Commit
•
d634acc
1
Parent(s):
7d6ecee
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/cranky_lichterman",
|
| 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 sha256:350fe4f14556edb5946ee5795fd818f8631a2eddb910dd052c4b5186a814ebba
|
| 3 |
+
size 995616113
|
checkpoint-251/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d78be75f82659b11d1b158f6a73b1cce48f4bf7e544d395de4254de03c56532
|
| 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:aed38ce5e44314a4dc9bc63f71a223ec8954abc0739f1cc6fa90c8b2d180ff74
|
| 3 |
+
size 14439
|
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 sha256:519409ca881c840d18b80e5b3dd8633f3a9ef46aa6b661d5185514237da0f40e
|
| 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": 0.10626587637595258,
|
| 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": 4.1666666666666665e-05,
|
| 13 |
+
"loss": 3.0643,
|
| 14 |
+
"theoretical_loss": 3.321567680436603,
|
| 15 |
+
"tokens_seen": 2990538752
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.0,
|
| 19 |
+
"learning_rate": 8.333333333333333e-05,
|
| 20 |
+
"loss": 3.0798,
|
| 21 |
+
"theoretical_loss": 3.3215564803546,
|
| 22 |
+
"tokens_seen": 2990669824
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.0,
|
| 26 |
+
"learning_rate": 0.000125,
|
| 27 |
+
"loss": 2.8688,
|
| 28 |
+
"theoretical_loss": 3.321545280900887,
|
| 29 |
+
"tokens_seen": 2990800896
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.0,
|
| 33 |
+
"learning_rate": 0.00016666666666666666,
|
| 34 |
+
"loss": 2.7194,
|
| 35 |
+
"theoretical_loss": 3.3215340820754022,
|
| 36 |
+
"tokens_seen": 2990931968
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.0,
|
| 40 |
+
"learning_rate": 0.00020833333333333335,
|
| 41 |
+
"loss": 2.6193,
|
| 42 |
+
"theoretical_loss": 3.3215228838780817,
|
| 43 |
+
"tokens_seen": 2991063040
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.0,
|
| 47 |
+
"learning_rate": 0.00025,
|
| 48 |
+
"loss": 2.8571,
|
| 49 |
+
"theoretical_loss": 3.3215116863088636,
|
| 50 |
+
"tokens_seen": 2991194112
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.0,
|
| 54 |
+
"learning_rate": 0.0002916666666666667,
|
| 55 |
+
"loss": 2.7571,
|
| 56 |
+
"theoretical_loss": 3.3215004893676854,
|
| 57 |
+
"tokens_seen": 2991325184
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.0,
|
| 61 |
+
"learning_rate": 0.0003333333333333333,
|
| 62 |
+
"loss": 2.8877,
|
| 63 |
+
"theoretical_loss": 3.321489293054483,
|
| 64 |
+
"tokens_seen": 2991456256
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.0,
|
| 68 |
+
"learning_rate": 0.000375,
|
| 69 |
+
"loss": 2.714,
|
| 70 |
+
"theoretical_loss": 3.321478097369195,
|
| 71 |
+
"tokens_seen": 2991587328
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.0,
|
| 75 |
+
"learning_rate": 0.0004166666666666667,
|
| 76 |
+
"loss": 2.6564,
|
| 77 |
+
"theoretical_loss": 3.321466902311758,
|
| 78 |
+
"tokens_seen": 2991718400
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.0,
|
| 82 |
+
"learning_rate": 0.0004583333333333333,
|
| 83 |
+
"loss": 2.5638,
|
| 84 |
+
"theoretical_loss": 3.3214557078821096,
|
| 85 |
+
"tokens_seen": 2991849472
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.01,
|
| 89 |
+
"learning_rate": 0.0005,
|
| 90 |
+
"loss": 2.4354,
|
| 91 |
+
"theoretical_loss": 3.321444514080187,
|
| 92 |
+
"tokens_seen": 2991980544
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.01,
|
| 96 |
+
"objective/train/docs_used": 1640856,
|
| 97 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 98 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 99 |
+
"objective/train/original_loss": 2.5749809741973877,
|
| 100 |
+
"objective/train/theoretical_loss": 3.321438917414603,
|
| 101 |
+
"objective/train/tokens_used": 22097376,
|
| 102 |
+
"theoretical_loss": 3.321438917414603,
|
| 103 |
+
"tokens_seen": 2992046080
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 0.01,
|
| 107 |
+
"learning_rate": 0.0005416666666666666,
|
| 108 |
+
"loss": 2.5713,
|
| 109 |
+
"theoretical_loss": 3.321433320905927,
|
| 110 |
+
"tokens_seen": 2992111616
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.01,
|
| 114 |
+
"learning_rate": 0.0005833333333333334,
|
| 115 |
+
"loss": 2.4812,
|
| 116 |
+
"theoretical_loss": 3.3214221283592678,
|
| 117 |
+
"tokens_seen": 2992242688
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.01,
|
| 121 |
+
"learning_rate": 0.000625,
|
| 122 |
+
"loss": 2.7622,
|
| 123 |
+
"theoretical_loss": 3.321410936440146,
|
| 124 |
+
"tokens_seen": 2992373760
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.01,
|
| 128 |
+
"learning_rate": 0.0006666666666666666,
|
| 129 |
+
"loss": 2.609,
|
| 130 |
+
"theoretical_loss": 3.3213997451485,
|
| 131 |
+
"tokens_seen": 2992504832
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.01,
|
| 135 |
+
"learning_rate": 0.0007083333333333334,
|
| 136 |
+
"loss": 2.4537,
|
| 137 |
+
"theoretical_loss": 3.3213885544842654,
|
| 138 |
+
"tokens_seen": 2992635904
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.01,
|
| 142 |
+
"learning_rate": 0.00075,
|
| 143 |
+
"loss": 2.4831,
|
| 144 |
+
"theoretical_loss": 3.321377364447381,
|
| 145 |
+
"tokens_seen": 2992766976
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.01,
|
| 149 |
+
"learning_rate": 0.0007916666666666666,
|
| 150 |
+
"loss": 2.5607,
|
| 151 |
+
"theoretical_loss": 3.3213661750377836,
|
| 152 |
+
"tokens_seen": 2992898048
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.01,
|
| 156 |
+
"learning_rate": 0.0008333333333333334,
|
| 157 |
+
"loss": 2.5759,
|
| 158 |
+
"theoretical_loss": 3.3213549862554106,
|
| 159 |
+
"tokens_seen": 2993029120
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.01,
|
| 163 |
+
"learning_rate": 0.000875,
|
| 164 |
+
"loss": 2.3106,
|
| 165 |
+
"theoretical_loss": 3.3213437981001994,
|
| 166 |
+
"tokens_seen": 2993160192
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.01,
|
| 170 |
+
"learning_rate": 0.0009166666666666666,
|
| 171 |
+
"loss": 2.5471,
|
| 172 |
+
"theoretical_loss": 3.3213326105720875,
|
| 173 |
+
"tokens_seen": 2993291264
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.01,
|
| 177 |
+
"learning_rate": 0.0009583333333333334,
|
| 178 |
+
"loss": 2.602,
|
| 179 |
+
"theoretical_loss": 3.3213214236710122,
|
| 180 |
+
"tokens_seen": 2993422336
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.01,
|
| 184 |
+
"learning_rate": 0.001,
|
| 185 |
+
"loss": 2.5877,
|
| 186 |
+
"theoretical_loss": 3.321310237396911,
|
| 187 |
+
"tokens_seen": 2993553408
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.01,
|
| 191 |
+
"objective/train/docs_used": 1641461,
|
| 192 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 193 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 194 |
+
"objective/train/original_loss": 2.557373523712158,
|
| 195 |
+
"objective/train/theoretical_loss": 3.3212990517497207,
|
| 196 |
+
"objective/train/tokens_used": 23735776,
|
| 197 |
+
"theoretical_loss": 3.3212990517497207,
|
| 198 |
+
"tokens_seen": 2993684480
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.01,
|
| 202 |
+
"learning_rate": 0.0009995722840034217,
|
| 203 |
+
"loss": 2.7042,
|
| 204 |
+
"theoretical_loss": 3.3212990517497207,
|
| 205 |
+
"tokens_seen": 2993684480
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.01,
|
| 209 |
+
"learning_rate": 0.0009991445680068436,
|
| 210 |
+
"loss": 2.5234,
|
| 211 |
+
"theoretical_loss": 3.3212878667293797,
|
| 212 |
+
"tokens_seen": 2993815552
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.01,
|
| 216 |
+
"learning_rate": 0.0009987168520102653,
|
| 217 |
+
"loss": 2.5502,
|
| 218 |
+
"theoretical_loss": 3.321276682335825,
|
| 219 |
+
"tokens_seen": 2993946624
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.01,
|
| 223 |
+
"learning_rate": 0.000998289136013687,
|
| 224 |
+
"loss": 2.6849,
|
| 225 |
+
"theoretical_loss": 3.3212654985689936,
|
| 226 |
+
"tokens_seen": 2994077696
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.01,
|
| 230 |
+
"learning_rate": 0.0009978614200171086,
|
| 231 |
+
"loss": 2.6348,
|
| 232 |
+
"theoretical_loss": 3.3212543154288237,
|
| 233 |
+
"tokens_seen": 2994208768
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.01,
|
| 237 |
+
"learning_rate": 0.0009974337040205303,
|
| 238 |
+
"loss": 2.6793,
|
| 239 |
+
"theoretical_loss": 3.3212431329152525,
|
| 240 |
+
"tokens_seen": 2994339840
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.01,
|
| 244 |
+
"learning_rate": 0.0009970059880239522,
|
| 245 |
+
"loss": 2.6212,
|
| 246 |
+
"theoretical_loss": 3.321231951028217,
|
| 247 |
+
"tokens_seen": 2994470912
