Upload folder using huggingface_hub
Browse files- checkpoint-625/optimizer.pt +3 -0
- checkpoint-625/pytorch_model.bin +3 -0
- checkpoint-625/rng_state_0.pth +3 -0
- checkpoint-625/rng_state_1.pth +3 -0
- checkpoint-625/rng_state_2.pth +3 -0
- checkpoint-625/rng_state_3.pth +3 -0
- checkpoint-625/rng_state_4.pth +3 -0
- checkpoint-625/rng_state_5.pth +3 -0
- checkpoint-625/rng_state_6.pth +3 -0
- checkpoint-625/rng_state_7.pth +3 -0
- checkpoint-625/scheduler.pt +3 -0
- checkpoint-625/special_tokens_map.json +37 -0
- checkpoint-625/tokenizer.json +0 -0
- checkpoint-625/tokenizer_config.json +53 -0
- checkpoint-625/trainer_state.json +2565 -0
- checkpoint-625/training_args.bin +3 -0
checkpoint-625/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7a592eeadbb799a324f38e5e4009de29644e148a4a689a13b0f5d789c3ce1cf
|
| 3 |
+
size 569086987
|
checkpoint-625/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:478e40b3f683eae3d844e37c07791eb884b2cf21846ab2c7aa5d2928d5fa55e7
|
| 3 |
+
size 284546819
|
checkpoint-625/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc7a5d9ca652a5bd1d04349d77fd0f56f8f1775e1b00b5cc5176468e017ac92a
|
| 3 |
+
size 16389
|
checkpoint-625/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3bd450366f4274a04e6d5dd0754dcf816f88f65b85ed9c88a1d081c89aada859
|
| 3 |
+
size 16389
|
checkpoint-625/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a77d0583487d8cfff2e76df0532730c5485b42767b1ed8f4969f22094d840e3
|
| 3 |
+
size 16389
|
checkpoint-625/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dfc063696020bbba4af73e5ff59ec7700b0b1cdad96c500dc21ee7ad1944a49f
|
| 3 |
+
size 16389
|
checkpoint-625/rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6eef58bc47946544af1ba531a8c236e1942654ee216ea13ace82cce27989f69
|
| 3 |
+
size 16389
|
checkpoint-625/rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1817a933eaa47c02483f98f317c6922afa277826ec0331b0e7b317b1a450ede
|
| 3 |
+
size 16389
|
checkpoint-625/rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9879f2fc500918bc865d70f89366cd6d137a38668bd679637ef9fb550fc7ed7a
|
| 3 |
+
size 16389
|
checkpoint-625/rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6dbd587ebbf015d1ccd7042d123702b4ff325bb586cf67ebe78a6992b029aa9a
|
| 3 |
+
size 16389
|
checkpoint-625/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0c69c2f7d49931369f163a83c384510a500520dde39b00a190ce1015cc8ad0d
|
| 3 |
+
size 1465
|
checkpoint-625/special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
checkpoint-625/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-625/tokenizer_config.json
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[UNK]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[PAD]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"extra_special_tokens": {},
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 52 |
+
"unk_token": "[UNK]"
|
| 53 |
+
}
|
checkpoint-625/trainer_state.json
ADDED
|
@@ -0,0 +1,2565 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 625,
|
| 3 |
+
"best_metric": 5.630118370056152,
|
| 4 |
+
"best_model_checkpoint": "/gpfs/scratch/guoh/DNAFM/output/gencode_human_12.8k_12800/Gencode-BPE/checkpoint-625",
|
| 5 |
+
"epoch": 0.1773049645390071,
|
| 6 |
+
"eval_steps": 125,
|
| 7 |
+
"global_step": 625,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0005673758865248227,
|
| 14 |
+
"grad_norm": 1275.0146484375,
|
| 15 |
+
"loss": 281.4781,
|
| 16 |
+
"lr": 2e-06,
|
| 17 |
+
"step": 2,
|
| 18 |
+
"tokens_trained": 0.000192256
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.0011347517730496454,
|
| 22 |
+
"grad_norm": 1437.579833984375,
|
| 23 |
+
"loss": 267.2211,
|
| 24 |
+
"lr": 6e-06,
|
| 25 |
+
"step": 4,
|
| 26 |
+
"tokens_trained": 0.000382024
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.001702127659574468,
|
| 30 |
+
"grad_norm": 1719.271484375,
|
| 31 |
+
"loss": 219.3822,
|
| 32 |
+
"lr": 1e-05,
|
| 33 |
+
"step": 6,
|
| 34 |
+
"tokens_trained": 0.00057072
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.0022695035460992908,
|
| 38 |
+
"grad_norm": 1444.94970703125,
|
| 39 |
+
"loss": 133.8172,
|
| 40 |
+
"lr": 1.4e-05,
|
| 41 |
+
"step": 8,
|
| 42 |
+
"tokens_trained": 0.000761336
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.0028368794326241137,
|
| 46 |
+
"grad_norm": 238.9689178466797,
|
| 47 |
+
"loss": 90.8177,
|
| 48 |
+
"lr": 1.8e-05,
|
| 49 |
+
"step": 10,
|
| 50 |
+
"tokens_trained": 0.000953248
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.003404255319148936,
|
| 54 |
+
"grad_norm": 158.53497314453125,
|
| 55 |
+
"loss": 84.6922,
|
| 56 |
+
"lr": 2.2e-05,
|
| 57 |
+
"step": 12,
|
| 58 |
+
"tokens_trained": 0.00114424
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.003971631205673759,
|
| 62 |
+
"grad_norm": 146.10595703125,
|
| 63 |
+
"loss": 76.7055,
|
| 64 |
+
"lr": 2.6e-05,
|
| 65 |
+
"step": 14,
|
| 66 |
+
"tokens_trained": 0.001334104
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.0045390070921985815,
|
| 70 |
+
"grad_norm": 140.69964599609375,
|
| 71 |
+
"loss": 67.9952,
|
| 72 |
+
"lr": 3e-05,
|
| 73 |
+
"step": 16,
|
| 74 |
+
"tokens_trained": 0.00152392
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.005106382978723404,
|
| 78 |
+
"grad_norm": 108.80303192138672,
|
| 79 |
+
"loss": 57.8088,
|
| 80 |
+
"lr": 3.4000000000000007e-05,
|
| 81 |
+
"step": 18,
|
| 82 |
+
"tokens_trained": 0.001713872
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.005673758865248227,
|
| 86 |
+
"grad_norm": 106.82334899902344,
|
| 87 |
+
"loss": 48.6585,
|
| 88 |
+
"lr": 3.8e-05,
|
| 89 |
+
"step": 20,
|
| 90 |
+
"tokens_trained": 0.001903976
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.00624113475177305,
|
| 94 |
+
"grad_norm": 93.58769989013672,
|
| 95 |
+
"loss": 41.7984,
|
| 96 |
+
"lr": 4.2000000000000004e-05,
|
| 97 |
+
"step": 22,
|
| 98 |
+
"tokens_trained": 0.002094288
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.006808510638297872,
|
| 102 |
+
"grad_norm": 87.5854721069336,
|
| 103 |
+
"loss": 37.6201,
|
| 104 |
+
"lr": 4.6e-05,
|
| 105 |
+
"step": 24,
|
| 106 |
+
"tokens_trained": 0.002282496
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.007375886524822695,
|
| 110 |
+
"grad_norm": 84.12794494628906,
|
| 111 |
+
"loss": 35.0091,
|
| 112 |
+
"lr": 5e-05,
|
| 113 |
+
"step": 26,
|
| 114 |
+
"tokens_trained": 0.00247068
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.007943262411347518,
|
| 118 |
+
"grad_norm": 79.77535247802734,
|
| 119 |
+
"loss": 33.2253,
|
| 120 |
+
"lr": 5.4e-05,
|
| 121 |
+
"step": 28,
|
| 122 |
+
"tokens_trained": 0.002662888
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.00851063829787234,
|
| 126 |
+
"grad_norm": 66.42157745361328,
|
| 127 |
+
"loss": 32.0682,
|
| 128 |
+
"lr": 5.800000000000001e-05,
|
| 129 |
+
"step": 30,
|
| 130 |
+
"tokens_trained": 0.002851968
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.009078014184397163,
|
| 134 |
+
"grad_norm": 87.52485656738281,
|
| 135 |
+
"loss": 30.893,
|
| 136 |
+
"lr": 6.2e-05,
|
| 137 |
+
"step": 32,
|
| 138 |
+
"tokens_trained": 0.003041384
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.009645390070921986,
|
| 142 |
+
"grad_norm": 58.33614730834961,
|
| 143 |
+
"loss": 30.0513,
|
| 144 |
+
"lr": 6.6e-05,
|
| 145 |
+
"step": 34,
|
| 146 |
+
"tokens_trained": 0.003232872
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.010212765957446808,
|
| 150 |
+
"grad_norm": 54.629329681396484,
|
| 151 |
+
"loss": 29.0115,
|
| 152 |
+
"lr": 7.000000000000001e-05,
|
| 153 |
+
"step": 36,
|
| 154 |
+
"tokens_trained": 0.003423824
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.01078014184397163,
|
| 158 |
+
"grad_norm": 52.79097366333008,
|
| 159 |
+
"loss": 28.2084,
|
| 160 |
+
"lr": 7.4e-05,
|
| 161 |
+
"step": 38,
|
| 162 |
+
"tokens_trained": 0.003613232
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.011347517730496455,
|
| 166 |
+
"grad_norm": 54.481224060058594,
|
| 167 |
+
"loss": 27.4345,
|
| 168 |
+
"lr": 7.8e-05,
|
| 169 |
+
"step": 40,
|
| 170 |
+
"tokens_trained": 0.003800952
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.011914893617021277,
|
| 174 |
+
"grad_norm": 58.7069091796875,
|
| 175 |
+
"loss": 26.5936,
|
| 176 |
+
"lr": 8.2e-05,
|
| 177 |
+
"step": 42,
|
| 178 |
+
"tokens_trained": 0.003991512
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.0124822695035461,
|
| 182 |
+
"grad_norm": 49.30760955810547,
|
| 183 |
+
"loss": 26.0608,
|
| 184 |
+
"lr": 8.599999999999999e-05,
|
| 185 |
+
"step": 44,
|
| 186 |
+
"tokens_trained": 0.004180648
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.013049645390070922,
|
| 190 |
+
"grad_norm": 61.902587890625,
|
| 191 |
+
"loss": 25.5363,
|
| 192 |
+
"lr": 8.999999999999999e-05,
|
| 193 |
+
"step": 46,
|
| 194 |
+
"tokens_trained": 0.00437148
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.013617021276595745,
|
| 198 |
+
"grad_norm": 46.76111602783203,
|
| 199 |
+
"loss": 24.9599,
|
| 200 |
+
"lr": 9.400000000000001e-05,
|
| 201 |
+
"step": 48,
|
| 202 |
+
"tokens_trained": 0.004559344
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.014184397163120567,
|
| 206 |
+
"grad_norm": 57.06416702270508,
|
| 207 |
+
"loss": 24.4087,
|
| 208 |
+
"lr": 9.800000000000001e-05,
|
| 209 |
+
"step": 50,
|
| 210 |
+
"tokens_trained": 0.004749256
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.01475177304964539,
