rate": 9.9101267854277e-05,
|
| 1881 |
+
"loss": 2.515,
|
| 1882 |
+
"theoretical_loss": 3.48128263668907,
|
| 1883 |
+
"tokens_seen": 1681195008
|
| 1884 |
+
},
|
| 1885 |
+
{
|
| 1886 |
+
"epoch": 0.02,
|
| 1887 |
+
"learning_rate": 9.909324346011877e-05,
|
| 1888 |
+
"loss": 2.5095,
|
| 1889 |
+
"theoretical_loss": 3.4812592278522687,
|
| 1890 |
+
"tokens_seen": 1681326080
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"epoch": 0.02,
|
| 1894 |
+
"learning_rate": 9.908521906596053e-05,
|
| 1895 |
+
"loss": 2.6043,
|
| 1896 |
+
"theoretical_loss": 3.4812358213512162,
|
| 1897 |
+
"tokens_seen": 1681457152
|
| 1898 |
+
},
|
| 1899 |
+
{
|
| 1900 |
+
"epoch": 0.02,
|
| 1901 |
+
"learning_rate": 9.907719467180229e-05,
|
| 1902 |
+
"loss": 2.6276,
|
| 1903 |
+
"theoretical_loss": 3.4812124171854966,
|
| 1904 |
+
"tokens_seen": 1681588224
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 0.02,
|
| 1908 |
+
"learning_rate": 9.906917027764405e-05,
|
| 1909 |
+
"loss": 2.3657,
|
| 1910 |
+
"theoretical_loss": 3.481189015354696,
|
| 1911 |
+
"tokens_seen": 1681719296
|
| 1912 |
+
},
|
| 1913 |
+
{
|
| 1914 |
+
"epoch": 0.02,
|
| 1915 |
+
"learning_rate": 9.906114588348581e-05,
|
| 1916 |
+
"loss": 2.4345,
|
| 1917 |
+
"theoretical_loss": 3.481165615858399,
|
| 1918 |
+
"tokens_seen": 1681850368
|
| 1919 |
+
},
|
| 1920 |
+
{
|
| 1921 |
+
"epoch": 0.02,
|
| 1922 |
+
"learning_rate": 9.905312148932757e-05,
|
| 1923 |
+
"loss": 2.6024,
|
| 1924 |
+
"theoretical_loss": 3.481142218696191,
|
| 1925 |
+
"tokens_seen": 1681981440
|
| 1926 |
+
},
|
| 1927 |
+
{
|
| 1928 |
+
"epoch": 0.02,
|
| 1929 |
+
"learning_rate": 9.904509709516932e-05,
|
| 1930 |
+
"loss": 2.5844,
|
| 1931 |
+
"theoretical_loss": 3.481118823867657,
|
| 1932 |
+
"tokens_seen": 1682112512
|
| 1933 |
+
},
|
| 1934 |
+
{
|
| 1935 |
+
"epoch": 0.02,
|
| 1936 |
+
"learning_rate": 9.903707270101109e-05,
|
| 1937 |
+
"loss": 2.4985,
|
| 1938 |
+
"theoretical_loss": 3.481095431372383,
|
| 1939 |
+
"tokens_seen": 1682243584
|
| 1940 |
+
},
|
| 1941 |
+
{
|
| 1942 |
+
"epoch": 0.02,
|
| 1943 |
+
"learning_rate": 9.902904830685284e-05,
|
| 1944 |
+
"loss": 2.4409,
|
| 1945 |
+
"theoretical_loss": 3.481072041209954,
|
| 1946 |
+
"tokens_seen": 1682374656
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 0.02,
|
| 1950 |
+
"learning_rate": 9.90210239126946e-05,
|
| 1951 |
+
"loss": 2.4786,
|
| 1952 |
+
"theoretical_loss": 3.481048653379955,
|
| 1953 |
+
"tokens_seen": 1682505728
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 0.02,
|
| 1957 |
+
"learning_rate": 9.901299951853636e-05,
|
| 1958 |
+
"loss": 2.4033,
|
| 1959 |
+
"theoretical_loss": 3.4810252678819733,
|
| 1960 |
+
"tokens_seen": 1682636800
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"epoch": 0.02,
|
| 1964 |
+
"objective/train/docs_used": 929273,
|
| 1965 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 1966 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 1967 |
+
"objective/train/original_loss": 2.6835052967071533,
|
| 1968 |
+
"objective/train/theoretical_loss": 3.481001884715594,
|
| 1969 |
+
"objective/train/tokens_used": 53226976,
|
| 1970 |
+
"theoretical_loss": 3.481001884715594,
|
| 1971 |
+
"tokens_seen": 1682767872
|
| 1972 |
+
},
|
| 1973 |
+
{
|
| 1974 |
+
"epoch": 0.02,
|
| 1975 |
+
"learning_rate": 9.900497512437812e-05,
|
| 1976 |
+
"loss": 2.5045,
|
| 1977 |
+
"theoretical_loss": 3.481001884715594,
|
| 1978 |
+
"tokens_seen": 1682767872
|
| 1979 |
+
},
|
| 1980 |
+
{
|
| 1981 |
+
"epoch": 0.02,
|
| 1982 |
+
"learning_rate": 9.899695073021988e-05,
|
| 1983 |
+
"loss": 2.4493,
|
| 1984 |
+
"theoretical_loss": 3.4809785038804026,
|
| 1985 |
+
"tokens_seen": 1682898944
|
| 1986 |
+
}
|
| 1987 |
+
],
|
| 1988 |
+
"max_steps": 12588,
|
| 1989 |
+
"num_train_epochs": 9223372036854775807,
|
| 1990 |
+
"total_flos": 1.6789580808192e+16,
|
| 1991 |
+
"trial_name": null,
|
| 1992 |
+
"trial_params": null
|
| 1993 |
+
}
|
checkpoint-251/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51bec2d3e2d88152dfe0a6734219bf08800b6233ea9aabb72d1cd25d9d6a0463
|
| 3 |
+
size 3375
|
checkpoint-251/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": "tomekkorbak/nervous_wozniak",
|
| 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": "4.24.0",
|
| 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:b02bbc577c8f6f348df77928a160eb8e385a9ed7974d47ab6ff04543cddf4763
|
| 3 |
+
size 510402665
|
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 sha256:51bec2d3e2d88152dfe0a6734219bf08800b6233ea9aabb72d1cd25d9d6a0463
|
| 3 |
+
size 3375
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|