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.01,
|
| 251 |
+
"learning_rate": 0.0009965782720273739,
|
| 252 |
+
"loss": 2.629,
|
| 253 |
+
"theoretical_loss": 3.3212207697676552,
|
| 254 |
+
"tokens_seen": 2994601984
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.01,
|
| 258 |
+
"learning_rate": 0.0009961505560307955,
|
| 259 |
+
"loss": 2.5865,
|
| 260 |
+
"theoretical_loss": 3.3212095891335043,
|
| 261 |
+
"tokens_seen": 2994733056
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.01,
|
| 265 |
+
"learning_rate": 0.0009957228400342174,
|
| 266 |
+
"loss": 2.667,
|
| 267 |
+
"theoretical_loss": 3.321198409125702,
|
| 268 |
+
"tokens_seen": 2994864128
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.01,
|
| 272 |
+
"learning_rate": 0.000995295124037639,
|
| 273 |
+
"loss": 2.55,
|
| 274 |
+
"theoretical_loss": 3.321187229744186,
|
| 275 |
+
"tokens_seen": 2994995200
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.02,
|
| 279 |
+
"learning_rate": 0.0009948674080410608,
|
| 280 |
+
"loss": 2.6324,
|
| 281 |
+
"theoretical_loss": 3.321176050988893,
|
| 282 |
+
"tokens_seen": 2995126272
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.02,
|
| 286 |
+
"learning_rate": 0.0009944396920444824,
|
| 287 |
+
"loss": 2.8406,
|
| 288 |
+
"theoretical_loss": 3.3211648728597614,
|
| 289 |
+
"tokens_seen": 2995257344
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.02,
|
| 293 |
+
"objective/train/docs_used": 1642666,
|
| 294 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 295 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 296 |
+
"objective/train/original_loss": 2.8021185398101807,
|
| 297 |
+
"objective/train/theoretical_loss": 3.3211592840299864,
|
| 298 |
+
"objective/train/tokens_used": 25374176,
|
| 299 |
+
"theoretical_loss": 3.3211592840299864,
|
| 300 |
+
"tokens_seen": 2995322880
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.02,
|
| 304 |
+
"learning_rate": 0.0009940119760479041,
|
| 305 |
+
"loss": 2.5438,
|
| 306 |
+
"theoretical_loss": 3.3211536953567284,
|
| 307 |
+
"tokens_seen": 2995388416
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.02,
|
| 311 |
+
"learning_rate": 0.000993584260051326,
|
| 312 |
+
"loss": 2.7618,
|
| 313 |
+
"theoretical_loss": 3.321142518479731,
|
| 314 |
+
"tokens_seen": 2995519488
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.02,
|
| 318 |
+
"learning_rate": 0.0009931565440547477,
|
| 319 |
+
"loss": 2.6638,
|
| 320 |
+
"theoretical_loss": 3.321131342228708,
|
| 321 |
+
"tokens_seen": 2995650560
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.02,
|
| 325 |
+
"learning_rate": 0.0009927288280581694,
|
| 326 |
+
"loss": 2.7287,
|
| 327 |
+
"theoretical_loss": 3.321120166603596,
|
| 328 |
+
"tokens_seen": 2995781632
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.02,
|
| 332 |
+
"learning_rate": 0.000992301112061591,
|
| 333 |
+
"loss": 2.5832,
|
| 334 |
+
"theoretical_loss": 3.3211089916043326,
|
| 335 |
+
"tokens_seen": 2995912704
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.02,
|
| 339 |
+
"learning_rate": 0.0009918733960650127,
|
| 340 |
+
"loss": 2.6355,
|
| 341 |
+
"theoretical_loss": 3.3210978172308554,
|
| 342 |
+
"tokens_seen": 2996043776
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.02,
|
| 346 |
+
"learning_rate": 0.0009914456800684346,
|
| 347 |
+
"loss": 2.5139,
|
| 348 |
+
"theoretical_loss": 3.3210866434831026,
|
| 349 |
+
"tokens_seen": 2996174848
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.02,
|
| 353 |
+
"learning_rate": 0.0009910179640718563,
|
| 354 |
+
"loss": 2.5879,
|
| 355 |
+
"theoretical_loss": 3.3210754703610106,
|
| 356 |
+
"tokens_seen": 2996305920
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.02,
|
| 360 |
+
"learning_rate": 0.0009905902480752782,
|
| 361 |
+
"loss": 2.5935,
|
| 362 |
+
"theoretical_loss": 3.321064297864518,
|
| 363 |
+
"tokens_seen": 2996436992
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.02,
|
| 367 |
+
"learning_rate": 0.0009901625320786998,
|
| 368 |
+
"loss": 2.6176,
|
| 369 |
+
"theoretical_loss": 3.3210531259935627,
|
| 370 |
+
"tokens_seen": 2996568064
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.02,
|
| 374 |
+
"learning_rate": 0.0009897348160821215,
|
| 375 |
+
"loss": 2.6405,
|
| 376 |
+
"theoretical_loss": 3.321041954748081,
|
| 377 |
+
"tokens_seen": 2996699136
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.02,
|
| 381 |
+
"learning_rate": 0.0009893071000855432,
|
| 382 |
+
"loss": 2.7274,
|
| 383 |
+
"theoretical_loss": 3.321030784128012,
|
| 384 |
+
"tokens_seen": 2996830208
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.02,
|
| 388 |
+
"objective/train/docs_used": 1643300,
|
| 389 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 390 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 391 |
+
"objective/train/original_loss": 3.023165464401245,
|
| 392 |
+
"objective/train/theoretical_loss": 3.321019614133292,
|
| 393 |
+
"objective/train/tokens_used": 27012576,
|
| 394 |
+
"theoretical_loss": 3.321019614133292,
|
| 395 |
+
"tokens_seen": 2996961280
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.02,
|
| 399 |
+
"learning_rate": 0.0009888793840889649,
|
| 400 |
+
"loss": 2.7003,
|
| 401 |
+
"theoretical_loss": 3.321019614133292,
|
| 402 |
+
"tokens_seen": 2996961280
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.02,
|
| 406 |
+
"learning_rate": 0.0009884516680923865,
|
| 407 |
+
"loss": 2.7436,
|
| 408 |
+
"theoretical_loss": 3.3210084447638595,
|
| 409 |
+
"tokens_seen": 2997092352
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.02,
|
| 413 |
+
"learning_rate": 0.0009880239520958084,
|
| 414 |
+
"loss": 2.5873,
|
| 415 |
+
"theoretical_loss": 3.320997276019652,
|
| 416 |
+
"tokens_seen": 2997223424
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.02,
|
| 420 |
+
"learning_rate": 0.00098759623609923,
|
| 421 |
+
"loss": 2.5974,
|
| 422 |
+
"theoretical_loss": 3.3209861079006067,
|
| 423 |
+
"tokens_seen": 2997354496
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.02,
|
| 427 |
+
"learning_rate": 0.000987168520102652,
|
| 428 |
+
"loss": 2.5806,
|
| 429 |
+
"theoretical_loss": 3.320974940406662,
|
| 430 |
+
"tokens_seen": 2997485568
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.02,
|
| 434 |
+
"learning_rate": 0.0009867408041060737,
|
| 435 |
+
"loss": 2.6771,
|
| 436 |
+
"theoretical_loss": 3.320963773537755,
|
| 437 |
+
"tokens_seen": 2997616640
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.02,
|
| 441 |
+
"learning_rate": 0.0009863130881094953,
|
| 442 |
+
"loss": 2.7313,
|
| 443 |
+
"theoretical_loss": 3.320952607293824,
|
| 444 |
+
"tokens_seen": 2997747712
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.02,
|
| 448 |
+
"learning_rate": 0.000985885372112917,
|
| 449 |
+
"loss": 2.7302,
|
| 450 |
+
"theoretical_loss": 3.320941441674806,
|
| 451 |
+
"tokens_seen": 2997878784
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.02,
|
| 455 |
+
"learning_rate": 0.0009854576561163387,
|
| 456 |
+
"loss": 2.893,
|
| 457 |
+
"theoretical_loss": 3.320930276680639,
|
| 458 |
+
"tokens_seen": 2998009856
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.02,
|
| 462 |
+
"learning_rate": 0.0009850299401197606,
|
| 463 |
+
"loss": 2.6886,
|
| 464 |
+
"theoretical_loss": 3.3209191123112607,
|
| 465 |
+
"tokens_seen": 2998140928
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.03,
|
| 469 |
+
"learning_rate": 0.0009846022241231823,
|
| 470 |
+
"loss": 2.7801,
|
| 471 |
+
"theoretical_loss": 3.320907948566609,
|
| 472 |
+
"tokens_seen": 2998272000
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.03,
|
| 476 |
+
"learning_rate": 0.000984174508126604,
|
| 477 |
+
"loss": 2.6538,
|
| 478 |
+
"theoretical_loss": 3.3208967854466214,
|
| 479 |
+
"tokens_seen": 2998403072
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.03,
|
| 483 |
+
"learning_rate": 0.0009837467921300258,
|
| 484 |
+
"loss": 2.5705,
|
| 485 |
+
"theoretical_loss": 3.3208856229512356,
|
| 486 |
+
"tokens_seen": 2998534144
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.03,
|
| 490 |
+
"objective/train/docs_used": 1644380,
|
| 491 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 492 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 493 |
+
"objective/train/original_loss": 2.542499542236328,
|
| 494 |
+
"objective/train/theoretical_loss": 3.320880041937749,
|
| 495 |
+
"objective/train/tokens_used": 28650976,
|
| 496 |
+
"theoretical_loss": 3.320880041937749,
|
| 497 |
+
"tokens_seen": 2998599680
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 0.03,
|
| 501 |
+
"learning_rate": 0.0009833190761334475,
|