|
| 214 |
+
"grad_norm": 44.798736572265625,
|
| 215 |
+
"loss": 24.1444,
|
| 216 |
+
"lr": 0.000102,
|
| 217 |
+
"step": 52,
|
| 218 |
+
"tokens_trained": 0.004940192
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.015319148936170212,
|
| 222 |
+
"grad_norm": 40.29296875,
|
| 223 |
+
"loss": 23.6011,
|
| 224 |
+
"lr": 0.000106,
|
| 225 |
+
"step": 54,
|
| 226 |
+
"tokens_trained": 0.005130304
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.015886524822695036,
|
| 230 |
+
"grad_norm": 38.75099563598633,
|
| 231 |
+
"loss": 23.1781,
|
| 232 |
+
"lr": 0.00011,
|
| 233 |
+
"step": 56,
|
| 234 |
+
"tokens_trained": 0.005322864
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.016453900709219857,
|
| 238 |
+
"grad_norm": 37.470706939697266,
|
| 239 |
+
"loss": 22.9136,
|
| 240 |
+
"lr": 0.000114,
|
| 241 |
+
"step": 58,
|
| 242 |
+
"tokens_trained": 0.00551392
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.01702127659574468,
|
| 246 |
+
"grad_norm": 35.1894645690918,
|
| 247 |
+
"loss": 22.6336,
|
| 248 |
+
"lr": 0.000118,
|
| 249 |
+
"step": 60,
|
| 250 |
+
"tokens_trained": 0.005703096
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.017588652482269502,
|
| 254 |
+
"grad_norm": 35.136573791503906,
|
| 255 |
+
"loss": 22.2998,
|
| 256 |
+
"lr": 0.000122,
|
| 257 |
+
"step": 62,
|
| 258 |
+
"tokens_trained": 0.005892448
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.018156028368794326,
|
| 262 |
+
"grad_norm": 38.05111312866211,
|
| 263 |
+
"loss": 21.9401,
|
| 264 |
+
"lr": 0.000126,
|
| 265 |
+
"step": 64,
|
| 266 |
+
"tokens_trained": 0.006081656
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.01872340425531915,
|
| 270 |
+
"grad_norm": 35.63850021362305,
|
| 271 |
+
"loss": 21.7206,
|
| 272 |
+
"lr": 0.00013000000000000002,
|
| 273 |
+
"step": 66,
|
| 274 |
+
"tokens_trained": 0.006273032
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.01929078014184397,
|
| 278 |
+
"grad_norm": 34.327667236328125,
|
| 279 |
+
"loss": 21.4051,
|
| 280 |
+
"lr": 0.000134,
|
| 281 |
+
"step": 68,
|
| 282 |
+
"tokens_trained": 0.00646304
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.019858156028368795,
|
| 286 |
+
"grad_norm": 31.457059860229492,
|
| 287 |
+
"loss": 21.0774,
|
| 288 |
+
"lr": 0.00013800000000000002,
|
| 289 |
+
"step": 70,
|
| 290 |
+
"tokens_trained": 0.006652832
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.020425531914893616,
|
| 294 |
+
"grad_norm": 34.91672897338867,
|
| 295 |
+
"loss": 20.8718,
|
| 296 |
+
"lr": 0.00014199999999999998,
|
| 297 |
+
"step": 72,
|
| 298 |
+
"tokens_trained": 0.006843512
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.02099290780141844,
|
| 302 |
+
"grad_norm": 27.959579467773438,
|
| 303 |
+
"loss": 20.6932,
|
| 304 |
+
"lr": 0.000146,
|
| 305 |
+
"step": 74,
|
| 306 |
+
"tokens_trained": 0.007033584
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.02156028368794326,
|
| 310 |
+
"grad_norm": 26.569866180419922,
|
| 311 |
+
"loss": 20.4072,
|
| 312 |
+
"lr": 0.00015,
|
| 313 |
+
"step": 76,
|
| 314 |
+
"tokens_trained": 0.007224032
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.022127659574468085,
|
| 318 |
+
"grad_norm": 28.009904861450195,
|
| 319 |
+
"loss": 20.2229,
|
| 320 |
+
"lr": 0.000154,
|
| 321 |
+
"step": 78,
|
| 322 |
+
"tokens_trained": 0.00741368
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.02269503546099291,
|
| 326 |
+
"grad_norm": 28.892959594726562,
|
| 327 |
+
"loss": 20.0528,
|
| 328 |
+
"lr": 0.000158,
|
| 329 |
+
"step": 80,
|
| 330 |
+
"tokens_trained": 0.00760416
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.02326241134751773,
|
| 334 |
+
"grad_norm": 31.58131980895996,
|
| 335 |
+
"loss": 19.8016,
|
| 336 |
+
"lr": 0.000162,
|
| 337 |
+
"step": 82,
|
| 338 |
+
"tokens_trained": 0.007793952
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.023829787234042554,
|
| 342 |
+
"grad_norm": 31.01254653930664,
|
| 343 |
+
"loss": 19.634,
|
| 344 |
+
"lr": 0.00016600000000000002,
|
| 345 |
+
"step": 84,
|
| 346 |
+
"tokens_trained": 0.007980792
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.024397163120567375,
|
| 350 |
+
"grad_norm": 28.732515335083008,
|
| 351 |
+
"loss": 19.3777,
|
| 352 |
+
"lr": 0.00017,
|
| 353 |
+
"step": 86,
|
| 354 |
+
"tokens_trained": 0.008171968
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.0249645390070922,
|
| 358 |
+
"grad_norm": 24.31264877319336,
|
| 359 |
+
"loss": 19.1346,
|
| 360 |
+
"lr": 0.000174,
|
| 361 |
+
"step": 88,
|
| 362 |
+
"tokens_trained": 0.008361632
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.02553191489361702,
|
| 366 |
+
"grad_norm": 26.557010650634766,
|
| 367 |
+
"loss": 19.0014,
|
| 368 |
+
"lr": 0.000178,
|
| 369 |
+
"step": 90,
|
| 370 |
+
"tokens_trained": 0.008552328
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.026099290780141844,
|
| 374 |
+
"grad_norm": 21.156103134155273,
|
| 375 |
+
"loss": 18.7032,
|
| 376 |
+
"lr": 0.000182,
|
| 377 |
+
"step": 92,
|
| 378 |
+
"tokens_trained": 0.008743136
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.02666666666666667,
|
| 382 |
+
"grad_norm": 25.7484188079834,
|
| 383 |
+
"loss": 18.4836,
|
| 384 |
+
"lr": 0.000186,
|
| 385 |
+
"step": 94,
|
| 386 |
+
"tokens_trained": 0.008932056
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.02723404255319149,
|
| 390 |
+
"grad_norm": 22.27949333190918,
|
| 391 |
+
"loss": 18.2233,
|
| 392 |
+
"lr": 0.00019,
|
| 393 |
+
"step": 96,
|
| 394 |
+
"tokens_trained": 0.009121608
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.027801418439716313,
|
| 398 |
+
"grad_norm": 24.9247989654541,
|
| 399 |
+
"loss": 17.9867,
|
| 400 |
+
"lr": 0.000194,
|
| 401 |
+
"step": 98,
|
| 402 |
+
"tokens_trained": 0.009311008
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.028368794326241134,
|
| 406 |
+
"grad_norm": 24.302066802978516,
|
| 407 |
+
"loss": 17.8016,
|
| 408 |
+
"lr": 0.00019800000000000002,
|
| 409 |
+
"step": 100,
|
| 410 |
+
"tokens_trained": 0.009501456
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.02893617021276596,
|
| 414 |
+
"grad_norm": 23.458459854125977,
|
| 415 |
+
"loss": 17.6295,
|
| 416 |
+
"lr": 0.000202,
|
| 417 |
+
"step": 102,
|
| 418 |
+
"tokens_trained": 0.009693952
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.02950354609929078,
|
| 422 |
+
"grad_norm": 24.092350006103516,
|
| 423 |
+
"loss": 17.4593,
|
| 424 |
+
"lr": 0.000206,
|
| 425 |
+
"step": 104,
|
| 426 |
+
"tokens_trained": 0.009883328
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.030070921985815603,
|
| 430 |
+
"grad_norm": 22.54726219177246,
|
| 431 |
+
"loss": 17.2141,
|
| 432 |
+
"lr": 0.00021,
|
| 433 |
+
"step": 106,
|
| 434 |
+
"tokens_trained": 0.01007316
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.030638297872340424,
|
| 438 |
+
"grad_norm": 21.334760665893555,
|
| 439 |
+
"loss": 17.044,
|
| 440 |
+
"lr": 0.000214,
|
| 441 |
+
"step": 108,
|
| 442 |
+
"tokens_trained": 0.010266504
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.031205673758865248,
|
| 446 |
+
"grad_norm": 20.584287643432617,
|
| 447 |
+
"loss": 16.8919,
|
| 448 |
+
"lr": 0.000218,
|
| 449 |
+
"step": 110,
|
| 450 |
+
"tokens_trained": 0.010455736
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.03177304964539007,
|
| 454 |
+
"grad_norm": 23.51676368713379,
|
| 455 |
+
"loss": 16.751,
|
| 456 |
+
"lr": 0.000222,
|
| 457 |
+
"step": 112,
|
| 458 |
+
"tokens_trained": 0.010645208
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.03234042553191489,
|
| 462 |
+
"grad_norm": 23.278276443481445,
|
| 463 |
+
"loss": 16.5997,
|
| 464 |
+
"lr": 0.00022600000000000002,
|
| 465 |
+
"step": 114,
|
| 466 |
+
"tokens_trained": 0.010838928
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.032907801418439714,
|
| 470 |
+
"grad_norm": 25.4830265045166,
|
| 471 |
+
"loss": 16.3416,
|
| 472 |
+
"lr": 0.00023,
|
| 473 |
+
"step": 116,
|
| 474 |
+
"tokens_trained": 0.011027792
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.03347517730496454,
|
| 478 |
+
"grad_norm": 29.442413330078125,
|
| 479 |
+
"loss": 16.24,
|
| 480 |
+
"lr": 0.00023400000000000002,
|
| 481 |
+
"step": 118,
|
| 482 |
+
"tokens_trained": 0.011217456
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.03404255319148936,
|
| 486 |
+
"grad_norm": 21.77578353881836,
|
| 487 |
+
"loss": 16.1922,
|
| 488 |
+
"lr": 0.00023799999999999998,
|
| 489 |
+
"step": 120,
|
| 490 |
+
"tokens_trained": 0.01140804
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.03460992907801418,
|
| 494 |
+
"grad_norm": 27.040719985961914,
|
| 495 |
+
"loss": 15.9059,
|
| 496 |
+
"lr": 0.000242,
|
| 497 |
+
"step": 122,
|
| 498 |
+
"tokens_trained": 0.011597816
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.035177304964539004,
|
| 502 |
+
"grad_norm": 24.74480628967285,
|
| 503 |
+
"loss": 15.7818,
|
| 504 |
+
"lr": 0.000246,
|
| 505 |
+
"step": 124,
|
| 506 |
+
"tokens_trained": 0.011785624
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.03546099290780142,
|
| 510 |
+
"eval_loss": 15.553059577941895,
|
| 511 |
+
"eval_runtime": 23.5485,
|
| 512 |
+
"step": 125,
|
| 513 |
+
"tokens_trained": 0.011880832
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.03574468085106383,
|
| 517 |
+
"grad_norm": 23.13482666015625,
|
| 518 |
+
"loss": 15.5739,
|
| 519 |
+
"lr": 0.00025,
|
| 520 |
+