| 502 |
+
"loss": 2.5074,
|
| 503 |
+
"theoretical_loss": 3.3208744610803898,
|
| 504 |
+
"tokens_seen": 2998665216
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.03,
|
| 508 |
+
"learning_rate": 0.0009828913601368692,
|
| 509 |
+
"loss": 2.6151,
|
| 510 |
+
"theoretical_loss": 3.320863299834021,
|
| 511 |
+
"tokens_seen": 2998796288
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 0.03,
|
| 515 |
+
"learning_rate": 0.0009824636441402908,
|
| 516 |
+
"loss": 2.6994,
|
| 517 |
+
"theoretical_loss": 3.320852139212068,
|
| 518 |
+
"tokens_seen": 2998927360
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.03,
|
| 522 |
+
"learning_rate": 0.0009820359281437125,
|
| 523 |
+
"loss": 2.568,
|
| 524 |
+
"theoretical_loss": 3.3208409792144677,
|
| 525 |
+
"tokens_seen": 2999058432
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.03,
|
| 529 |
+
"learning_rate": 0.0009816082121471344,
|
| 530 |
+
"loss": 2.5552,
|
| 531 |
+
"theoretical_loss": 3.320829819841158,
|
| 532 |
+
"tokens_seen": 2999189504
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.03,
|
| 536 |
+
"learning_rate": 0.000981180496150556,
|
| 537 |
+
"loss": 2.6719,
|
| 538 |
+
"theoretical_loss": 3.320818661092077,
|
| 539 |
+
"tokens_seen": 2999320576
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.03,
|
| 543 |
+
"learning_rate": 0.0009807527801539778,
|
| 544 |
+
"loss": 2.5567,
|
| 545 |
+
"theoretical_loss": 3.3208075029671624,
|
| 546 |
+
"tokens_seen": 2999451648
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.03,
|
| 550 |
+
"learning_rate": 0.0009803250641573994,
|
| 551 |
+
"loss": 2.5511,
|
| 552 |
+
"theoretical_loss": 3.320796345466352,
|
| 553 |
+
"tokens_seen": 2999582720
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.03,
|
| 557 |
+
"learning_rate": 0.0009798973481608211,
|
| 558 |
+
"loss": 2.6608,
|
| 559 |
+
"theoretical_loss": 3.320785188589584,
|
| 560 |
+
"tokens_seen": 2999713792
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.03,
|
| 564 |
+
"learning_rate": 0.000979469632164243,
|
| 565 |
+
"loss": 2.5947,
|
| 566 |
+
"theoretical_loss": 3.3207740323367956,
|
| 567 |
+
"tokens_seen": 2999844864
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.03,
|
| 571 |
+
"learning_rate": 0.0009790419161676647,
|
| 572 |
+
"loss": 2.6511,
|
| 573 |
+
"theoretical_loss": 3.3207628767079242,
|
| 574 |
+
"tokens_seen": 2999975936
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 0.03,
|
| 578 |
+
"learning_rate": 0.0009786142001710863,
|
| 579 |
+
"loss": 2.5573,
|
| 580 |
+
"theoretical_loss": 3.3207517217029094,
|
| 581 |
+
"tokens_seen": 3000107008
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 0.03,
|
| 585 |
+
"objective/train/docs_used": 1645056,
|
| 586 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 587 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 588 |
+
"objective/train/original_loss": 2.4763801097869873,
|
| 589 |
+
"objective/train/theoretical_loss": 3.3207405673216877,
|
| 590 |
+
"objective/train/tokens_used": 30289376,
|
| 591 |
+
"theoretical_loss": 3.3207405673216877,
|
| 592 |
+
"tokens_seen": 3000238080
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.03,
|
| 596 |
+
"learning_rate": 0.0009781864841745082,
|
| 597 |
+
"loss": 2.6745,
|
| 598 |
+
"theoretical_loss": 3.3207405673216877,
|
| 599 |
+
"tokens_seen": 3000238080
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.03,
|
| 603 |
+
"learning_rate": 0.00097775876817793,
|
| 604 |
+
"loss": 2.697,
|
| 605 |
+
"theoretical_loss": 3.320729413564197,
|
| 606 |
+
"tokens_seen": 3000369152
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.03,
|
| 610 |
+
"learning_rate": 0.0009773310521813516,
|
| 611 |
+
"loss": 2.6853,
|
| 612 |
+
"theoretical_loss": 3.3207182604303753,
|
| 613 |
+
"tokens_seen": 3000500224
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.03,
|
| 617 |
+
"learning_rate": 0.0009769033361847733,
|
| 618 |
+
"loss": 2.3445,
|
| 619 |
+
"theoretical_loss": 3.320707107920161,
|
| 620 |
+
"tokens_seen": 3000631296
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.03,
|
| 624 |
+
"learning_rate": 0.000976475620188195,
|
| 625 |
+
"loss": 2.6763,
|
| 626 |
+
"theoretical_loss": 3.3206959560334917,
|
| 627 |
+
"tokens_seen": 3000762368
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.03,
|
| 631 |
+
"learning_rate": 0.0009760479041916168,
|
| 632 |
+
"loss": 2.5198,
|
| 633 |
+
"theoretical_loss": 3.320684804770305,
|
| 634 |
+
"tokens_seen": 3000893440
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.03,
|
| 638 |
+
"learning_rate": 0.0009756201881950385,
|
| 639 |
+
"loss": 2.7,
|
| 640 |
+
"theoretical_loss": 3.3206736541305393,
|
| 641 |
+
"tokens_seen": 3001024512
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.03,
|
| 645 |
+
"learning_rate": 0.0009751924721984602,
|
| 646 |
+
"loss": 2.6958,
|
| 647 |
+
"theoretical_loss": 3.3206625041141318,
|
| 648 |
+
"tokens_seen": 3001155584
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.04,
|
| 652 |
+
"learning_rate": 0.000974764756201882,
|
| 653 |
+
"loss": 2.6457,
|
| 654 |
+
"theoretical_loss": 3.3206513547210212,
|
| 655 |
+
"tokens_seen": 3001286656
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.04,
|
| 659 |
+
"learning_rate": 0.0009743370402053036,
|
| 660 |
+
"loss": 2.7946,
|
| 661 |
+
"theoretical_loss": 3.320640205951145,
|
| 662 |
+
"tokens_seen": 3001417728
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.04,
|
| 666 |
+
"learning_rate": 0.0009739093242087254,
|
| 667 |
+
"loss": 2.6682,
|
| 668 |
+
"theoretical_loss": 3.3206290578044415,
|
| 669 |
+
"tokens_seen": 3001548800
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.04,
|
| 673 |
+
"learning_rate": 0.0009734816082121472,
|
| 674 |
+
"loss": 2.5484,
|
| 675 |
+
"theoretical_loss": 3.3206179102808484,
|
| 676 |
+
"tokens_seen": 3001679872
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.04,
|
| 680 |
+
"learning_rate": 0.0009730538922155689,
|
| 681 |
+
"loss": 2.6724,
|
| 682 |
+
"theoretical_loss": 3.3206067633803036,
|
| 683 |
+
"tokens_seen": 3001810944
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.04,
|
| 687 |
+
"objective/train/docs_used": 1646327,
|
| 688 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 689 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 690 |
+
"objective/train/original_loss": 2.547891855239868,
|
| 691 |
+
"objective/train/theoretical_loss": 3.320601190163655,
|
| 692 |
+
"objective/train/tokens_used": 31927776,
|
| 693 |
+
"theoretical_loss": 3.320601190163655,
|
| 694 |
+
"tokens_seen": 3001876480
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 0.04,
|
| 698 |
+
"learning_rate": 0.0009726261762189907,
|
| 699 |
+
"loss": 2.5267,
|
| 700 |
+
"theoretical_loss": 3.320595617102745,
|
| 701 |
+
"tokens_seen": 3001942016
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 0.04,
|
| 705 |
+
"learning_rate": 0.0009721984602224123,
|
| 706 |
+
"loss": 2.6548,
|
| 707 |
+
"theoretical_loss": 3.320584471448111,
|
| 708 |
+
"tokens_seen": 3002073088
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 0.04,
|
| 712 |
+
"learning_rate": 0.0009717707442258341,
|
| 713 |
+
"loss": 2.5147,
|
| 714 |
+
"theoretical_loss": 3.3205733264163393,
|
| 715 |
+
"tokens_seen": 3002204160
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 0.04,
|
| 719 |
+
"learning_rate": 0.0009713430282292558,
|
| 720 |
+
"loss": 2.4505,
|
| 721 |
+
"theoretical_loss": 3.320562182007368,
|
| 722 |
+
"tokens_seen": 3002335232
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.04,
|
| 726 |
+
"learning_rate": 0.0009709153122326775,
|
| 727 |
+
"loss": 2.6305,
|
| 728 |
+
"theoretical_loss": 3.320551038221135,
|
| 729 |
+
"tokens_seen": 3002466304
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.04,
|
| 733 |
+
"learning_rate": 0.0009704875962360993,
|
| 734 |
+
"loss": 2.5482,
|
| 735 |
+
"theoretical_loss": 3.3205398950575784,
|
| 736 |
+
"tokens_seen": 3002597376
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.04,
|
| 740 |
+
"learning_rate": 0.0009700598802395209,
|
| 741 |
+
"loss": 2.7266,
|
| 742 |
+
"theoretical_loss": 3.320528752516636,
|
| 743 |
+
"tokens_seen": 3002728448
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 0.04,
|
| 747 |
+
"learning_rate": 0.0009696321642429427,
|
| 748 |
+
"loss": 2.5155,
|
| 749 |
+
"theoretical_loss": 3.3205176105982463,
|
| 750 |
+
"tokens_seen": 3002859520
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 0.04,
|
| 754 |
+
"learning_rate": 0.0009692044482463645,
|
| 755 |
+
"loss": 2.7628,
|
| 756 |
+
"theoretical_loss": 3.320506469302347,
|
| 757 |
+
"tokens_seen": 3002990592
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 0.04,
|
| 761 |
+
"learning_rate": 0.0009687767322497862,
|
| 762 |
+
"loss": 2.6802,
|
| 763 |
+
"theoretical_loss": 3.3204953286288763,
|
| 764 |
+
"tokens_seen": 3003121664
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 0.04,
|
| 768 |
+
"learning_rate": 0.000968349016253208,
|
| 769 |
+
"loss": 2.7921,
|
| 770 |
+
"theoretical_loss": 3.3204841885777725,
|
| 771 |
+
"tokens_seen": 3003252736
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.04,
|
| 775 |
+
"learning_rate": 0.0009679213002566296,
|
| 776 |
+
"loss": 2.6088,
|
| 777 |
+
"theoretical_loss": 3.3204730491489727,
|
| 778 |
+
"tokens_seen": 3003383808
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 0.04,
|
| 782 |
+
"objective/train/docs_used": 1647543,
|
| 783 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 784 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 785 |
+
"objective/train/original_loss": 2.5402848720550537,
|
| 786 |
+
"objective/train/theoretical_loss": 3.3204619103424164,
|
| 787 |
+
"objective/train/tokens_used": 33566176,
|
| 788 |
+
"theoretical_loss": 3.3204619103424164,
|
| 789 |
+
"tokens_seen": 3003514880
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.04,
|
| 793 |
+
"learning_rate": 0.0009674935842600513,
|
| 794 |
+
"loss": 2.6446,
|
| 795 |
+
"theoretical_loss": 3.3204619103424164,
|
| 796 |
+
"tokens_seen": 3003514880
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.04,
|
| 800 |
+
"learning_rate": 0.0009670658682634731,
|
| 801 |
+
"loss": 2.5202,
|
| 802 |
+
"theoretical_loss": 3.3204507721580403,
|
| 803 |
+
"tokens_seen": 3003645952
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.04,
|
| 807 |
+
"learning_rate": 0.0009666381522668948,
|
| 808 |
+
"loss": 2.4832,
|
| 809 |
+
"theoretical_loss": 3.3204396345957834,
|
| 810 |
+
"tokens_seen": 3003777024
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.04,
|
| 814 |
+
"learning_rate": 0.0009662104362703165,
|
| 815 |
+
"loss": 2.6544,
|
| 816 |
+
"theoretical_loss": 3.320428497655584,
|
| 817 |
+
"tokens_seen": 3003908096
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.04,
|
| 821 |
+
"learning_rate": 0.0009657827202737382,
|
| 822 |
+
"loss": 2.7507,
|
| 823 |
+
"theoretical_loss": 3.320417361337379,
|
| 824 |
+
"tokens_seen": 3004039168
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.04,
|
| 828 |
+
"learning_rate": 0.00096535500427716,
|
| 829 |
+
"loss": 2.5786,
|
| 830 |
+
"theoretical_loss": 3.3204062256411078,
|
| 831 |
+
"tokens_seen": 3004170240
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.04,
|
| 835 |
+
"learning_rate": 0.0009649272882805818,
|
| 836 |
+
"loss": 2.6649,
|
| 837 |
+
"theoretical_loss": 3.320395090566708,
|
| 838 |
+
"tokens_seen": 3004301312
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.05,
|
| 842 |
+
"learning_rate": 0.0009644995722840035,
|
| 843 |
+
"loss": 2.6338,
|
| 844 |
+
"theoretical_loss": 3.3203839561141173,
|
| 845 |
+
"tokens_seen": 3004432384
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.05,
|
| 849 |
+
"learning_rate": 0.0009640718562874252,
|
| 850 |
+
"loss": 2.664,
|
| 851 |
+
"theoretical_loss": 3.320372822283275,
|
| 852 |
+
"tokens_seen": 3004563456
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.05,
|
| 856 |
+
"learning_rate": 0.0009636441402908469,
|
| 857 |
+
"loss": 2.6909,
|
| 858 |
+
"theoretical_loss": 3.3203616890741183,
|
| 859 |
+
"tokens_seen": 3004694528
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.05,
|
| 863 |
+
"learning_rate": 0.0009632164242942686,
|
| 864 |
+
"loss": 2.4478,
|
| 865 |
+
"theoretical_loss": 3.3203505564865856,
|
| 866 |
+
"tokens_seen": 3004825600
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.05,
|
| 870 |
+
"learning_rate": 0.0009627887082976904,
|
| 871 |
+
"loss": 2.6265,
|
| 872 |
+
"theoretical_loss": 3.3203394245206153,
|
| 873 |
+
"tokens_seen": 3004956672
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.05,
|
| 877 |
+
"learning_rate": 0.000962360992301112,
|
| 878 |
+
"loss": 2.5755,
|
| 879 |
+
"theoretical_loss": 3.320328293176145,
|
| 880 |
+
"tokens_seen": 3005087744
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.05,
|
| 884 |
+
"objective/train/docs_used": 1648109,
|
| 885 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 886 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 887 |
+
"objective/train/original_loss": 2.5592408180236816,
|
| 888 |
+
"objective/train/theoretical_loss": 3.3203227277369534,
|
| 889 |
+
"objective/train/tokens_used": 35204576,
|
| 890 |
+
"theoretical_loss": 3.3203227277369534,
|
| 891 |
+
"tokens_seen": 3005153280
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.05,
|
| 895 |
+
"learning_rate": 0.0009619332763045337,
|
| 896 |
+
"loss": 2.567,
|
| 897 |
+
"theoretical_loss": 3.320317162453114,
|
| 898 |
+
"tokens_seen": 3005218816
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.05,
|
| 902 |
+
"learning_rate": 0.0009615055603079555,
|
| 903 |
+
"loss": 2.6035,
|
| 904 |
+
"theoretical_loss": 3.3203060323514593,
|
| 905 |
+
"tokens_seen": 3005349888
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.05,
|
| 909 |
+
"learning_rate": 0.0009610778443113773,
|
| 910 |
+
"loss": 2.6209,
|
| 911 |
+
"theoretical_loss": 3.3202949028711197,
|
| 912 |
+
"tokens_seen": 3005480960
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.05,
|
| 916 |
+
"learning_rate": 0.0009606501283147991,
|
| 917 |
+
"loss": 2.522,
|
| 918 |
+
"theoretical_loss": 3.3202837740120335,
|
| 919 |
+
"tokens_seen": 3005612032
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.05,
|
| 923 |
+
"learning_rate": 0.0009602224123182207,
|
| 924 |
+
"loss": 2.5764,
|
| 925 |
+
"theoretical_loss": 3.3202726457741387,
|
| 926 |
+
"tokens_seen": 3005743104
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.05,
|
| 930 |
+
"learning_rate": 0.0009597946963216424,
|
| 931 |
+
"loss": 2.6805,
|
| 932 |
+
"theoretical_loss": 3.320261518157374,
|
| 933 |
+
"tokens_seen": 3005874176
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.05,
|
| 937 |
+
"learning_rate": 0.0009593669803250642,
|
| 938 |
+
"loss": 2.4835,
|
| 939 |
+
"theoretical_loss": 3.3202503911616765,
|
| 940 |
+
"tokens_seen": 3006005248
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.05,
|
| 944 |
+
"learning_rate": 0.0009589392643284859,
|
| 945 |
+
"loss": 2.5907,
|
| 946 |
+
"theoretical_loss": 3.320239264786986,
|
| 947 |
+
"tokens_seen": 3006136320
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.05,
|
| 951 |
+
"learning_rate": 0.0009585115483319077,
|
| 952 |
+
"loss": 2.617,
|
| 953 |
+
"theoretical_loss": 3.3202281390332393,
|
| 954 |
+
"tokens_seen": 3006267392
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.05,
|
| 958 |
+
"learning_rate": 0.0009580838323353293,
|
| 959 |
+
"loss": 2.5027,
|
| 960 |
+
"theoretical_loss": 3.320217013900376,
|
| 961 |
+
"tokens_seen": 3006398464
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.05,
|
| 965 |
+
"learning_rate": 0.000957656116338751,
|
| 966 |
+
"loss": 2.6857,
|
| 967 |
+
"theoretical_loss": 3.3202058893883333,
|
| 968 |
+
"tokens_seen": 3006529536
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.05,
|
| 972 |
+
"learning_rate": 0.0009572284003421729,
|
| 973 |
+
"loss": 2.6411,
|
| 974 |
+
"theoretical_loss": 3.3201947654970505,
|
| 975 |
+
"tokens_seen": 3006660608
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.05,
|
| 979 |
+
"objective/train/docs_used": 1649212,
|
| 980 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 981 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 982 |
+
"objective/train/original_loss": 2.7101857662200928,
|
| 983 |
+
"objective/train/theoretical_loss": 3.320183642226465,
|
| 984 |
+
"objective/train/tokens_used": 36842976,
|
| 985 |
+
"theoretical_loss": 3.320183642226465,
|
| 986 |
+
"tokens_seen": 3006791680
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 0.05,
|
| 990 |
+
"learning_rate": 0.0009568006843455946,
|
| 991 |
+
"loss": 2.5369,
|
| 992 |
+
"theoretical_loss": 3.320183642226465,
|
| 993 |
+
"tokens_seen": 3006791680
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 0.05,
|
| 997 |
+
"learning_rate": 0.0009563729683490164,
|
| 998 |
+
"loss": 2.5836,
|
| 999 |
+
"theoretical_loss": 3.3201725195765155,
|
| 1000 |
+
"tokens_seen": 3006922752
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 0.05,
|
| 1004 |
+
"learning_rate": 0.000955945252352438,
|
| 1005 |
+
"loss": 2.5358,
|
| 1006 |
+
"theoretical_loss": 3.3201613975471402,
|
| 1007 |
+
"tokens_seen": 3007053824
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 0.05,
|