"step": 126,
|
| 521 |
+
"tokens_trained": 0.011975976
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.03631205673758865,
|
| 525 |
+
"grad_norm": 22.8618106842041,
|
| 526 |
+
"loss": 15.4302,
|
| 527 |
+
"lr": 0.000254,
|
| 528 |
+
"step": 128,
|
| 529 |
+
"tokens_trained": 0.012166744
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.03687943262411347,
|
| 533 |
+
"grad_norm": 26.804859161376953,
|
| 534 |
+
"loss": 15.3623,
|
| 535 |
+
"lr": 0.00025800000000000004,
|
| 536 |
+
"step": 130,
|
| 537 |
+
"tokens_trained": 0.01235436
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.0374468085106383,
|
| 541 |
+
"grad_norm": 21.826601028442383,
|
| 542 |
+
"loss": 15.1465,
|
| 543 |
+
"lr": 0.000262,
|
| 544 |
+
"step": 132,
|
| 545 |
+
"tokens_trained": 0.012544976
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 0.03801418439716312,
|
| 549 |
+
"grad_norm": 39.447086334228516,
|
| 550 |
+
"loss": 15.0137,
|
| 551 |
+
"lr": 0.000266,
|
| 552 |
+
"step": 134,
|
| 553 |
+
"tokens_trained": 0.012736352
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.03858156028368794,
|
| 557 |
+
"grad_norm": 23.44275665283203,
|
| 558 |
+
"loss": 14.9355,
|
| 559 |
+
"lr": 0.00027,
|
| 560 |
+
"step": 136,
|
| 561 |
+
"tokens_trained": 0.012925008
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.03914893617021276,
|
| 565 |
+
"grad_norm": 21.631427764892578,
|
| 566 |
+
"loss": 14.6825,
|
| 567 |
+
"lr": 0.00027400000000000005,
|
| 568 |
+
"step": 138,
|
| 569 |
+
"tokens_trained": 0.013114672
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.03971631205673759,
|
| 573 |
+
"grad_norm": 23.674650192260742,
|
| 574 |
+
"loss": 14.5194,
|
| 575 |
+
"lr": 0.00027800000000000004,
|
| 576 |
+
"step": 140,
|
| 577 |
+
"tokens_trained": 0.013304016
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.04028368794326241,
|
| 581 |
+
"grad_norm": 23.974796295166016,
|
| 582 |
+
"loss": 14.4829,
|
| 583 |
+
"lr": 0.00028199999999999997,
|
| 584 |
+
"step": 142,
|
| 585 |
+
"tokens_trained": 0.013496696
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.04085106382978723,
|
| 589 |
+
"grad_norm": 26.112201690673828,
|
| 590 |
+
"loss": 14.3027,
|
| 591 |
+
"lr": 0.00028599999999999996,
|
| 592 |
+
"step": 144,
|
| 593 |
+
"tokens_trained": 0.013684816
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.04141843971631206,
|
| 597 |
+
"grad_norm": 20.67386817932129,
|
| 598 |
+
"loss": 14.1499,
|
| 599 |
+
"lr": 0.00029,
|
| 600 |
+
"step": 146,
|
| 601 |
+
"tokens_trained": 0.013874832
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.04198581560283688,
|
| 605 |
+
"grad_norm": 24.253408432006836,
|
| 606 |
+
"loss": 13.9378,
|
| 607 |
+
"lr": 0.000294,
|
| 608 |
+
"step": 148,
|
| 609 |
+
"tokens_trained": 0.014065056
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.0425531914893617,
|
| 613 |
+
"grad_norm": 35.716087341308594,
|
| 614 |
+
"loss": 14.0562,
|
| 615 |
+
"lr": 0.000298,
|
| 616 |
+
"step": 150,
|
| 617 |
+
"tokens_trained": 0.014256784
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.04312056737588652,
|
| 621 |
+
"grad_norm": 29.414331436157227,
|
| 622 |
+
"loss": 14.0462,
|
| 623 |
+
"lr": 0.000302,
|
| 624 |
+
"step": 152,
|
| 625 |
+
"tokens_trained": 0.014446312
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.04368794326241135,
|
| 629 |
+
"grad_norm": 30.687482833862305,
|
| 630 |
+
"loss": 13.7603,
|
| 631 |
+
"lr": 0.000306,
|
| 632 |
+
"step": 154,
|
| 633 |
+
"tokens_trained": 0.014639872
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.04425531914893617,
|
| 637 |
+
"grad_norm": 29.806455612182617,
|
| 638 |
+
"loss": 13.708,
|
| 639 |
+
"lr": 0.00031,
|
| 640 |
+
"step": 156,
|
| 641 |
+
"tokens_trained": 0.014831112
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.04482269503546099,
|
| 645 |
+
"grad_norm": 24.900897979736328,
|
| 646 |
+
"loss": 13.548,
|
| 647 |
+
"lr": 0.000314,
|
| 648 |
+
"step": 158,
|
| 649 |
+
"tokens_trained": 0.015021288
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.04539007092198582,
|
| 653 |
+
"grad_norm": 24.29252815246582,
|
| 654 |
+
"loss": 13.3119,
|
| 655 |
+
"lr": 0.00031800000000000003,
|
| 656 |
+
"step": 160,
|
| 657 |
+
"tokens_trained": 0.01521228
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.04595744680851064,
|
| 661 |
+
"grad_norm": 20.68342399597168,
|
| 662 |
+
"loss": 13.1829,
|
| 663 |
+
"lr": 0.000322,
|
| 664 |
+
"step": 162,
|
| 665 |
+
"tokens_trained": 0.015403688
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 0.04652482269503546,
|
| 669 |
+
"grad_norm": 20.822795867919922,
|
| 670 |
+
"loss": 12.9044,
|
| 671 |
+
"lr": 0.000326,
|
| 672 |
+
"step": 164,
|
| 673 |
+
"tokens_trained": 0.015593416
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 0.04709219858156028,
|
| 677 |
+
"grad_norm": 21.689916610717773,
|
| 678 |
+
"loss": 12.6862,
|
| 679 |
+
"lr": 0.00033,
|
| 680 |
+
"step": 166,
|
| 681 |
+
"tokens_trained": 0.015784408
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.04765957446808511,
|
| 685 |
+
"grad_norm": 17.873889923095703,
|
| 686 |
+
"loss": 12.5502,
|
| 687 |
+
"lr": 0.00033400000000000004,
|
| 688 |
+
"step": 168,
|
| 689 |
+
"tokens_trained": 0.0159744
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.04822695035460993,
|
| 693 |
+
"grad_norm": 18.951616287231445,
|
| 694 |
+
"loss": 12.308,
|
| 695 |
+
"lr": 0.00033800000000000003,
|
| 696 |
+
"step": 170,
|
| 697 |
+
"tokens_trained": 0.016163736
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.04879432624113475,
|
| 701 |
+
"grad_norm": 15.146363258361816,
|
| 702 |
+
"loss": 12.1558,
|
| 703 |
+
"lr": 0.000342,
|
| 704 |
+
"step": 172,
|
| 705 |
+
"tokens_trained": 0.016353832
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.04936170212765958,
|
| 709 |
+
"grad_norm": 18.336984634399414,
|
| 710 |
+
"loss": 12.0386,
|
| 711 |
+
"lr": 0.000346,
|
| 712 |
+
"step": 174,
|
| 713 |
+
"tokens_trained": 0.016545088
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.0499290780141844,
|
| 717 |
+
"grad_norm": 17.221126556396484,
|
| 718 |
+
"loss": 11.8791,
|
| 719 |
+
"lr": 0.00035,
|
| 720 |
+
"step": 176,
|
| 721 |
+
"tokens_trained": 0.016735704
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 0.05049645390070922,
|
| 725 |
+
"grad_norm": 19.362564086914062,
|
| 726 |
+
"loss": 11.7224,
|
| 727 |
+
"lr": 0.000354,
|
| 728 |
+
"step": 178,
|
| 729 |
+
"tokens_trained": 0.016927944
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.05106382978723404,
|
| 733 |
+
"grad_norm": 15.564507484436035,
|
| 734 |
+
"loss": 11.6448,
|
| 735 |
+
"lr": 0.000358,
|
| 736 |
+
"step": 180,
|
| 737 |
+
"tokens_trained": 0.017116096
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.05163120567375887,
|
| 741 |
+
"grad_norm": 20.711383819580078,
|
| 742 |
+
"loss": 11.4398,
|
| 743 |
+
"lr": 0.000362,
|
| 744 |
+
"step": 182,
|
| 745 |
+
"tokens_trained": 0.01730564
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.05219858156028369,
|
| 749 |
+
"grad_norm": 18.627403259277344,
|
| 750 |
+
"loss": 11.3377,
|
| 751 |
+
"lr": 0.000366,
|
| 752 |
+
"step": 184,
|
| 753 |
+
"tokens_trained": 0.017495864
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.05276595744680851,
|
| 757 |
+
"grad_norm": 15.00942325592041,
|
| 758 |
+
"loss": 11.1416,
|
| 759 |
+
"lr": 0.00037,
|
| 760 |
+
"step": 186,
|
| 761 |
+
"tokens_trained": 0.017686464
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.05333333333333334,
|
| 765 |
+
"grad_norm": 17.070598602294922,
|
| 766 |
+
"loss": 11.0148,
|
| 767 |
+
"lr": 0.000374,
|
| 768 |
+
"step": 188,
|
| 769 |
+
"tokens_trained": 0.017879488
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 0.05390070921985816,
|
| 773 |
+
"grad_norm": 16.101457595825195,
|
| 774 |
+
"loss": 10.8874,
|
| 775 |
+
"lr": 0.000378,
|
| 776 |
+
"step": 190,
|
| 777 |
+
"tokens_trained": 0.018068312
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.05446808510638298,
|
| 781 |
+
"grad_norm": 15.613334655761719,
|
| 782 |
+
"loss": 10.7055,
|
| 783 |
+
"lr": 0.000382,
|
| 784 |
+
"step": 192,
|
| 785 |
+
"tokens_trained": 0.018255752
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 0.0550354609929078,
|
| 789 |
+
"grad_norm": 17.671857833862305,
|
| 790 |
+
"loss": 10.5706,
|
| 791 |
+
"lr": 0.000386,
|
| 792 |
+
"step": 194,
|
| 793 |
+
"tokens_trained": 0.018447096
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.05560283687943263,
|
| 797 |
+
"grad_norm": 16.080909729003906,
|
| 798 |
+
"loss": 10.4476,
|
| 799 |
+
"lr": 0.00039000000000000005,
|
| 800 |
+
"step": 196,
|
| 801 |
+
"tokens_trained": 0.018637264
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.05617021276595745,
|
| 805 |
+
"grad_norm": 15.02849292755127,
|
| 806 |
+
"loss": 10.2962,
|
| 807 |
+
"lr": 0.00039400000000000004,
|
| 808 |
+
"step": 198,
|
| 809 |
+
"tokens_trained": 0.018827552
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.05673758865248227,
|
| 813 |
+
"grad_norm": 14.990167617797852,
|
| 814 |
+
"loss": 10.1912,
|
| 815 |
+
"lr": 0.000398,
|
| 816 |
+
"step": 200,
|
| 817 |
+
"tokens_trained": 0.019018
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.05730496453900709,
|
| 821 |
+
"grad_norm": 15.390633583068848,
|
| 822 |
+
"loss": 10.0442,
|
| 823 |
+
"lr": 0.000402,
|
| 824 |
+
"step": 202,
|
| 825 |
+
"tokens_trained": 0.019209864