| 1011 |
+
"learning_rate": 0.0009555175363558597,
|
| 1012 |
+
"loss": 2.6035,
|
| 1013 |
+
"theoretical_loss": 3.3201502761382775,
|
| 1014 |
+
"tokens_seen": 3007184896
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 0.05,
|
| 1018 |
+
"learning_rate": 0.0009550898203592815,
|
| 1019 |
+
"loss": 2.4594,
|
| 1020 |
+
"theoretical_loss": 3.320139155349866,
|
| 1021 |
+
"tokens_seen": 3007315968
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 0.06,
|
| 1025 |
+
"learning_rate": 0.0009546621043627032,
|
| 1026 |
+
"loss": 2.6376,
|
| 1027 |
+
"theoretical_loss": 3.3201280351818436,
|
| 1028 |
+
"tokens_seen": 3007447040
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 0.06,
|
| 1032 |
+
"learning_rate": 0.0009542343883661248,
|
| 1033 |
+
"loss": 2.5904,
|
| 1034 |
+
"theoretical_loss": 3.320116915634149,
|
| 1035 |
+
"tokens_seen": 3007578112
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.06,
|
| 1039 |
+
"learning_rate": 0.0009538066723695466,
|
| 1040 |
+
"loss": 2.7616,
|
| 1041 |
+
"theoretical_loss": 3.3201057967067205,
|
| 1042 |
+
"tokens_seen": 3007709184
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 0.06,
|
| 1046 |
+
"learning_rate": 0.0009533789563729683,
|
| 1047 |
+
"loss": 2.6076,
|
| 1048 |
+
"theoretical_loss": 3.3200946783994962,
|
| 1049 |
+
"tokens_seen": 3007840256
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 0.06,
|
| 1053 |
+
"learning_rate": 0.0009529512403763902,
|
| 1054 |
+
"loss": 2.6121,
|
| 1055 |
+
"theoretical_loss": 3.3200835607124146,
|
| 1056 |
+
"tokens_seen": 3007971328
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 0.06,
|
| 1060 |
+
"learning_rate": 0.0009525235243798119,
|
| 1061 |
+
"loss": 2.6083,
|
| 1062 |
+
"theoretical_loss": 3.3200724436454143,
|
| 1063 |
+
"tokens_seen": 3008102400
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 0.06,
|
| 1067 |
+
"learning_rate": 0.0009520958083832335,
|
| 1068 |
+
"loss": 2.6831,
|
| 1069 |
+
"theoretical_loss": 3.3200613271984336,
|
| 1070 |
+
"tokens_seen": 3008233472
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 0.06,
|
| 1074 |
+
"learning_rate": 0.0009516680923866553,
|
| 1075 |
+
"loss": 2.6156,
|
| 1076 |
+
"theoretical_loss": 3.3200502113714108,
|
| 1077 |
+
"tokens_seen": 3008364544
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 0.06,
|
| 1081 |
+
"objective/train/docs_used": 1649940,
|
| 1082 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 1083 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 1084 |
+
"objective/train/original_loss": 2.545426368713379,
|
| 1085 |
+
"objective/train/theoretical_loss": 3.3200446536903643,
|
| 1086 |
+
"objective/train/tokens_used": 38481376,
|
| 1087 |
+
"theoretical_loss": 3.3200446536903643,
|
| 1088 |
+
"tokens_seen": 3008430080
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.06,
|
| 1092 |
+
"learning_rate": 0.000951240376390077,
|
| 1093 |
+
"loss": 2.6849,
|
| 1094 |
+
"theoretical_loss": 3.3200390961642845,
|
| 1095 |
+
"tokens_seen": 3008495616
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.06,
|
| 1099 |
+
"learning_rate": 0.0009508126603934988,
|
| 1100 |
+
"loss": 2.654,
|
| 1101 |
+
"theoretical_loss": 3.3200279815769926,
|
| 1102 |
+
"tokens_seen": 3008626688
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.06,
|
| 1106 |
+
"learning_rate": 0.0009503849443969204,
|
| 1107 |
+
"loss": 2.6215,
|
| 1108 |
+
"theoretical_loss": 3.3200168676094743,
|
| 1109 |
+
"tokens_seen": 3008757760
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.06,
|
| 1113 |
+
"learning_rate": 0.0009499572284003421,
|
| 1114 |
+
"loss": 2.4387,
|
| 1115 |
+
"theoretical_loss": 3.320005754261668,
|
| 1116 |
+
"tokens_seen": 3008888832
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.06,
|
| 1120 |
+
"learning_rate": 0.0009495295124037639,
|
| 1121 |
+
"loss": 2.5621,
|
| 1122 |
+
"theoretical_loss": 3.319994641533511,
|
| 1123 |
+
"tokens_seen": 3009019904
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.06,
|
| 1127 |
+
"learning_rate": 0.0009491017964071857,
|
| 1128 |
+
"loss": 2.731,
|
| 1129 |
+
"theoretical_loss": 3.319983529424943,
|
| 1130 |
+
"tokens_seen": 3009150976
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.06,
|
| 1134 |
+
"learning_rate": 0.0009486740804106075,
|
| 1135 |
+
"loss": 2.5847,
|
| 1136 |
+
"theoretical_loss": 3.3199724179359027,
|
| 1137 |
+
"tokens_seen": 3009282048
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.06,
|
| 1141 |
+
"learning_rate": 0.0009482463644140291,
|
| 1142 |
+
"loss": 2.5836,
|
| 1143 |
+
"theoretical_loss": 3.319961307066327,
|
| 1144 |
+
"tokens_seen": 3009413120
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.06,
|
| 1148 |
+
"learning_rate": 0.0009478186484174508,
|
| 1149 |
+
"loss": 2.6488,
|
| 1150 |
+
"theoretical_loss": 3.3199501968161558,
|
| 1151 |
+
"tokens_seen": 3009544192
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.06,
|
| 1155 |
+
"learning_rate": 0.0009473909324208726,
|
| 1156 |
+
"loss": 2.6244,
|
| 1157 |
+
"theoretical_loss": 3.319939087185327,
|
| 1158 |
+
"tokens_seen": 3009675264
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.06,
|
| 1162 |
+
"learning_rate": 0.0009469632164242943,
|
| 1163 |
+
"loss": 2.6873,
|
| 1164 |
+
"theoretical_loss": 3.3199279781737796,
|
| 1165 |
+
"tokens_seen": 3009806336
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.06,
|
| 1169 |
+
"learning_rate": 0.000946535500427716,
|
| 1170 |
+
"loss": 2.5921,
|
| 1171 |
+
"theoretical_loss": 3.3199168697814514,
|
| 1172 |
+
"tokens_seen": 3009937408
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.06,
|
| 1176 |
+
"objective/train/docs_used": 1651249,
|
| 1177 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 1178 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 1179 |
+
"objective/train/original_loss": 2.582075834274292,
|
| 1180 |
+
"objective/train/theoretical_loss": 3.3199057620082812,
|
| 1181 |
+
"objective/train/tokens_used": 40119776,
|
| 1182 |
+
"theoretical_loss": 3.3199057620082812,
|
| 1183 |
+
"tokens_seen": 3010068480
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 0.06,
|
| 1187 |
+
"learning_rate": 0.0009461077844311377,
|
| 1188 |
+
"loss": 2.5527,
|
| 1189 |
+
"theoretical_loss": 3.3199057620082812,
|
| 1190 |
+
"tokens_seen": 3010068480
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 0.06,
|
| 1194 |
+
"learning_rate": 0.0009456800684345594,
|
| 1195 |
+
"loss": 2.7818,
|
| 1196 |
+
"theoretical_loss": 3.319894654854208,
|
| 1197 |
+
"tokens_seen": 3010199552
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 0.06,
|
| 1201 |
+
"learning_rate": 0.0009452523524379812,
|
| 1202 |
+
"loss": 2.628,
|
| 1203 |
+
"theoretical_loss": 3.3198835483191695,
|
| 1204 |
+
"tokens_seen": 3010330624
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 0.06,
|
| 1208 |
+
"learning_rate": 0.000944824636441403,
|
| 1209 |
+
"loss": 2.4649,
|
| 1210 |
+
"theoretical_loss": 3.319872442403105,
|
| 1211 |
+
"tokens_seen": 3010461696
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 0.07,
|
| 1215 |
+
"learning_rate": 0.0009443969204448247,
|
| 1216 |
+
"loss": 2.7571,
|
| 1217 |
+
"theoretical_loss": 3.3198613371059524,
|
| 1218 |
+
"tokens_seen": 3010592768
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 0.07,
|
| 1222 |
+
"learning_rate": 0.0009439692044482464,
|
| 1223 |
+
"loss": 2.5878,
|
| 1224 |
+
"theoretical_loss": 3.319850232427651,
|
| 1225 |
+
"tokens_seen": 3010723840
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 0.07,
|
| 1229 |
+
"learning_rate": 0.0009435414884516681,
|
| 1230 |
+
"loss": 2.6015,
|
| 1231 |
+
"theoretical_loss": 3.3198391283681383,
|
| 1232 |
+
"tokens_seen": 3010854912
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 0.07,
|
| 1236 |
+
"learning_rate": 0.0009431137724550899,
|
| 1237 |
+
"loss": 2.5823,
|
| 1238 |
+
"theoretical_loss": 3.3198280249273546,
|
| 1239 |
+
"tokens_seen": 3010985984
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 0.07,
|
| 1243 |
+
"learning_rate": 0.0009426860564585116,
|
| 1244 |
+
"loss": 2.7222,
|
| 1245 |
+
"theoretical_loss": 3.319816922105237,
|
| 1246 |
+
"tokens_seen": 3011117056
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 0.07,
|
| 1250 |
+
"learning_rate": 0.0009422583404619332,
|
| 1251 |
+
"loss": 2.6364,
|
| 1252 |
+
"theoretical_loss": 3.319805819901724,
|
| 1253 |
+
"tokens_seen": 3011248128
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 0.07,
|
| 1257 |
+
"learning_rate": 0.000941830624465355,
|
| 1258 |
+
"loss": 2.6811,
|
| 1259 |
+
"theoretical_loss": 3.3197947183167553,
|
| 1260 |
+
"tokens_seen": 3011379200