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.05787234042553192,
|
| 829 |
+
"grad_norm": 16.871570587158203,
|
| 830 |
+
"loss": 9.9685,
|
| 831 |
+
"lr": 0.00040600000000000006,
|
| 832 |
+
"step": 204,
|
| 833 |
+
"tokens_trained": 0.019400176
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.05843971631205674,
|
| 837 |
+
"grad_norm": 20.16544532775879,
|
| 838 |
+
"loss": 9.8531,
|
| 839 |
+
"lr": 0.00041,
|
| 840 |
+
"step": 206,
|
| 841 |
+
"tokens_trained": 0.019589424
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.05900709219858156,
|
| 845 |
+
"grad_norm": 16.825023651123047,
|
| 846 |
+
"loss": 9.7777,
|
| 847 |
+
"lr": 0.000414,
|
| 848 |
+
"step": 208,
|
| 849 |
+
"tokens_trained": 0.019779112
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.059574468085106386,
|
| 853 |
+
"grad_norm": 16.43510627746582,
|
| 854 |
+
"loss": 9.6122,
|
| 855 |
+
"lr": 0.00041799999999999997,
|
| 856 |
+
"step": 210,
|
| 857 |
+
"tokens_trained": 0.019970048
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.060141843971631206,
|
| 861 |
+
"grad_norm": 17.340473175048828,
|
| 862 |
+
"loss": 9.4859,
|
| 863 |
+
"lr": 0.000422,
|
| 864 |
+
"step": 212,
|
| 865 |
+
"tokens_trained": 0.020160968
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.06070921985815603,
|
| 869 |
+
"grad_norm": 15.019119262695312,
|
| 870 |
+
"loss": 9.3656,
|
| 871 |
+
"lr": 0.000426,
|
| 872 |
+
"step": 214,
|
| 873 |
+
"tokens_trained": 0.020349664
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.06127659574468085,
|
| 877 |
+
"grad_norm": 13.379194259643555,
|
| 878 |
+
"loss": 9.2348,
|
| 879 |
+
"lr": 0.00043,
|
| 880 |
+
"step": 216,
|
| 881 |
+
"tokens_trained": 0.020538192
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 0.061843971631205676,
|
| 885 |
+
"grad_norm": 16.71472930908203,
|
| 886 |
+
"loss": 9.2258,
|
| 887 |
+
"lr": 0.00043400000000000003,
|
| 888 |
+
"step": 218,
|
| 889 |
+
"tokens_trained": 0.020728936
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 0.062411347517730496,
|
| 893 |
+
"grad_norm": 12.743139266967773,
|
| 894 |
+
"loss": 9.0569,
|
| 895 |
+
"lr": 0.000438,
|
| 896 |
+
"step": 220,
|
| 897 |
+
"tokens_trained": 0.020917472
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.06297872340425532,
|
| 901 |
+
"grad_norm": 15.739934921264648,
|
| 902 |
+
"loss": 8.9623,
|
| 903 |
+
"lr": 0.000442,
|
| 904 |
+
"step": 222,
|
| 905 |
+
"tokens_trained": 0.02110928
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.06354609929078014,
|
| 909 |
+
"grad_norm": 14.23620891571045,
|
| 910 |
+
"loss": 8.8201,
|
| 911 |
+
"lr": 0.000446,
|
| 912 |
+
"step": 224,
|
| 913 |
+
"tokens_trained": 0.021300168
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.06411347517730497,
|
| 917 |
+
"grad_norm": 13.005538940429688,
|
| 918 |
+
"loss": 8.7235,
|
| 919 |
+
"lr": 0.00045000000000000004,
|
| 920 |
+
"step": 226,
|
| 921 |
+
"tokens_trained": 0.021490272
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.06468085106382979,
|
| 925 |
+
"grad_norm": 17.17629051208496,
|
| 926 |
+
"loss": 8.6907,
|
| 927 |
+
"lr": 0.00045400000000000003,
|
| 928 |
+
"step": 228,
|
| 929 |
+
"tokens_trained": 0.021681552
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.06524822695035461,
|
| 933 |
+
"grad_norm": 14.430739402770996,
|
| 934 |
+
"loss": 8.6196,
|
| 935 |
+
"lr": 0.000458,
|
| 936 |
+
"step": 230,
|
| 937 |
+
"tokens_trained": 0.02187236
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 0.06581560283687943,
|
| 941 |
+
"grad_norm": 14.575714111328125,
|
| 942 |
+
"loss": 8.4741,
|
| 943 |
+
"lr": 0.000462,
|
| 944 |
+
"step": 232,
|
| 945 |
+
"tokens_trained": 0.022061976
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.06638297872340425,
|
| 949 |
+
"grad_norm": 13.892754554748535,
|
| 950 |
+
"loss": 8.4118,
|
| 951 |
+
"lr": 0.00046600000000000005,
|
| 952 |
+
"step": 234,
|
| 953 |
+
"tokens_trained": 0.022252008
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.06695035460992908,
|
| 957 |
+
"grad_norm": 11.58240795135498,
|
| 958 |
+
"loss": 8.2781,
|
| 959 |
+
"lr": 0.00047,
|
| 960 |
+
"step": 236,
|
| 961 |
+
"tokens_trained": 0.02244284
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.0675177304964539,
|
| 965 |
+
"grad_norm": 13.022644996643066,
|
| 966 |
+
"loss": 8.2139,
|
| 967 |
+
"lr": 0.000474,
|
| 968 |
+
"step": 238,
|
| 969 |
+
"tokens_trained": 0.022631152
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.06808510638297872,
|
| 973 |
+
"grad_norm": 11.844677925109863,
|
| 974 |
+
"loss": 8.1134,
|
| 975 |
+
"lr": 0.00047799999999999996,
|
| 976 |
+
"step": 240,
|
| 977 |
+
"tokens_trained": 0.022821096
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 0.06865248226950355,
|
| 981 |
+
"grad_norm": 13.878067016601562,
|
| 982 |
+
"loss": 8.0221,
|
| 983 |
+
"lr": 0.000482,
|
| 984 |
+
"step": 242,
|
| 985 |
+
"tokens_trained": 0.023011656
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.06921985815602837,
|
| 989 |
+
"grad_norm": 12.34648323059082,
|
| 990 |
+
"loss": 7.9755,
|
| 991 |
+
"lr": 0.000486,
|
| 992 |
+
"step": 244,
|
| 993 |
+
"tokens_trained": 0.023201
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 0.06978723404255319,
|
| 997 |
+
"grad_norm": 14.238297462463379,
|
| 998 |
+
"loss": 7.8969,
|
| 999 |
+
"lr": 0.00049,
|
| 1000 |
+
"step": 246,
|
| 1001 |
+
"tokens_trained": 0.023391128
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 0.07035460992907801,
|
| 1005 |
+
"grad_norm": 14.386019706726074,
|
| 1006 |
+
"loss": 7.8627,
|
| 1007 |
+
"lr": 0.000494,
|
| 1008 |
+
"step": 248,
|
| 1009 |
+
"tokens_trained": 0.023581768
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 0.07092198581560284,
|
| 1013 |
+
"grad_norm": 13.623086929321289,
|
| 1014 |
+
"loss": 7.7568,
|
| 1015 |
+
"lr": 0.000498,
|
| 1016 |
+
"step": 250,
|
| 1017 |
+
"tokens_trained": 0.023771248
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.07092198581560284,
|
| 1021 |
+
"eval_loss": 7.70297384262085,
|
| 1022 |
+
"eval_runtime": 21.3853,
|
| 1023 |
+
"step": 250,
|
| 1024 |
+
"tokens_trained": 0.023771248
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.07148936170212766,
|
| 1028 |
+
"grad_norm": 14.347646713256836,
|
| 1029 |
+
"loss": 7.6842,
|
| 1030 |
+
"lr": 0.0005020000000000001,
|
| 1031 |
+
"step": 252,
|
| 1032 |
+
"tokens_trained": 0.023961056
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.07205673758865248,
|
| 1036 |
+
"grad_norm": 12.5592041015625,
|
| 1037 |
+
"loss": 7.6516,
|
| 1038 |
+
"lr": 0.000506,
|
| 1039 |
+
"step": 254,
|
| 1040 |
+
"tokens_trained": 0.024150968
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 0.0726241134751773,
|
| 1044 |
+
"grad_norm": 13.219141960144043,
|
| 1045 |
+
"loss": 7.5789,
|
| 1046 |
+
"lr": 0.00051,
|
| 1047 |
+
"step": 256,
|
| 1048 |
+
"tokens_trained": 0.024340072
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.07319148936170213,
|
| 1052 |
+
"grad_norm": 12.654081344604492,
|
| 1053 |
+
"loss": 7.5369,
|
| 1054 |
+
"lr": 0.000514,
|
| 1055 |
+
"step": 258,
|
| 1056 |
+
"tokens_trained": 0.024529296
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 0.07375886524822695,
|
| 1060 |
+
"grad_norm": 13.136971473693848,
|
| 1061 |
+
"loss": 7.4949,
|
| 1062 |
+
"lr": 0.000518,
|
| 1063 |
+
"step": 260,
|
| 1064 |
+
"tokens_trained": 0.024719688
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 0.07432624113475177,
|
| 1068 |
+
"grad_norm": 12.680288314819336,
|
| 1069 |
+
"loss": 7.3904,
|
| 1070 |
+
"lr": 0.000522,
|
| 1071 |
+
"step": 262,
|
| 1072 |
+
"tokens_trained": 0.024909632
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 0.0748936170212766,
|
| 1076 |
+
"grad_norm": 12.754518508911133,
|
| 1077 |
+
"loss": 7.3514,
|
| 1078 |
+
"lr": 0.000526,
|
| 1079 |
+
"step": 264,
|
| 1080 |
+
"tokens_trained": 0.025098416
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.07546099290780142,
|
| 1084 |
+
"grad_norm": 13.22311019897461,
|
| 1085 |
+
"loss": 7.2951,
|
| 1086 |
+
"lr": 0.0005300000000000001,
|
| 1087 |
+
"step": 266,
|
| 1088 |
+
"tokens_trained": 0.025287344
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.07602836879432624,
|
| 1092 |
+
"grad_norm": 12.11903190612793,
|
| 1093 |
+
"loss": 7.2229,
|
| 1094 |
+
"lr": 0.0005340000000000001,
|
| 1095 |
+
"step": 268,
|
| 1096 |
+
"tokens_trained": 0.025477152
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 0.07659574468085106,
|
| 1100 |
+
"grad_norm": 13.771833419799805,
|
| 1101 |
+
"loss": 7.1815,
|
| 1102 |
+
"lr": 0.0005380000000000001,
|
| 1103 |
+
"step": 270,
|
| 1104 |
+
"tokens_trained": 0.025668288
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 0.07716312056737588,
|
| 1108 |
+
"grad_norm": 11.756864547729492,
|
| 1109 |
+
"loss": 7.1669,
|
| 1110 |
+
"lr": 0.0005420000000000001,
|
| 1111 |
+
"step": 272,
|
| 1112 |
+
"tokens_trained": 0.025858528
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.0777304964539007,
|
| 1116 |
+
"grad_norm": 13.613094329833984,
|
| 1117 |
+
"loss": 7.1079,
|
| 1118 |
+
"lr": 0.000546,
|
| 1119 |
+
"step": 274,
|
| 1120 |
+
"tokens_trained": 0.026048616
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 0.07829787234042553,
|
| 1124 |
+
"grad_norm": 10.001923561096191,
|
| 1125 |
+
"loss": 7.0508,
|
| 1126 |
+
"lr": 0.00055,
|
| 1127 |
+
"step": 276,
|
| 1128 |
+
"tokens_trained": 0.026236944
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 0.07886524822695036,
|
| 1132 |
+
"grad_norm": 14.262083053588867,
|
| 1133 |
+
"loss": 6.9955,
|
| 1134 |
+
"lr": 0.000554,
|
| 1135 |
+
"step": 278,
|
| 1136 |
+
"tokens_trained": 0.026426848
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.07943262411347518,
|
| 1140 |
+
"grad_norm": 12.381136894226074,
|
| 1141 |
+
"loss": 6.9831,
|
| 1142 |
+
"lr": 0.000558,
|
| 1143 |
+
"step": 280,
|
| 1144 |
+
"tokens_trained": 0.026616784
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.08,
|
| 1148 |
+
"grad_norm": 9.815845489501953,
|
| 1149 |
+
"loss": 6.917,
|
| 1150 |
+
"lr": 0.0005620000000000001,
|
| 1151 |
+
"step": 282,
|
| 1152 |
+
"tokens_trained": 0.026805176
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 0.08056737588652482,
|
| 1156 |
+
"grad_norm": 11.669997215270996,
|
| 1157 |
+
"loss": 6.8999,
|
| 1158 |
+
"lr": 0.000566,
|
| 1159 |
+
"step": 284,
|
| 1160 |
+
"tokens_trained": 0.02699488
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 0.08113475177304964,
|
| 1164 |
+
"grad_norm": 12.770941734313965,
|
| 1165 |
+
"loss": 6.8998,
|
| 1166 |
+
"lr": 0.00057,
|
| 1167 |
+
"step": 286,
|
| 1168 |
+
"tokens_trained": 0.027185784
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.08170212765957446,
|
| 1172 |
+
"grad_norm": 15.572457313537598,
|
| 1173 |
+
"loss": 6.841,
|
| 1174 |
+
"lr": 0.000574,
|
| 1175 |
+
"step": 288,
|
| 1176 |
+
"tokens_trained": 0.027375896
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 0.08226950354609928,
|
| 1180 |
+
"grad_norm": 10.980833053588867,
|
| 1181 |
+
"loss": 6.8545,
|
| 1182 |
+
"lr": 0.000578,
|
| 1183 |
+
"step": 290,
|
| 1184 |
+
"tokens_trained": 0.02756588
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 0.08283687943262412,
|
| 1188 |
+
"grad_norm": 11.678337097167969,
|
| 1189 |
+
"loss": 6.7853,
|
| 1190 |
+
"lr": 0.0005819999999999999,
|
| 1191 |
+
"step": 292,
|
| 1192 |
+
"tokens_trained": 0.02775456
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.08340425531914894,
|
| 1196 |
+
"grad_norm": 9.77885913848877,
|
| 1197 |
+
"loss": 6.7465,
|
| 1198 |
+
"lr": 0.0005859999999999999,
|
| 1199 |
+
"step": 294,
|
| 1200 |
+
"tokens_trained": 0.027942856
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.08397163120567376,
|
| 1204 |
+
"grad_norm": 13.62730884552002,
|
| 1205 |
+
"loss": 6.7276,
|
| 1206 |
+
"lr": 0.00059,
|
| 1207 |
+
"step": 296,
|
| 1208 |
+
"tokens_trained": 0.028133152
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 0.08453900709219858,
|
| 1212 |
+
"grad_norm": 10.644404411315918,
|
| 1213 |
+
"loss": 6.6802,
|
| 1214 |
+
"lr": 0.000594,
|
| 1215 |
+
"step": 298,
|
| 1216 |
+
"tokens_trained": 0.028322192
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 0.0851063829787234,
|
| 1220 |
+
"grad_norm": 11.130610466003418,
|
| 1221 |
+
"loss": 6.6548,
|
| 1222 |
+
"lr": 0.000598,
|
| 1223 |
+
"step": 300,
|
| 1224 |
+
"tokens_trained": 0.0285122
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.08567375886524822,
|
| 1228 |
+
"grad_norm": 11.557455062866211,
|
| 1229 |
+
"loss": 6.6155,
|
| 1230 |
+
"lr": 0.000602,
|
| 1231 |
+
"step": 302,
|
| 1232 |
+
"tokens_trained": 0.028699792
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 0.08624113475177304,
|
| 1236 |
+
"grad_norm": 9.276884078979492,
|
| 1237 |
+
"loss": 6.5989,
|
| 1238 |
+
"lr": 0.000606,
|
| 1239 |
+
"step": 304,
|
| 1240 |
+
"tokens_trained": 0.028889896
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"epoch": 0.08680851063829788,
|
| 1244 |
+
"grad_norm": 9.616179466247559,
|
| 1245 |
+
"loss": 6.5773,
|
| 1246 |
+
"lr": 0.00061,
|
| 1247 |
+
"step": 306,
|
| 1248 |
+
"tokens_trained": 0.029082272
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.0873758865248227,
|
| 1252 |
+
"grad_norm": 10.575953483581543,
|
| 1253 |
+
"loss": 6.5358,
|
| 1254 |
+
"lr": 0.000614,
|
| 1255 |
+
"step": 308,
|
| 1256 |
+
"tokens_trained": 0.029273352
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.08794326241134752,
|
| 1260 |
+
"grad_norm": 9.089850425720215,
|
| 1261 |
+
"loss": 6.5088,
|
| 1262 |
+
"lr": 0.0006180000000000001,
|
| 1263 |
+
"step": 310,
|
| 1264 |
+
"tokens_trained": 0.029463848
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 0.08851063829787234,
|
| 1268 |
+
"grad_norm": 9.090002059936523,
|
| 1269 |
+
"loss": 6.4849,
|
| 1270 |
+
"lr": 0.000622,
|
| 1271 |
+
"step": 312,
|
| 1272 |
+
"tokens_trained": 0.029653272
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 0.08907801418439716,
|
| 1276 |
+
"grad_norm": 12.038308143615723,
|
| 1277 |
+
"loss": 6.4624,
|
| 1278 |
+
"lr": 0.000626,
|
| 1279 |
+
"step": 314,
|
| 1280 |
+
"tokens_trained": 0.029841928
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.08964539007092198,
|
| 1284 |
+
"grad_norm": 9.073866844177246,
|
| 1285 |
+
"loss": 6.4515,
|
| 1286 |
+
"lr": 0.00063,
|
| 1287 |
+
"step": 316,
|
| 1288 |
+
"tokens_trained": 0.030029808
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 0.0902127659574468,
|
| 1292 |
+
"grad_norm": 8.727197647094727,
|
| 1293 |
+
"loss": 6.43,
|
| 1294 |
+
"lr": 0.000634,
|
| 1295 |
+
"step": 318,
|
| 1296 |
+
"tokens_trained": 0.030221288
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 0.09078014184397164,
|
| 1300 |
+
"grad_norm": 14.558151245117188,
|
| 1301 |
+
"loss": 6.4487,
|
| 1302 |
+
"lr": 0.000638,
|
| 1303 |
+
"step": 320,
|
| 1304 |
+
"tokens_trained": 0.030410872
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.09134751773049646,
|
| 1308 |
+
"grad_norm": 9.98914623260498,
|
| 1309 |
+
"loss": 6.4279,
|
| 1310 |
+
"lr": 0.000642,
|
| 1311 |
+
"step": 322,
|
| 1312 |
+
"tokens_trained": 0.030602376
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.09191489361702128,
|
| 1316 |
+
"grad_norm": 10.395442962646484,
|
| 1317 |
+
"loss": 6.4311,
|
| 1318 |
+
"lr": 0.000646,
|
| 1319 |
+
"step": 324,
|
| 1320 |
+
"tokens_trained": 0.030792968
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 0.0924822695035461,
|
| 1324 |
+
"grad_norm": 10.8250093460083,
|
| 1325 |
+
"loss": 6.3726,
|
| 1326 |
+
"lr": 0.0006500000000000001,
|
| 1327 |
+
"step": 326,
|
| 1328 |
+
"tokens_trained": 0.030982944
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 0.09304964539007092,
|
| 1332 |
+
"grad_norm": 9.73416805267334,
|
| 1333 |
+
"loss": 6.34,
|
| 1334 |
+
"lr": 0.0006540000000000001,
|
| 1335 |
+
"step": 328,
|
| 1336 |
+
"tokens_trained": 0.031174928
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.09361702127659574,
|
| 1340 |
+
"grad_norm": 8.596503257751465,
|
| 1341 |
+
"loss": 6.3322,
|
| 1342 |
+
"lr": 0.0006580000000000001,
|
| 1343 |
+
"step": 330,
|
| 1344 |
+
"tokens_trained": 0.031364288
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 0.09418439716312056,
|
| 1348 |
+
"grad_norm": 8.49472427368164,
|
| 1349 |
+
"loss": 6.3096,
|
| 1350 |
+
"lr": 0.000662,
|
| 1351 |
+
"step": 332,
|
| 1352 |
+
"tokens_trained": 0.03155376
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 0.0947517730496454,
|
| 1356 |
+
"grad_norm": 7.857503414154053,
|
| 1357 |
+
"loss": 6.2368,
|
| 1358 |
+
"lr": 0.000666,
|
| 1359 |
+
"step": 334,
|
| 1360 |
+
"tokens_trained": 0.031744368
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.09531914893617022,
|
| 1364 |
+
"grad_norm": 9.007513999938965,
|
| 1365 |
+
"loss": 6.198,
|
| 1366 |
+
"lr": 0.00067,
|
| 1367 |
+
"step": 336,
|
| 1368 |
+
"tokens_trained": 0.031934136
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.09588652482269504,
|
| 1372 |
+
"grad_norm": 8.185524940490723,
|
| 1373 |
+
"loss": 6.2328,
|
| 1374 |
+
"lr": 0.000674,
|
| 1375 |
+
"step": 338,
|
| 1376 |
+
"tokens_trained": 0.032124984
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 0.09645390070921986,
|
| 1380 |
+
"grad_norm": 8.784396171569824,
|
| 1381 |
+
"loss": 6.1945,
|
| 1382 |
+
"lr": 0.0006780000000000001,
|
| 1383 |
+
"step": 340,
|
| 1384 |
+
"tokens_trained": 0.032316016
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 0.09702127659574468,
|
| 1388 |
+
"grad_norm": 8.642311096191406,
|
| 1389 |
+
"loss": 6.218,
|
| 1390 |
+
"lr": 0.0006820000000000001,
|
| 1391 |
+
"step": 342,
|
| 1392 |
+
"tokens_trained": 0.032506224
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.0975886524822695,
|
| 1396 |
+
"grad_norm": 8.493780136108398,
|
| 1397 |
+
"loss": 6.194,
|
| 1398 |
+
"lr": 0.0006860000000000001,
|
| 1399 |
+
"step": 344,
|
| 1400 |
+
"tokens_trained": 0.032696152
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 0.09815602836879432,
|
| 1404 |
+
"grad_norm": 9.120508193969727,
|
| 1405 |
+
"loss": 6.2241,
|
| 1406 |
+
"lr": 0.00069,
|
| 1407 |
+
"step": 346,
|
| 1408 |
+
"tokens_trained": 0.032885688
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 0.09872340425531916,
|
| 1412 |
+
"grad_norm": 9.34500503540039,
|
| 1413 |
+
"loss": 6.1548,
|
| 1414 |
+
"lr": 0.000694,
|
| 1415 |
+
"step": 348,
|
| 1416 |
+
"tokens_trained": 0.03307568
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.09929078014184398,
|
| 1420 |
+
"grad_norm": 7.483356952667236,
|
| 1421 |
+
"loss": 6.1282,
|
| 1422 |
+
"lr": 0.0006979999999999999,
|
| 1423 |
+
"step": 350,
|
| 1424 |
+
"tokens_trained": 0.033267208
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.0998581560283688,
|
| 1428 |
+