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 0.07,
|
| 1264 |
+
"learning_rate": 0.0009414029084687767,
|
| 1265 |
+
"loss": 2.8016,
|
| 1266 |
+
"theoretical_loss": 3.319783617350269,
|
| 1267 |
+
"tokens_seen": 3011510272
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 0.07,
|
| 1271 |
+
"learning_rate": 0.0009409751924721985,
|
| 1272 |
+
"loss": 2.5657,
|
| 1273 |
+
"theoretical_loss": 3.319772517002204,
|
| 1274 |
+
"tokens_seen": 3011641344
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 0.07,
|
| 1278 |
+
"objective/train/docs_used": 1651905,
|
| 1279 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 1280 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 1281 |
+
"objective/train/original_loss": 3.0052103996276855,
|
| 1282 |
+
"objective/train/theoretical_loss": 3.31976696706006,
|
| 1283 |
+
"objective/train/tokens_used": 41758176,
|
| 1284 |
+
"theoretical_loss": 3.31976696706006,
|
| 1285 |
+
"tokens_seen": 3011706880
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 0.07,
|
| 1289 |
+
"learning_rate": 0.0009405474764756203,
|
| 1290 |
+
"loss": 2.6357,
|
| 1291 |
+
"theoretical_loss": 3.319761417272498,
|
| 1292 |
+
"tokens_seen": 3011772416
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 0.07,
|
| 1296 |
+
"learning_rate": 0.0009401197604790419,
|
| 1297 |
+
"loss": 2.5734,
|
| 1298 |
+
"theoretical_loss": 3.319750318161091,
|
| 1299 |
+
"tokens_seen": 3011903488
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 0.07,
|
| 1303 |
+
"learning_rate": 0.0009396920444824637,
|
| 1304 |
+
"loss": 2.424,
|
| 1305 |
+
"theoretical_loss": 3.3197392196679205,
|
| 1306 |
+
"tokens_seen": 3012034560
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 0.07,
|
| 1310 |
+
"learning_rate": 0.0009392643284858854,
|
| 1311 |
+
"loss": 2.5344,
|
| 1312 |
+
"theoretical_loss": 3.3197281217929255,
|
| 1313 |
+
"tokens_seen": 3012165632
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 0.07,
|
| 1317 |
+
"learning_rate": 0.0009388366124893071,
|
| 1318 |
+
"loss": 2.5689,
|
| 1319 |
+
"theoretical_loss": 3.319717024536045,
|
| 1320 |
+
"tokens_seen": 3012296704
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 0.07,
|
| 1324 |
+
"learning_rate": 0.0009384088964927289,
|
| 1325 |
+
"loss": 2.4989,
|
| 1326 |
+
"theoretical_loss": 3.3197059278972176,
|
| 1327 |
+
"tokens_seen": 3012427776
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 0.07,
|
| 1331 |
+
"learning_rate": 0.0009379811804961505,
|
| 1332 |
+
"loss": 2.6272,
|
| 1333 |
+
"theoretical_loss": 3.3196948318763817,
|
| 1334 |
+
"tokens_seen": 3012558848
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 0.07,
|
| 1338 |
+
"learning_rate": 0.0009375534644995723,
|
| 1339 |
+
"loss": 2.5959,
|
| 1340 |
+
"theoretical_loss": 3.319683736473476,
|
| 1341 |
+
"tokens_seen": 3012689920
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 0.07,
|
| 1345 |
+
"learning_rate": 0.000937125748502994,
|
| 1346 |
+
"loss": 2.5228,
|
| 1347 |
+
"theoretical_loss": 3.3196726416884395,
|
| 1348 |
+
"tokens_seen": 3012820992
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 0.07,
|
| 1352 |
+
"learning_rate": 0.0009366980325064158,
|
| 1353 |
+
"loss": 2.7357,
|
| 1354 |
+
"theoretical_loss": 3.3196615475212106,
|
| 1355 |
+
"tokens_seen": 3012952064
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 0.07,
|
| 1359 |
+
"learning_rate": 0.0009362703165098376,
|
| 1360 |
+
"loss": 2.6946,
|
| 1361 |
+
"theoretical_loss": 3.3196504539717284,
|
| 1362 |
+
"tokens_seen": 3013083136
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 0.07,
|
| 1366 |
+
"learning_rate": 0.0009358426005132592,
|
| 1367 |
+
"loss": 2.7344,
|
| 1368 |
+
"theoretical_loss": 3.3196393610399317,
|
| 1369 |
+
"tokens_seen": 3013214208
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 0.07,
|
| 1373 |
+
"objective/train/docs_used": 1652881,
|
| 1374 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 1375 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 1376 |
+
"objective/train/original_loss": 2.5316507816314697,
|
| 1377 |
+
"objective/train/theoretical_loss": 3.3196282687257583,
|
| 1378 |
+
"objective/train/tokens_used": 43396576,
|
| 1379 |
+
"theoretical_loss": 3.3196282687257583,
|
| 1380 |
+
"tokens_seen": 3013345280
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 0.07,
|
| 1384 |
+
"learning_rate": 0.000935414884516681,
|
| 1385 |
+
"loss": 2.7259,
|
| 1386 |
+
"theoretical_loss": 3.3196282687257583,
|
| 1387 |
+
"tokens_seen": 3013345280
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 0.07,
|
| 1391 |
+
"learning_rate": 0.0009349871685201027,
|
| 1392 |
+
"loss": 2.4882,
|
| 1393 |
+
"theoretical_loss": 3.3196171770291483,
|
| 1394 |
+
"tokens_seen": 3013476352
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 0.07,
|
| 1398 |
+
"learning_rate": 0.0009345594525235244,
|
| 1399 |
+
"loss": 2.6169,
|
| 1400 |
+
"theoretical_loss": 3.3196060859500394,
|
| 1401 |
+
"tokens_seen": 3013607424
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 0.08,
|
| 1405 |
+
"learning_rate": 0.0009341317365269461,
|
| 1406 |
+
"loss": 2.5293,
|
| 1407 |
+
"theoretical_loss": 3.319594995488371,
|
| 1408 |
+
"tokens_seen": 3013738496
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 0.08,
|
| 1412 |
+
"learning_rate": 0.0009337040205303678,
|
| 1413 |
+
"loss": 2.7782,
|
| 1414 |
+
"theoretical_loss": 3.3195839056440812,
|
| 1415 |
+
"tokens_seen": 3013869568
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 0.08,
|
| 1419 |
+
"learning_rate": 0.0009332763045337895,
|
| 1420 |
+
"loss": 2.6719,
|
| 1421 |
+
"theoretical_loss": 3.3195728164171094,
|
| 1422 |
+
"tokens_seen": 3014000640
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"epoch": 0.08,
|
| 1426 |
+
"learning_rate": 0.0009328485885372114,
|
| 1427 |
+
"loss": 2.7268,
|
| 1428 |
+
"theoretical_loss": 3.319561727807394,
|
| 1429 |
+
"tokens_seen": 3014131712
|
| 1430 |
+
},
|
| 1431 |
+
{
|
| 1432 |
+
"epoch": 0.08,
|
| 1433 |
+
"learning_rate": 0.0009324208725406331,
|
| 1434 |
+
"loss": 2.5997,
|
| 1435 |
+
"theoretical_loss": 3.3195506398148744,
|
| 1436 |
+
"tokens_seen": 3014262784
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 0.08,
|
| 1440 |
+
"learning_rate": 0.0009319931565440548,
|
| 1441 |
+
"loss": 2.7602,
|
| 1442 |
+
"theoretical_loss": 3.319539552439489,
|
| 1443 |
+
"tokens_seen": 3014393856
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 0.08,
|
| 1447 |
+
"learning_rate": 0.0009315654405474765,
|
| 1448 |
+
"loss": 2.5845,
|
| 1449 |
+
"theoretical_loss": 3.3195284656811763,
|
| 1450 |
+
"tokens_seen": 3014524928
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 0.08,
|
| 1454 |
+
"learning_rate": 0.0009311377245508982,
|
| 1455 |
+
"loss": 2.7053,
|
| 1456 |
+
"theoretical_loss": 3.319517379539876,
|
| 1457 |
+
"tokens_seen": 3014656000
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 0.08,
|
| 1461 |
+
"learning_rate": 0.00093071000855432,
|
| 1462 |
+
"loss": 2.6045,
|
| 1463 |
+
"theoretical_loss": 3.3195062940155258,
|
| 1464 |
+
"tokens_seen": 3014787072
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 0.08,
|
| 1468 |
+
"learning_rate": 0.0009302822925577416,
|
| 1469 |
+
"loss": 2.6324,
|
| 1470 |
+
"theoretical_loss": 3.3194952091080654,
|
| 1471 |
+
"tokens_seen": 3014918144
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 0.08,
|
| 1475 |
+
"objective/train/docs_used": 1653310,
|
| 1476 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 1477 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 1478 |
+
"objective/train/original_loss": 2.4821465015411377,
|
| 1479 |
+
"objective/train/theoretical_loss": 3.3194896668856497,
|
| 1480 |
+
"objective/train/tokens_used": 45034976,
|
| 1481 |
+
"theoretical_loss": 3.3194896668856497,
|
| 1482 |
+
"tokens_seen": 3014983680
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 0.08,
|
| 1486 |
+
"learning_rate": 0.0009298545765611634,
|
| 1487 |
+
"loss": 2.532,
|
| 1488 |
+
"theoretical_loss": 3.3194841248174334,
|
| 1489 |
+
"tokens_seen": 3015049216
|
| 1490 |
+
},
|
| 1491 |
+
{
|
| 1492 |
+
"epoch": 0.08,
|
| 1493 |
+
"learning_rate": 0.0009294268605645851,
|
| 1494 |
+
"loss": 2.544,
|
| 1495 |
+
"theoretical_loss": 3.3194730411435684,
|
| 1496 |
+
"tokens_seen": 3015180288
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 0.08,
|
| 1500 |
+
"learning_rate": 0.0009289991445680068,
|
| 1501 |
+
"loss": 2.826,
|
| 1502 |
+
"theoretical_loss": 3.3194619580864098,
|
| 1503 |
+
"tokens_seen": 3015311360
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 0.08,
|
| 1507 |
+