"grad_norm": 7.974069118499756,
|
| 1429 |
+
"loss": 6.1032,
|
| 1430 |
+
"lr": 0.0007019999999999999,
|
| 1431 |
+
"step": 352,
|
| 1432 |
+
"tokens_trained": 0.033458144
|
| 1433 |
+
},
|
| 1434 |
+
{
|
| 1435 |
+
"epoch": 0.10042553191489362,
|
| 1436 |
+
"grad_norm": 8.247384071350098,
|
| 1437 |
+
"loss": 6.1698,
|
| 1438 |
+
"lr": 0.0007059999999999999,
|
| 1439 |
+
"step": 354,
|
| 1440 |
+
"tokens_trained": 0.033650352
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 0.10099290780141844,
|
| 1444 |
+
"grad_norm": 8.554885864257812,
|
| 1445 |
+
"loss": 6.1429,
|
| 1446 |
+
"lr": 0.00071,
|
| 1447 |
+
"step": 356,
|
| 1448 |
+
"tokens_trained": 0.033840232
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 0.10156028368794326,
|
| 1452 |
+
"grad_norm": 7.209281921386719,
|
| 1453 |
+
"loss": 6.0997,
|
| 1454 |
+
"lr": 0.000714,
|
| 1455 |
+
"step": 358,
|
| 1456 |
+
"tokens_trained": 0.034030032
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 0.10212765957446808,
|
| 1460 |
+
"grad_norm": 8.660383224487305,
|
| 1461 |
+
"loss": 6.1497,
|
| 1462 |
+
"lr": 0.000718,
|
| 1463 |
+
"step": 360,
|
| 1464 |
+
"tokens_trained": 0.034218592
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 0.10269503546099291,
|
| 1468 |
+
"grad_norm": 9.382761001586914,
|
| 1469 |
+
"loss": 6.0665,
|
| 1470 |
+
"lr": 0.000722,
|
| 1471 |
+
"step": 362,
|
| 1472 |
+
"tokens_trained": 0.034408408
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.10326241134751774,
|
| 1476 |
+
"grad_norm": 6.915714263916016,
|
| 1477 |
+
"loss": 6.0636,
|
| 1478 |
+
"lr": 0.000726,
|
| 1479 |
+
"step": 364,
|
| 1480 |
+
"tokens_trained": 0.034600016
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.10382978723404256,
|
| 1484 |
+
"grad_norm": 7.8990631103515625,
|
| 1485 |
+
"loss": 6.0975,
|
| 1486 |
+
"lr": 0.00073,
|
| 1487 |
+
"step": 366,
|
| 1488 |
+
"tokens_trained": 0.034790792
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 0.10439716312056738,
|
| 1492 |
+
"grad_norm": 8.859809875488281,
|
| 1493 |
+
"loss": 6.0754,
|
| 1494 |
+
"lr": 0.000734,
|
| 1495 |
+
"step": 368,
|
| 1496 |
+
"tokens_trained": 0.034981304
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 0.1049645390070922,
|
| 1500 |
+
"grad_norm": 7.392801761627197,
|
| 1501 |
+
"loss": 6.039,
|
| 1502 |
+
"lr": 0.000738,
|
| 1503 |
+
"step": 370,
|
| 1504 |
+
"tokens_trained": 0.03516956
|
| 1505 |
+
},
|
| 1506 |
+
{
|
| 1507 |
+
"epoch": 0.10553191489361702,
|
| 1508 |
+
"grad_norm": 9.427324295043945,
|
| 1509 |
+
"loss": 6.084,
|
| 1510 |
+
"lr": 0.000742,
|
| 1511 |
+
"step": 372,
|
| 1512 |
+
"tokens_trained": 0.035358816
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 0.10609929078014184,
|
| 1516 |
+
"grad_norm": 7.168910503387451,
|
| 1517 |
+
"loss": 6.0498,
|
| 1518 |
+
"lr": 0.000746,
|
| 1519 |
+
"step": 374,
|
| 1520 |
+
"tokens_trained": 0.035548016
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 0.10638297872340426,
|
| 1524 |
+
"eval_loss": 6.038269996643066,
|
| 1525 |
+
"eval_runtime": 21.3445,
|
| 1526 |
+
"step": 375,
|
| 1527 |
+
"tokens_trained": 0.035644104
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 0.10666666666666667,
|
| 1531 |
+
"grad_norm": 7.899259567260742,
|
| 1532 |
+
"loss": 6.0345,
|
| 1533 |
+
"lr": 0.00075,
|
| 1534 |
+
"step": 376,
|
| 1535 |
+
"tokens_trained": 0.035739856
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.1072340425531915,
|
| 1539 |
+
"grad_norm": 8.91533374786377,
|
| 1540 |
+
"loss": 6.0386,
|
| 1541 |
+
"lr": 0.000754,
|
| 1542 |
+
"step": 378,
|
| 1543 |
+
"tokens_trained": 0.035930264
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.10780141843971631,
|
| 1547 |
+
"grad_norm": 6.998043060302734,
|
| 1548 |
+
"loss": 6.0294,
|
| 1549 |
+
"lr": 0.000758,
|
| 1550 |
+
"step": 380,
|
| 1551 |
+
"tokens_trained": 0.036119616
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 0.10836879432624114,
|
| 1555 |
+
"grad_norm": 7.343894958496094,
|
| 1556 |
+
"loss": 6.0116,
|
| 1557 |
+
"lr": 0.000762,
|
| 1558 |
+
"step": 382,
|
| 1559 |
+
"tokens_trained": 0.036308416
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 0.10893617021276596,
|
| 1563 |
+
"grad_norm": 8.182528495788574,
|
| 1564 |
+
"loss": 5.9904,
|
| 1565 |
+
"lr": 0.0007660000000000001,
|
| 1566 |
+
"step": 384,
|
| 1567 |
+
"tokens_trained": 0.036497264
|
| 1568 |
+
},
|
| 1569 |
+
{
|
| 1570 |
+
"epoch": 0.10950354609929078,
|
| 1571 |
+
"grad_norm": 7.927818775177002,
|
| 1572 |
+
"loss": 6.0345,
|
| 1573 |
+
"lr": 0.0007700000000000001,
|
| 1574 |
+
"step": 386,
|
| 1575 |
+
"tokens_trained": 0.036688192
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 0.1100709219858156,
|
| 1579 |
+
"grad_norm": 8.07447338104248,
|
| 1580 |
+
"loss": 5.9685,
|
| 1581 |
+
"lr": 0.0007740000000000001,
|
| 1582 |
+
"step": 388,
|
| 1583 |
+
"tokens_trained": 0.036878256
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 0.11063829787234042,
|
| 1587 |
+
"grad_norm": 7.281871318817139,
|
| 1588 |
+
"loss": 6.0125,
|
| 1589 |
+
"lr": 0.000778,
|
| 1590 |
+
"step": 390,
|
| 1591 |
+
"tokens_trained": 0.037068272
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.11120567375886525,
|
| 1595 |
+
"grad_norm": 8.298929214477539,
|
| 1596 |
+
"loss": 6.0071,
|
| 1597 |
+
"lr": 0.000782,
|
| 1598 |
+
"step": 392,
|
| 1599 |
+
"tokens_trained": 0.037259464
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.11177304964539007,
|
| 1603 |
+
"grad_norm": 7.546716690063477,
|
| 1604 |
+
"loss": 5.9721,
|
| 1605 |
+
"lr": 0.000786,
|
| 1606 |
+
"step": 394,
|
| 1607 |
+
"tokens_trained": 0.037449696
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 0.1123404255319149,
|
| 1611 |
+
"grad_norm": 8.28548526763916,
|
| 1612 |
+
"loss": 5.9819,
|
| 1613 |
+
"lr": 0.00079,
|
| 1614 |
+
"step": 396,
|
| 1615 |
+
"tokens_trained": 0.037639672
|
| 1616 |
+
},
|
| 1617 |
+
{
|
| 1618 |
+
"epoch": 0.11290780141843972,
|
| 1619 |
+
"grad_norm": 7.064655303955078,
|
| 1620 |
+
"loss": 5.9873,
|
| 1621 |
+
"lr": 0.0007940000000000001,
|
| 1622 |
+
"step": 398,
|
| 1623 |
+
"tokens_trained": 0.03782712
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 0.11347517730496454,
|
| 1627 |
+
"grad_norm": 7.743175506591797,
|
| 1628 |
+
"loss": 5.9528,
|
| 1629 |
+
"lr": 0.0007980000000000001,
|
| 1630 |
+
"step": 400,
|
| 1631 |
+
"tokens_trained": 0.03801792
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 0.11404255319148936,
|
| 1635 |
+
"grad_norm": 7.00898551940918,
|
| 1636 |
+
"loss": 5.9504,
|
| 1637 |
+
"lr": 0.0008020000000000001,
|
| 1638 |
+
"step": 402,
|
| 1639 |
+
"tokens_trained": 0.038209176
|
| 1640 |
+
},
|
| 1641 |
+
{
|
| 1642 |
+
"epoch": 0.11460992907801418,
|
| 1643 |
+
"grad_norm": 7.9350409507751465,
|
| 1644 |
+
"loss": 5.9555,
|
| 1645 |
+
"lr": 0.0008060000000000001,
|
| 1646 |
+
"step": 404,
|
| 1647 |
+
"tokens_trained": 0.03839824
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.11517730496453901,
|
| 1651 |
+
"grad_norm": 7.048569679260254,
|
| 1652 |
+
"loss": 5.9787,
|
| 1653 |
+
"lr": 0.0008100000000000001,
|
| 1654 |
+
"step": 406,
|
| 1655 |
+
"tokens_trained": 0.03858732
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.11574468085106383,
|
| 1659 |
+
"grad_norm": 7.088194370269775,
|
| 1660 |
+
"loss": 5.928,
|
| 1661 |
+
"lr": 0.0008139999999999999,
|
| 1662 |
+
"step": 408,
|
| 1663 |
+
"tokens_trained": 0.038777712
|
| 1664 |
+
},
|
| 1665 |
+
{
|
| 1666 |
+
"epoch": 0.11631205673758865,
|
| 1667 |
+
"grad_norm": 8.230712890625,
|
| 1668 |
+
"loss": 5.9716,
|
| 1669 |
+
"lr": 0.0008179999999999999,
|
| 1670 |
+
"step": 410,
|
| 1671 |
+
"tokens_trained": 0.038969464
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 0.11687943262411347,
|
| 1675 |
+
"grad_norm": 8.076972007751465,
|
| 1676 |
+
"loss": 5.9624,
|
| 1677 |
+
"lr": 0.0008219999999999999,
|
| 1678 |
+
"step": 412,
|
| 1679 |
+
"tokens_trained": 0.039162064
|
| 1680 |
+
},
|
| 1681 |
+
{
|
| 1682 |
+
"epoch": 0.1174468085106383,
|
| 1683 |
+
"grad_norm": 8.065289497375488,
|
| 1684 |
+
"loss": 5.9937,
|
| 1685 |
+
"lr": 0.000826,
|
| 1686 |
+
"step": 414,
|
| 1687 |
+
"tokens_trained": 0.039348688
|
| 1688 |
+
},
|
| 1689 |
+
{
|
| 1690 |
+
"epoch": 0.11801418439716312,
|
| 1691 |
+
"grad_norm": 6.393420696258545,
|
| 1692 |
+
"loss": 5.9278,
|
| 1693 |
+
"lr": 0.00083,
|
| 1694 |
+
"step": 416,
|
| 1695 |
+
"tokens_trained": 0.03953732
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 0.11858156028368794,
|
| 1699 |
+
"grad_norm": 7.384702682495117,
|
| 1700 |
+
"loss": 5.931,
|
| 1701 |
+
"lr": 0.000834,
|
| 1702 |
+
"step": 418,
|
| 1703 |
+
"tokens_trained": 0.039729808
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.11914893617021277,
|
| 1707 |
+
"grad_norm": 7.007425308227539,
|
| 1708 |
+
"loss": 5.93,
|
| 1709 |
+
"lr": 0.000838,
|
| 1710 |
+
"step": 420,
|
| 1711 |
+
"tokens_trained": 0.039921096
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.11971631205673759,
|
| 1715 |
+
"grad_norm": 7.112692832946777,
|
| 1716 |
+
"loss": 5.9625,
|
| 1717 |
+
"lr": 0.000842,
|
| 1718 |
+
"step": 422,
|
| 1719 |
+
"tokens_trained": 0.040110856
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 0.12028368794326241,
|
| 1723 |
+
"grad_norm": 8.484418869018555,
|
| 1724 |
+
"loss": 5.9848,
|
| 1725 |
+
"lr": 0.000846,
|
| 1726 |
+
"step": 424,
|
| 1727 |
+
"tokens_trained": 0.040300504
|
| 1728 |
+
},
|
| 1729 |
+
{
|
| 1730 |
+
"epoch": 0.12085106382978723,
|
| 1731 |
+
"grad_norm": 6.633459091186523,
|
| 1732 |
+
"loss": 6.0226,
|
| 1733 |
+
"lr": 0.00085,
|
| 1734 |
+
"step": 426,
|
| 1735 |
+
"tokens_trained": 0.04049056
|
| 1736 |
+
},
|
| 1737 |
+
{
|
| 1738 |
+
"epoch": 0.12141843971631205,
|
| 1739 |
+
"grad_norm": 7.796964168548584,
|
| 1740 |
+
"loss": 5.9152,
|
| 1741 |
+
"lr": 0.000854,
|
| 1742 |
+
"step": 428,
|
| 1743 |
+
"tokens_trained": 0.040680544
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 0.12198581560283688,
|
| 1747 |
+
"grad_norm": 7.833578586578369,
|
| 1748 |
+
"loss": 5.924,
|
| 1749 |
+
"lr": 0.000858,
|
| 1750 |
+
"step": 430,
|
| 1751 |
+
"tokens_trained": 0.040873128
|
| 1752 |
+
},
|
| 1753 |
+
{
|
| 1754 |
+
"epoch": 0.1225531914893617,
|
| 1755 |
+
"grad_norm": 6.7470550537109375,
|
| 1756 |
+
"loss": 5.9318,
|
| 1757 |
+
"lr": 0.000862,
|
| 1758 |
+
"step": 432,
|
| 1759 |
+
"tokens_trained": 0.041063488
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.12312056737588653,
|
| 1763 |
+
"grad_norm": 6.066318988800049,
|
| 1764 |
+
"loss": 5.9569,
|
| 1765 |
+
"lr": 0.000866,
|
| 1766 |
+
"step": 434,
|
| 1767 |
+
"tokens_trained": 0.041254368
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.12368794326241135,
|
| 1771 |
+
"grad_norm": 6.753541469573975,
|
| 1772 |
+
"loss": 5.8851,
|
| 1773 |
+
"lr": 0.00087,
|
| 1774 |
+
"step": 436,
|
| 1775 |
+
"tokens_trained": 0.04144516
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 0.12425531914893617,
|
| 1779 |
+
"grad_norm": 6.471331596374512,
|
| 1780 |
+
"loss": 5.864,
|
| 1781 |
+
"lr": 0.000874,
|
| 1782 |
+
"step": 438,
|
| 1783 |
+
"tokens_trained": 0.041636912
|
| 1784 |
+
},
|
| 1785 |
+
{
|
| 1786 |
+
"epoch": 0.12482269503546099,
|
| 1787 |
+
"grad_norm": 6.129056930541992,
|
| 1788 |
+
"loss": 5.8965,
|
| 1789 |
+
"lr": 0.000878,
|
| 1790 |
+
"step": 440,
|
| 1791 |
+
"tokens_trained": 0.041828104
|
| 1792 |
+
},
|
| 1793 |
+
{
|
| 1794 |
+
"epoch": 0.1253900709219858,
|
| 1795 |
+
"grad_norm": 6.478890895843506,
|
| 1796 |
+
"loss": 5.8817,
|
| 1797 |
+
"lr": 0.000882,
|
| 1798 |
+
"step": 442,
|
| 1799 |
+
"tokens_trained": 0.04201808
|
| 1800 |
+
},
|
| 1801 |
+
{
|
| 1802 |
+
"epoch": 0.12595744680851065,
|
| 1803 |
+
"grad_norm": 6.014713287353516,
|
| 1804 |
+
"loss": 5.8268,
|
| 1805 |
+
"lr": 0.0008860000000000001,
|
| 1806 |
+
"step": 444,
|
| 1807 |
+
"tokens_trained": 0.042207328
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 0.12652482269503545,
|
| 1811 |
+
"grad_norm": 5.505755424499512,
|
| 1812 |
+
"loss": 5.8684,
|
| 1813 |
+
"lr": 0.0008900000000000001,
|
| 1814 |
+
"step": 446,
|
| 1815 |
+
"tokens_trained": 0.042398152
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.1270921985815603,
|
| 1819 |
+
"grad_norm": 10.096606254577637,
|
| 1820 |
+
"loss": 5.8608,
|
| 1821 |
+
"lr": 0.000894,
|
| 1822 |
+
"step": 448,
|
| 1823 |
+
"tokens_trained": 0.042588984
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 0.1276595744680851,
|
| 1827 |
+
"grad_norm": 6.388499736785889,
|
| 1828 |
+
"loss": 5.8766,
|
| 1829 |
+
"lr": 0.000898,
|
| 1830 |
+
"step": 450,
|
| 1831 |
+
"tokens_trained": 0.042778592
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 0.12822695035460993,
|
| 1835 |
+
"grad_norm": 7.145125865936279,
|
| 1836 |
+
"loss": 5.8571,
|
| 1837 |
+
"lr": 0.000902,
|
| 1838 |
+
"step": 452,
|
| 1839 |
+
"tokens_trained": 0.042967176
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 0.12879432624113477,
|
| 1843 |
+
"grad_norm": 6.826383113861084,
|
| 1844 |
+
"loss": 5.8655,
|
| 1845 |
+
"lr": 0.000906,
|
| 1846 |
+
"step": 454,
|
| 1847 |
+
"tokens_trained": 0.043158952
|
| 1848 |
+
},
|
| 1849 |
+
{
|
| 1850 |
+
"epoch": 0.12936170212765957,
|
| 1851 |
+
"grad_norm": 6.036892414093018,
|
| 1852 |
+
"loss": 5.8775,
|
| 1853 |
+
"lr": 0.00091,
|
| 1854 |
+
"step": 456,
|
| 1855 |
+
"tokens_trained": 0.043349288
|
| 1856 |
+
},
|
| 1857 |
+
{
|
| 1858 |
+
"epoch": 0.1299290780141844,
|
| 1859 |
+
"grad_norm": 6.36528205871582,
|
| 1860 |
+
"loss": 5.8908,
|
| 1861 |
+
"lr": 0.0009140000000000001,
|
| 1862 |
+
"step": 458,
|
| 1863 |
+
"tokens_trained": 0.043539888
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 0.13049645390070921,
|
| 1867 |
+
"grad_norm": 6.317558288574219,
|
| 1868 |
+
"loss": 5.8702,
|
| 1869 |
+
"lr": 0.0009180000000000001,
|
| 1870 |
+
"step": 460,
|
| 1871 |
+
"tokens_trained": 0.04373232
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.13106382978723405,
|
| 1875 |
+
"grad_norm": 6.427131175994873,
|
| 1876 |
+
"loss": 5.8399,
|
| 1877 |
+
"lr": 0.0009220000000000001,
|
| 1878 |
+
"step": 462,
|
| 1879 |
+
"tokens_trained": 0.043922744
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 0.13163120567375886,
|
| 1883 |
+
"grad_norm": 5.666539669036865,
|
| 1884 |
+
"loss": 5.7899,
|
| 1885 |
+
"lr": 0.0009260000000000001,
|
| 1886 |
+
"step": 464,
|
| 1887 |
+
"tokens_trained": 0.044112888
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"epoch": 0.1321985815602837,
|
| 1891 |
+
"grad_norm": 5.241824150085449,
|
| 1892 |
+
"loss": 5.8203,
|
| 1893 |
+
"lr": 0.00093,
|
| 1894 |
+
"step": 466,
|
| 1895 |
+
"tokens_trained": 0.04430244
|
| 1896 |
+
},
|
| 1897 |
+
{
|
| 1898 |
+
"epoch": 0.1327659574468085,
|
| 1899 |
+
"grad_norm": 6.072646141052246,
|
| 1900 |
+
"loss": 5.8367,
|
| 1901 |
+
"lr": 0.000934,
|
| 1902 |
+
"step": 468,
|
| 1903 |
+
"tokens_trained": 0.044493528
|
| 1904 |
+
},
|
| 1905 |
+
{
|
| 1906 |
+
"epoch": 0.13333333333333333,
|
| 1907 |
+
"grad_norm": 6.414418697357178,
|
| 1908 |
+
"loss": 5.8236,
|
| 1909 |
+
"lr": 0.0009379999999999999,
|
| 1910 |
+
"step": 470,
|
| 1911 |
+
"tokens_trained": 0.044682328
|
| 1912 |
+
},
|
| 1913 |
+
{
|
| 1914 |
+
"epoch": 0.13390070921985817,
|
| 1915 |
+
"grad_norm": 6.958801746368408,
|
| 1916 |
+
"loss": 5.8179,
|
| 1917 |
+
"lr": 0.000942,
|
| 1918 |
+
"step": 472,
|
| 1919 |
+
"tokens_trained": 0.044874256
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 0.13446808510638297,
|
| 1923 |
+
"grad_norm": 5.787843227386475,
|
| 1924 |
+
"loss": 5.8478,
|
| 1925 |
+
"lr": 0.000946,
|
| 1926 |
+
"step": 474,
|
| 1927 |
+
"tokens_trained": 0.045065616
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.1350354609929078,
|
| 1931 |
+
"grad_norm": 5.5841240882873535,
|
| 1932 |
+
"loss": 5.8307,
|
| 1933 |
+
"lr": 0.00095,
|
| 1934 |
+
"step": 476,
|
| 1935 |
+
"tokens_trained": 0.045257024
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 0.13560283687943261,
|
| 1939 |
+
"grad_norm": 6.607712745666504,
|
| 1940 |
+
"loss": 5.8512,
|
| 1941 |
+
"lr": 0.000954,
|
| 1942 |
+
"step": 478,
|
| 1943 |
+
"tokens_trained": 0.045446432
|
| 1944 |
+
},
|
| 1945 |
+
{
|
| 1946 |
+
"epoch": 0.13617021276595745,
|
| 1947 |
+
"grad_norm": 5.473597049713135,
|
| 1948 |
+
"loss": 5.8174,
|
| 1949 |
+
"lr": 0.000958,
|
| 1950 |
+
"step": 480,
|
| 1951 |
+
"tokens_trained": 0.045636392
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 0.13673758865248226,
|
| 1955 |
+
"grad_norm": 5.435728549957275,
|
| 1956 |
+
"loss": 5.8308,
|
| 1957 |
+
"lr": 0.000962,
|
| 1958 |
+
"step": 482,
|
| 1959 |
+
"tokens_trained": 0.045823784
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 0.1373049645390071,
|
| 1963 |
+
"grad_norm": 6.049300670623779,
|
| 1964 |
+
"loss": 5.8293,
|
| 1965 |
+
"lr": 0.000966,
|
| 1966 |
+
"step": 484,
|
| 1967 |
+
"tokens_trained": 0.046013408
|
| 1968 |
+
},
|
| 1969 |
+
{
|
| 1970 |
+
"epoch": 0.13787234042553193,
|
| 1971 |
+
"grad_norm": 6.311764717102051,
|
| 1972 |
+
"loss": 5.8086,
|
| 1973 |
+
"lr": 0.0009699999999999999,
|
| 1974 |
+
"step": 486,
|
| 1975 |
+
"tokens_trained": 0.046202528
|
| 1976 |
+
},
|
| 1977 |
+
{
|
| 1978 |
+
"epoch": 0.13843971631205673,
|
| 1979 |
+
"grad_norm": 5.886009216308594,
|
| 1980 |
+
"loss": 5.7986,
|
| 1981 |
+
"lr": 0.000974,
|
| 1982 |
+
"step": 488,
|
| 1983 |
+
"tokens_trained": 0.04639404
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.13900709219858157,
|
| 1987 |
+
"grad_norm": 5.438202381134033,
|
| 1988 |
+
"loss": 5.8473,
|
| 1989 |
+
"lr": 0.000978,
|
| 1990 |
+
"step": 490,
|
| 1991 |
+
"tokens_trained": 0.046586512
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 0.13957446808510637,
|
| 1995 |
+
"grad_norm": 5.08393669128418,
|
| 1996 |
+
"loss": 5.7613,
|
| 1997 |
+
"lr": 0.000982,
|
| 1998 |
+
"step": 492,
|
| 1999 |
+
"tokens_trained": 0.046777448
|
| 2000 |
+
},
|
| 2001 |
+
{
|
| 2002 |
+
"epoch": 0.1401418439716312,
|
| 2003 |
+
"grad_norm": 5.645389080047607,
|
| 2004 |
+
"loss": 5.7723,
|
| 2005 |
+
"lr": 0.0009860000000000001,
|
| 2006 |
+
"step": 494,
|
| 2007 |
+
"tokens_trained": 0.046966096
|
| 2008 |
+
},
|
| 2009 |
+
{
|
| 2010 |
+
"epoch": 0.14070921985815601,
|
| 2011 |
+
"grad_norm": 6.320916652679443,
|
| 2012 |
+
"loss": 5.7772,
|
| 2013 |
+
"lr": 0.00099,
|
| 2014 |
+
"step": 496,
|
| 2015 |
+
"tokens_trained": 0.047155152
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 0.14127659574468085,
|
| 2019 |
+
"grad_norm": 5.573540210723877,
|
| 2020 |
+
"loss": 5.7412,
|
| 2021 |
+
"lr": 0.000994,
|
| 2022 |
+
"step": 498,
|
| 2023 |
+
"tokens_trained": 0.047345352
|
| 2024 |
+
},
|
| 2025 |
+
{
|
| 2026 |
+
"epoch": 0.14184397163120568,
|
| 2027 |
+
"grad_norm": 4.939594745635986,
|