"learning_rate": 0.0009285714285714287,
|
| 1508 |
+
"loss": 2.7561,
|
| 1509 |
+
"theoretical_loss": 3.3194508756458965,
|
| 1510 |
+
"tokens_seen": 3015442432
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"epoch": 0.08,
|
| 1514 |
+
"learning_rate": 0.0009281437125748503,
|
| 1515 |
+
"loss": 2.5692,
|
| 1516 |
+
"theoretical_loss": 3.319439793821967,
|
| 1517 |
+
"tokens_seen": 3015573504
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 0.08,
|
| 1521 |
+
"learning_rate": 0.000927715996578272,
|
| 1522 |
+
"loss": 2.6322,
|
| 1523 |
+
"theoretical_loss": 3.3194287126145596,
|
| 1524 |
+
"tokens_seen": 3015704576
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 0.08,
|
| 1528 |
+
"learning_rate": 0.0009272882805816938,
|
| 1529 |
+
"loss": 2.6346,
|
| 1530 |
+
"theoretical_loss": 3.3194176320236144,
|
| 1531 |
+
"tokens_seen": 3015835648
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 0.08,
|
| 1535 |
+
"learning_rate": 0.0009268605645851155,
|
| 1536 |
+
"loss": 2.7908,
|
| 1537 |
+
"theoretical_loss": 3.31940655204907,
|
| 1538 |
+
"tokens_seen": 3015966720
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 0.08,
|
| 1542 |
+
"learning_rate": 0.0009264328485885373,
|
| 1543 |
+
"loss": 2.6439,
|
| 1544 |
+
"theoretical_loss": 3.319395472690865,
|
| 1545 |
+
"tokens_seen": 3016097792
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 0.08,
|
| 1549 |
+
"learning_rate": 0.0009260051325919589,
|
| 1550 |
+
"loss": 2.5589,
|
| 1551 |
+
"theoretical_loss": 3.3193843939489382,
|
| 1552 |
+
"tokens_seen": 3016228864
|
| 1553 |
+
},
|
| 1554 |
+
{
|
| 1555 |
+
"epoch": 0.08,
|
| 1556 |
+
"learning_rate": 0.0009255774165953806,
|
| 1557 |
+
"loss": 2.6926,
|
| 1558 |
+
"theoretical_loss": 3.319373315823229,
|
| 1559 |
+
"tokens_seen": 3016359936
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 0.08,
|
| 1563 |
+
"learning_rate": 0.0009251497005988024,
|
| 1564 |
+
"loss": 2.7646,
|
| 1565 |
+
"theoretical_loss": 3.3193622383136763,
|
| 1566 |
+
"tokens_seen": 3016491008
|
| 1567 |
+
},
|
| 1568 |
+
{
|
| 1569 |
+
"epoch": 0.08,
|
| 1570 |
+
"objective/train/docs_used": 1654644,
|
| 1571 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 1572 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 1573 |
+
"objective/train/original_loss": 2.3390886783599854,
|
| 1574 |
+
"objective/train/theoretical_loss": 3.3193511614202187,
|
| 1575 |
+
"objective/train/tokens_used": 46673376,
|
| 1576 |
+
"theoretical_loss": 3.3193511614202187,
|
| 1577 |
+
"tokens_seen": 3016622080
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.08,
|
| 1581 |
+
"learning_rate": 0.0009247219846022242,
|
| 1582 |
+
"loss": 2.5287,
|
| 1583 |
+
"theoretical_loss": 3.3193511614202187,
|
| 1584 |
+
"tokens_seen": 3016622080
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.09,
|
| 1588 |
+
"learning_rate": 0.000924294268605646,
|
| 1589 |
+
"loss": 2.7607,
|
| 1590 |
+
"theoretical_loss": 3.319340085142796,
|
| 1591 |
+
"tokens_seen": 3016753152
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.09,
|
| 1595 |
+
"learning_rate": 0.0009238665526090676,
|
| 1596 |
+
"loss": 2.6289,
|
| 1597 |
+
"theoretical_loss": 3.319329009481346,
|
| 1598 |
+
"tokens_seen": 3016884224
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.09,
|
| 1602 |
+
"learning_rate": 0.0009234388366124893,
|
| 1603 |
+
"loss": 2.7648,
|
| 1604 |
+
"theoretical_loss": 3.3193179344358086,
|
| 1605 |
+
"tokens_seen": 3017015296
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.09,
|
| 1609 |
+
"learning_rate": 0.0009230111206159111,
|
| 1610 |
+
"loss": 2.497,
|
| 1611 |
+
"theoretical_loss": 3.319306860006122,
|
| 1612 |
+
"tokens_seen": 3017146368
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.09,
|
| 1616 |
+
"learning_rate": 0.0009225834046193328,
|
| 1617 |
+
"loss": 2.4963,
|
| 1618 |
+
"theoretical_loss": 3.319295786192226,
|
| 1619 |
+
"tokens_seen": 3017277440
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.09,
|
| 1623 |
+
"learning_rate": 0.0009221556886227545,
|
| 1624 |
+
"loss": 2.5823,
|
| 1625 |
+
"theoretical_loss": 3.319284712994059,
|
| 1626 |
+
"tokens_seen": 3017408512
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.09,
|
| 1630 |
+
"learning_rate": 0.0009217279726261762,
|
| 1631 |
+
"loss": 2.6555,
|
| 1632 |
+
"theoretical_loss": 3.3192736404115606,
|
| 1633 |
+
"tokens_seen": 3017539584
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.09,
|
| 1637 |
+
"learning_rate": 0.0009213002566295979,
|
| 1638 |
+
"loss": 2.5264,
|
| 1639 |
+
"theoretical_loss": 3.3192625684446693,
|
| 1640 |
+
"tokens_seen": 3017670656
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.09,
|
| 1644 |
+
"learning_rate": 0.0009208725406330197,
|
| 1645 |
+
"loss": 2.397,
|
| 1646 |
+
"theoretical_loss": 3.3192514970933242,
|
| 1647 |
+
"tokens_seen": 3017801728
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.09,
|
| 1651 |
+
"learning_rate": 0.0009204448246364415,
|
| 1652 |
+
"loss": 2.6273,
|
| 1653 |
+
"theoretical_loss": 3.319240426357465,
|
| 1654 |
+
"tokens_seen": 3017932800
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.09,
|
| 1658 |
+
"learning_rate": 0.0009200171086398631,
|
| 1659 |
+
"loss": 2.6414,
|
| 1660 |
+
"theoretical_loss": 3.31922935623703,
|
| 1661 |
+
"tokens_seen": 3018063872
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.09,
|
| 1665 |
+
"learning_rate": 0.0009195893926432849,
|
| 1666 |
+
"loss": 2.5706,
|
| 1667 |
+
"theoretical_loss": 3.3192182867319584,
|
| 1668 |
+
"tokens_seen": 3018194944
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.09,
|
| 1672 |
+
"objective/train/docs_used": 1655335,
|
| 1673 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 1674 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 1675 |
+
"objective/train/original_loss": 2.3051180839538574,
|
| 1676 |
+
"objective/train/theoretical_loss": 3.319212752210165,
|
| 1677 |
+
"objective/train/tokens_used": 48311776,
|
| 1678 |
+
"theoretical_loss": 3.319212752210165,
|
| 1679 |
+
"tokens_seen": 3018260480
|
| 1680 |
+
},
|
| 1681 |
+
{
|
| 1682 |
+
"epoch": 0.09,
|
| 1683 |
+
"learning_rate": 0.0009191616766467066,
|
| 1684 |
+
"loss": 2.5393,
|
| 1685 |
+
"theoretical_loss": 3.3192072178421896,
|
| 1686 |
+
"tokens_seen": 3018326016
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 0.09,
|
| 1690 |
+
"learning_rate": 0.0009187339606501284,
|
| 1691 |
+
"loss": 2.6545,
|
| 1692 |
+
"theoretical_loss": 3.319196149567662,
|
| 1693 |
+
"tokens_seen": 3018457088
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 0.09,
|
| 1697 |
+
"learning_rate": 0.00091830624465355,
|
| 1698 |
+
"loss": 2.5623,
|
| 1699 |
+
"theoretical_loss": 3.3191850819083157,
|
| 1700 |
+
"tokens_seen": 3018588160
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 0.09,
|
| 1704 |
+
"learning_rate": 0.0009178785286569717,
|
| 1705 |
+
"loss": 2.6804,
|
| 1706 |
+
"theoretical_loss": 3.319174014864089,
|
| 1707 |
+
"tokens_seen": 3018719232
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 0.09,
|
| 1711 |
+
"learning_rate": 0.0009174508126603935,
|
| 1712 |
+
"loss": 2.8051,
|
| 1713 |
+
"theoretical_loss": 3.319162948434921,
|
| 1714 |
+
"tokens_seen": 3018850304
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 0.09,
|
| 1718 |
+
"learning_rate": 0.0009170230966638152,
|
| 1719 |
+
"loss": 2.7044,
|
| 1720 |
+
"theoretical_loss": 3.319151882620752,
|
| 1721 |
+
"tokens_seen": 3018981376
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 0.09,
|
| 1725 |
+
"learning_rate": 0.0009165953806672371,
|
| 1726 |
+
"loss": 2.5421,
|
| 1727 |
+
"theoretical_loss": 3.3191408174215193,
|
| 1728 |
+
"tokens_seen": 3019112448
|
| 1729 |
+
},
|
| 1730 |
+
{
|
| 1731 |
+
"epoch": 0.09,
|
| 1732 |
+
"learning_rate": 0.0009161676646706587,
|
| 1733 |
+
"loss": 2.7474,
|
| 1734 |
+
"theoretical_loss": 3.3191297528371635,
|
| 1735 |
+
"tokens_seen": 3019243520
|
| 1736 |
+
},
|
| 1737 |
+
{
|
| 1738 |
+
"epoch": 0.09,
|
| 1739 |
+
"learning_rate": 0.0009157399486740804,
|
| 1740 |
+
"loss": 2.5804,
|
| 1741 |
+
"theoretical_loss": 3.319118688867623,
|
| 1742 |
+
"tokens_seen": 3019374592
|
| 1743 |
+
},
|
| 1744 |
+
{
|
| 1745 |
+
"epoch": 0.09,
|
| 1746 |
+
"learning_rate": 0.0009153122326775022,
|
| 1747 |
+
"loss": 2.5145,
|
| 1748 |
+
"theoretical_loss": 3.319107625512837,
|
| 1749 |
+
"tokens_seen": 3019505664
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 0.09,
|
| 1753 |
+
"learning_rate": 0.0009148845166809239,
|
| 1754 |
+
"loss": 2.746,
|
| 1755 |
+
"theoretical_loss": 3.3190965627727445,
|
| 1756 |
+
"tokens_seen": 3019636736
|
| 1757 |
+
},
|
| 1758 |
+
{
|
| 1759 |
+
"epoch": 0.09,
|
| 1760 |
+
"learning_rate": 0.0009144568006843457,
|
| 1761 |
+
"loss": 2.5949,
|
| 1762 |
+
"theoretical_loss": 3.3190855006472857,
|
| 1763 |
+
"tokens_seen": 3019767808
|
| 1764 |
+
},
|
| 1765 |
+
{
|
| 1766 |
+
"epoch": 0.09,
|
| 1767 |
+
"objective/train/docs_used": 1656670,
|
| 1768 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 1769 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 1770 |
+
"objective/train/original_loss": 2.1859257221221924,
|
| 1771 |
+
"objective/train/theoretical_loss": 3.3190744391363984,
|
| 1772 |
+
"objective/train/tokens_used": 49950176,
|
| 1773 |
+
"theoretical_loss": 3.3190744391363984,
|
| 1774 |
+
"tokens_seen": 3019898880
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 0.1,
|
| 1778 |
+
"learning_rate": 0.0009140290846877673,
|
| 1779 |
+
"loss": 2.6334,
|
| 1780 |
+
"theoretical_loss": 3.3190744391363984,
|
| 1781 |
+
"tokens_seen": 3019898880
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 0.1,
|
| 1785 |
+
"learning_rate": 0.000913601368691189,
|
| 1786 |
+
"loss": 2.6976,
|
| 1787 |
+
"theoretical_loss": 3.3190633782400223,
|
| 1788 |
+
"tokens_seen": 3020029952
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 0.1,
|
| 1792 |
+
"learning_rate": 0.0009131736526946108,
|
| 1793 |
+
"loss": 2.5658,
|
| 1794 |
+
"theoretical_loss": 3.3190523179580973,
|
| 1795 |
+
"tokens_seen": 3020161024
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.1,
|
| 1799 |
+
"learning_rate": 0.0009127459366980325,
|
| 1800 |
+
"loss": 2.7495,
|
| 1801 |
+
"theoretical_loss": 3.3190412582905617,
|
| 1802 |
+
"tokens_seen": 3020292096
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.1,
|
| 1806 |
+
"learning_rate": 0.0009123182207014543,
|
| 1807 |
+
"loss": 2.7093,
|
| 1808 |
+
"theoretical_loss": 3.319030199237355,
|
| 1809 |
+
"tokens_seen": 3020423168
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.1,
|
| 1813 |
+
"learning_rate": 0.000911890504704876,
|
| 1814 |
+
"loss": 2.5295,
|
| 1815 |
+
"theoretical_loss": 3.3190191407984164,
|
| 1816 |
+
"tokens_seen": 3020554240
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.1,
|
| 1820 |
+
"learning_rate": 0.0009114627887082977,
|
| 1821 |
+
"loss": 2.6081,
|
| 1822 |
+
"theoretical_loss": 3.3190080829736854,
|
| 1823 |
+
"tokens_seen": 3020685312
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 0.1,
|
| 1827 |
+
"learning_rate": 0.0009110350727117195,
|
| 1828 |
+
"loss": 2.6166,
|
| 1829 |
+
"theoretical_loss": 3.318997025763101,
|
| 1830 |
+
"tokens_seen": 3020816384
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 0.1,
|
| 1834 |
+
"learning_rate": 0.0009106073567151412,
|
| 1835 |
+
"loss": 2.7691,
|
| 1836 |
+
"theoretical_loss": 3.318985969166602,
|
| 1837 |
+
"tokens_seen": 3020947456
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 0.1,
|
| 1841 |
+
"learning_rate": 0.0009101796407185628,
|
| 1842 |
+
"loss": 2.6465,
|
| 1843 |
+
"theoretical_loss": 3.3189749131841286,
|
| 1844 |
+
"tokens_seen": 3021078528
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 0.1,
|
| 1848 |
+
"learning_rate": 0.0009097519247219846,
|
| 1849 |
+
"loss": 2.5314,
|
| 1850 |
+
"theoretical_loss": 3.3189638578156195,
|
| 1851 |
+
"tokens_seen": 3021209600
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 0.1,
|
| 1855 |
+
"learning_rate": 0.0009093242087254063,
|
| 1856 |
+
"loss": 2.8726,
|
| 1857 |
+
"theoretical_loss": 3.3189528030610136,
|
| 1858 |
+
"tokens_seen": 3021340672
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 0.1,
|
| 1862 |
+
"learning_rate": 0.0009088964927288281,
|
| 1863 |
+
"loss": 2.6762,
|
| 1864 |
+
"theoretical_loss": 3.318941748920251,
|
| 1865 |
+
"tokens_seen": 3021471744
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 0.1,
|
| 1869 |
+
"objective/train/docs_used": 1657192,
|
| 1870 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 1871 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 1872 |
+
"objective/train/original_loss": 2.9018635749816895,
|
| 1873 |
+
"objective/train/theoretical_loss": 3.318936222080042,
|
| 1874 |
+
"objective/train/tokens_used": 51588576,
|
| 1875 |
+
"theoretical_loss": 3.318936222080042,
|
| 1876 |
+
"tokens_seen": 3021537280
|
| 1877 |
+
},
|
| 1878 |
+
{
|
| 1879 |
+
"epoch": 0.1,
|
| 1880 |
+
"learning_rate": 0.0009084687767322499,
|
| 1881 |
+
"loss": 2.643,
|
| 1882 |
+
"theoretical_loss": 3.318930695393271,
|
| 1883 |
+
"tokens_seen": 3021602816
|
| 1884 |
+
},
|
| 1885 |
+
{
|
| 1886 |
+
"epoch": 0.1,
|
| 1887 |
+
"learning_rate": 0.0009080410607356715,
|
| 1888 |
+
"loss": 2.6665,
|
| 1889 |
+
"theoretical_loss": 3.3189196424800116,
|
| 1890 |
+
"tokens_seen": 3021733888
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"epoch": 0.1,
|
| 1894 |
+
"learning_rate": 0.0009076133447390933,
|
| 1895 |
+
"loss": 2.6265,
|
| 1896 |
+
"theoretical_loss": 3.3189085901804134,
|
| 1897 |
+
"tokens_seen": 3021864960
|
| 1898 |
+
},
|
| 1899 |
+
{
|
| 1900 |
+
"epoch": 0.1,
|
| 1901 |
+
"learning_rate": 0.000907185628742515,
|
| 1902 |
+
"loss": 2.5788,
|
| 1903 |
+
"theoretical_loss": 3.3188975384944155,
|
| 1904 |
+
"tokens_seen": 3021996032
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 0.1,
|
| 1908 |
+
"learning_rate": 0.0009067579127459367,
|
| 1909 |
+
"loss": 2.6531,
|
| 1910 |
+
"theoretical_loss": 3.318886487421957,
|
| 1911 |
+
"tokens_seen": 3022127104
|
| 1912 |
+
},
|
| 1913 |
+
{
|
| 1914 |
+
"epoch": 0.1,
|
| 1915 |
+
"learning_rate": 0.0009063301967493585,
|
| 1916 |
+
"loss": 2.7177,
|
| 1917 |
+
"theoretical_loss": 3.318875436962977,
|
| 1918 |
+
"tokens_seen": 3022258176
|
| 1919 |
+
},
|
| 1920 |
+
{
|
| 1921 |
+
"epoch": 0.1,
|
| 1922 |
+
"learning_rate": 0.0009059024807527801,
|
| 1923 |
+
"loss": 2.4989,
|
| 1924 |
+
"theoretical_loss": 3.3188643871174155,
|
| 1925 |
+
"tokens_seen": 3022389248
|
| 1926 |
+
},
|
| 1927 |
+
{
|
| 1928 |
+
"epoch": 0.1,
|
| 1929 |
+
"learning_rate": 0.0009054747647562019,
|
| 1930 |
+
"loss": 2.5249,
|
| 1931 |
+
"theoretical_loss": 3.318853337885211,
|
| 1932 |
+
"tokens_seen": 3022520320
|
| 1933 |
+
},
|
| 1934 |
+
{
|
| 1935 |
+
"epoch": 0.1,
|
| 1936 |
+
"learning_rate": 0.0009050470487596236,
|
| 1937 |
+
"loss": 2.6031,
|
| 1938 |
+
"theoretical_loss": 3.318842289266304,
|
| 1939 |
+
"tokens_seen": 3022651392
|
| 1940 |
+
},
|
| 1941 |
+
{
|
| 1942 |
+
"epoch": 0.1,
|
| 1943 |
+
"learning_rate": 0.0009046193327630453,
|
| 1944 |
+
"loss": 2.5702,
|
| 1945 |
+
"theoretical_loss": 3.3188312412606327,
|
| 1946 |
+
"tokens_seen": 3022782464
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 0.1,
|
| 1950 |
+
"learning_rate": 0.0009041916167664672,
|
| 1951 |
+
"loss": 2.5348,
|
| 1952 |
+
"theoretical_loss": 3.3188201938681368,
|
| 1953 |
+
"tokens_seen": 3022913536
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 0.11,
|
| 1957 |
+
"learning_rate": 0.0009037639007698888,
|
| 1958 |
+
"loss": 2.5876,
|
| 1959 |
+
"theoretical_loss": 3.318809147088756,
|
| 1960 |
+
"tokens_seen": 3023044608
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"epoch": 0.11,
|
| 1964 |
+
"objective/train/docs_used": 1658380,
|
| 1965 |
+
"objective/train/instantaneous_batch_size": 16,
|
| 1966 |
+
"objective/train/instantaneous_microbatch_size": 16384,
|
| 1967 |
+
"objective/train/original_loss": 2.8608322143554688,
|
| 1968 |
+
"objective/train/theoretical_loss": 3.3187981009224297,
|
| 1969 |
+
"objective/train/tokens_used": 53226976,
|
| 1970 |
+
"theoretical_loss": 3.3187981009224297,
|
| 1971 |
+
"tokens_seen": 3023175680
|
| 1972 |
+
},
|
| 1973 |
+
{
|
| 1974 |
+
"epoch": 0.11,
|
| 1975 |
+
"learning_rate": 0.0009033361847733106,
|
| 1976 |
+
"loss": 2.6644,
|
| 1977 |
+
"theoretical_loss": 3.3187981009224297,
|
| 1978 |
+
"tokens_seen": 3023175680
|
| 1979 |
+
},
|
| 1980 |
+
{
|
| 1981 |
+
"epoch": 0.11,
|
| 1982 |
+
"learning_rate": 0.0009029084687767323,
|
| 1983 |
+
"loss": 2.5824,
|
| 1984 |
+
"theoretical_loss": 3.3187870553690972,
|
| 1985 |
+
"tokens_seen": 3023306752
|
| 1986 |
+
}
|
| 1987 |
+
],
|
| 1988 |
+
"max_steps": 2362,
|
| 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 sha256:038f7f52bfd7053e27b91ec9656d72c84a01243a9b1efc287719bc9559af4e0c
|
| 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/cranky_lichterman",
|
| 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 sha256:3d78be75f82659b11d1b158f6a73b1cce48f4bf7e544d395de4254de03c56532
|
| 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 sha256:038f7f52bfd7053e27b91ec9656d72c84a01243a9b1efc287719bc9559af4e0c
|
| 3 |
+
size 3375
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|