| 2028 |
+
"loss": 5.8208,
|
| 2029 |
+
"lr": 0.000998,
|
| 2030 |
+
"step": 500,
|
| 2031 |
+
"tokens_trained": 0.047535016
|
| 2032 |
+
},
|
| 2033 |
+
{
|
| 2034 |
+
"epoch": 0.14184397163120568,
|
| 2035 |
+
"eval_loss": 5.799490928649902,
|
| 2036 |
+
"eval_runtime": 20.8575,
|
| 2037 |
+
"step": 500,
|
| 2038 |
+
"tokens_trained": 0.047535016
|
| 2039 |
+
},
|
| 2040 |
+
{
|
| 2041 |
+
"epoch": 0.1424113475177305,
|
| 2042 |
+
"grad_norm": 5.805343151092529,
|
| 2043 |
+
"loss": 5.7734,
|
| 2044 |
+
"lr": 0.00099986013986014,
|
| 2045 |
+
"step": 502,
|
| 2046 |
+
"tokens_trained": 0.047724216
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 0.14297872340425533,
|
| 2050 |
+
"grad_norm": 5.831176280975342,
|
| 2051 |
+
"loss": 5.8044,
|
| 2052 |
+
"lr": 0.0009995804195804196,
|
| 2053 |
+
"step": 504,
|
| 2054 |
+
"tokens_trained": 0.047914328
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 0.14354609929078013,
|
| 2058 |
+
"grad_norm": 5.045091152191162,
|
| 2059 |
+
"loss": 5.8133,
|
| 2060 |
+
"lr": 0.0009993006993006994,
|
| 2061 |
+
"step": 506,
|
| 2062 |
+
"tokens_trained": 0.048105032
|
| 2063 |
+
},
|
| 2064 |
+
{
|
| 2065 |
+
"epoch": 0.14411347517730497,
|
| 2066 |
+
"grad_norm": 5.276819705963135,
|
| 2067 |
+
"loss": 5.7555,
|
| 2068 |
+
"lr": 0.000999020979020979,
|
| 2069 |
+
"step": 508,
|
| 2070 |
+
"tokens_trained": 0.048293104
|
| 2071 |
+
},
|
| 2072 |
+
{
|
| 2073 |
+
"epoch": 0.14468085106382977,
|
| 2074 |
+
"grad_norm": 5.710324287414551,
|
| 2075 |
+
"loss": 5.7619,
|
| 2076 |
+
"lr": 0.0009987412587412587,
|
| 2077 |
+
"step": 510,
|
| 2078 |
+
"tokens_trained": 0.048483888
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 0.1452482269503546,
|
| 2082 |
+
"grad_norm": 4.9472527503967285,
|
| 2083 |
+
"loss": 5.767,
|
| 2084 |
+
"lr": 0.0009984615384615386,
|
| 2085 |
+
"step": 512,
|
| 2086 |
+
"tokens_trained": 0.04867336
|
| 2087 |
+
},
|
| 2088 |
+
{
|
| 2089 |
+
"epoch": 0.14581560283687944,
|
| 2090 |
+
"grad_norm": 5.410078525543213,
|
| 2091 |
+
"loss": 5.7238,
|
| 2092 |
+
"lr": 0.0009981818181818182,
|
| 2093 |
+
"step": 514,
|
| 2094 |
+
"tokens_trained": 0.048863104
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 0.14638297872340425,
|
| 2098 |
+
"grad_norm": 6.025843143463135,
|
| 2099 |
+
"loss": 5.7664,
|
| 2100 |
+
"lr": 0.000997902097902098,
|
| 2101 |
+
"step": 516,
|
| 2102 |
+
"tokens_trained": 0.049053856
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 0.14695035460992908,
|
| 2106 |
+
"grad_norm": 5.3211669921875,
|
| 2107 |
+
"loss": 5.747,
|
| 2108 |
+
"lr": 0.0009976223776223777,
|
| 2109 |
+
"step": 518,
|
| 2110 |
+
"tokens_trained": 0.049245104
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 0.1475177304964539,
|
| 2114 |
+
"grad_norm": 6.059483051300049,
|
| 2115 |
+
"loss": 5.7611,
|
| 2116 |
+
"lr": 0.0009973426573426573,
|
| 2117 |
+
"step": 520,
|
| 2118 |
+
"tokens_trained": 0.049434368
|
| 2119 |
+
},
|
| 2120 |
+
{
|
| 2121 |
+
"epoch": 0.14808510638297873,
|
| 2122 |
+
"grad_norm": 5.362505912780762,
|
| 2123 |
+
"loss": 5.7607,
|
| 2124 |
+
"lr": 0.000997062937062937,
|
| 2125 |
+
"step": 522,
|
| 2126 |
+
"tokens_trained": 0.049622648
|
| 2127 |
+
},
|
| 2128 |
+
{
|
| 2129 |
+
"epoch": 0.14865248226950353,
|
| 2130 |
+
"grad_norm": 5.391371726989746,
|
| 2131 |
+
"loss": 5.7857,
|
| 2132 |
+
"lr": 0.0009967832167832168,
|
| 2133 |
+
"step": 524,
|
| 2134 |
+
"tokens_trained": 0.049812304
|
| 2135 |
+
},
|
| 2136 |
+
{
|
| 2137 |
+
"epoch": 0.14921985815602837,
|
| 2138 |
+
"grad_norm": 4.3839030265808105,
|
| 2139 |
+
"loss": 5.7334,
|
| 2140 |
+
"lr": 0.0009965034965034964,
|
| 2141 |
+
"step": 526,
|
| 2142 |
+
"tokens_trained": 0.05000356
|
| 2143 |
+
},
|
| 2144 |
+
{
|
| 2145 |
+
"epoch": 0.1497872340425532,
|
| 2146 |
+
"grad_norm": 5.008530616760254,
|
| 2147 |
+
"loss": 5.7475,
|
| 2148 |
+
"lr": 0.0009962237762237763,
|
| 2149 |
+
"step": 528,
|
| 2150 |
+
"tokens_trained": 0.050193304
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"epoch": 0.150354609929078,
|
| 2154 |
+
"grad_norm": 5.068671226501465,
|
| 2155 |
+
"loss": 5.7866,
|
| 2156 |
+
"lr": 0.000995944055944056,
|
| 2157 |
+
"step": 530,
|
| 2158 |
+
"tokens_trained": 0.050382856
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 0.15092198581560284,
|
| 2162 |
+
"grad_norm": 5.399240493774414,
|
| 2163 |
+
"loss": 5.6857,
|
| 2164 |
+
"lr": 0.0009956643356643356,
|
| 2165 |
+
"step": 532,
|
| 2166 |
+
"tokens_trained": 0.050570864
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 0.15148936170212765,
|
| 2170 |
+
"grad_norm": 5.689481735229492,
|
| 2171 |
+
"loss": 5.7586,
|
| 2172 |
+
"lr": 0.0009953846153846154,
|
| 2173 |
+
"step": 534,
|
| 2174 |
+
"tokens_trained": 0.050760384
|
| 2175 |
+
},
|
| 2176 |
+
{
|
| 2177 |
+
"epoch": 0.15205673758865249,
|
| 2178 |
+
"grad_norm": 4.652275562286377,
|
| 2179 |
+
"loss": 5.7866,
|
| 2180 |
+
"lr": 0.000995104895104895,
|
| 2181 |
+
"step": 536,
|
| 2182 |
+
"tokens_trained": 0.050952712
|
| 2183 |
+
},
|
| 2184 |
+
{
|
| 2185 |
+
"epoch": 0.1526241134751773,
|
| 2186 |
+
"grad_norm": 4.126920223236084,
|
| 2187 |
+
"loss": 5.7261,
|
| 2188 |
+
"lr": 0.000994825174825175,
|
| 2189 |
+
"step": 538,
|
| 2190 |
+
"tokens_trained": 0.051141656
|
| 2191 |
+
},
|
| 2192 |
+
{
|
| 2193 |
+
"epoch": 0.15319148936170213,
|
| 2194 |
+
"grad_norm": 4.233098030090332,
|
| 2195 |
+
"loss": 5.6903,
|
| 2196 |
+
"lr": 0.0009945454545454546,
|
| 2197 |
+
"step": 540,
|
| 2198 |
+
"tokens_trained": 0.051331256
|
| 2199 |
+
},
|
| 2200 |
+
{
|
| 2201 |
+
"epoch": 0.15375886524822696,
|
| 2202 |
+
"grad_norm": 4.271973133087158,
|
| 2203 |
+
"loss": 5.7293,
|
| 2204 |
+
"lr": 0.0009942657342657344,
|
| 2205 |
+
"step": 542,
|
| 2206 |
+
"tokens_trained": 0.051522072
|
| 2207 |
+
},
|
| 2208 |
+
{
|
| 2209 |
+
"epoch": 0.15432624113475177,
|
| 2210 |
+
"grad_norm": 4.653008937835693,
|
| 2211 |
+
"loss": 5.7133,
|
| 2212 |
+
"lr": 0.000993986013986014,
|
| 2213 |
+
"step": 544,
|
| 2214 |
+
"tokens_trained": 0.051711624
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 0.1548936170212766,
|
| 2218 |
+
"grad_norm": 4.192624092102051,
|
| 2219 |
+
"loss": 5.6876,
|
| 2220 |
+
"lr": 0.0009937062937062937,
|
| 2221 |
+
"step": 546,
|
| 2222 |
+
"tokens_trained": 0.051901744
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 0.1554609929078014,
|
| 2226 |
+
"grad_norm": 5.497848033905029,
|
| 2227 |
+
"loss": 5.7378,
|
| 2228 |
+
"lr": 0.0009934265734265735,
|
| 2229 |
+
"step": 548,
|
| 2230 |
+
"tokens_trained": 0.052092872
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"epoch": 0.15602836879432624,
|
| 2234 |
+
"grad_norm": 4.350259780883789,
|
| 2235 |
+
"loss": 5.6533,
|
| 2236 |
+
"lr": 0.0009931468531468532,
|
| 2237 |
+
"step": 550,
|
| 2238 |
+
"tokens_trained": 0.052281768
|
| 2239 |
+
},
|
| 2240 |
+
{
|
| 2241 |
+
"epoch": 0.15659574468085105,
|
| 2242 |
+
"grad_norm": 4.515641689300537,
|
| 2243 |
+
"loss": 5.7492,
|
| 2244 |
+
"lr": 0.000992867132867133,
|
| 2245 |
+
"step": 552,
|
| 2246 |
+
"tokens_trained": 0.052471848
|
| 2247 |
+
},
|
| 2248 |
+
{
|
| 2249 |
+
"epoch": 0.15716312056737589,
|
| 2250 |
+
"grad_norm": 4.628066539764404,
|
| 2251 |
+
"loss": 5.7113,
|
| 2252 |
+
"lr": 0.0009925874125874127,
|
| 2253 |
+
"step": 554,
|
| 2254 |
+
"tokens_trained": 0.052660168
|
| 2255 |
+
},
|
| 2256 |
+
{
|
| 2257 |
+
"epoch": 0.15773049645390072,
|
| 2258 |
+
"grad_norm": 4.8322930335998535,
|
| 2259 |
+
"loss": 5.6696,
|
| 2260 |
+
"lr": 0.0009923076923076923,
|
| 2261 |
+
"step": 556,
|
| 2262 |
+
"tokens_trained": 0.05284776
|
| 2263 |
+
},
|
| 2264 |
+
{
|
| 2265 |
+
"epoch": 0.15829787234042553,
|
| 2266 |
+
"grad_norm": 3.999706506729126,
|
| 2267 |
+
"loss": 5.7296,
|
| 2268 |
+
"lr": 0.000992027972027972,
|
| 2269 |
+
"step": 558,
|
| 2270 |
+
"tokens_trained": 0.053037344
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 0.15886524822695036,
|
| 2274 |
+
"grad_norm": 4.332971572875977,
|
| 2275 |
+
"loss": 5.7362,
|
| 2276 |
+
"lr": 0.0009917482517482518,
|
| 2277 |
+
"step": 560,
|
| 2278 |
+
"tokens_trained": 0.053228168
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 0.15943262411347517,
|
| 2282 |
+
"grad_norm": 4.500301361083984,
|
| 2283 |
+
"loss": 5.6982,
|
| 2284 |
+
"lr": 0.0009914685314685314,
|
| 2285 |
+
"step": 562,
|
| 2286 |
+
"tokens_trained": 0.05341856
|
| 2287 |
+
},
|
| 2288 |
+
{
|
| 2289 |
+
"epoch": 0.16,
|
| 2290 |
+
"grad_norm": 4.721808910369873,
|
| 2291 |
+
"loss": 5.7166,
|
| 2292 |
+
"lr": 0.0009911888111888113,
|
| 2293 |
+
"step": 564,
|
| 2294 |
+
"tokens_trained": 0.053608824
|
| 2295 |
+
},
|
| 2296 |
+
{
|
| 2297 |
+
"epoch": 0.1605673758865248,
|
| 2298 |
+
"grad_norm": 5.265316009521484,
|
| 2299 |
+
"loss": 5.7069,
|
| 2300 |
+
"lr": 0.000990909090909091,
|
| 2301 |
+
"step": 566,
|
| 2302 |
+
"tokens_trained": 0.053799728
|
| 2303 |
+
},
|
| 2304 |
+
{
|
| 2305 |
+
"epoch": 0.16113475177304964,
|
| 2306 |
+
"grad_norm": 5.024131774902344,
|
| 2307 |
+
"loss": 5.7113,
|
| 2308 |
+
"lr": 0.0009906293706293705,
|
| 2309 |
+
"step": 568,
|
| 2310 |
+
"tokens_trained": 0.05398944
|
| 2311 |
+
},
|
| 2312 |
+
{
|
| 2313 |
+
"epoch": 0.16170212765957448,
|
| 2314 |
+
"grad_norm": 4.063276767730713,
|
| 2315 |
+
"loss": 5.6251,
|
| 2316 |
+
"lr": 0.0009903496503496504,
|
| 2317 |
+
"step": 570,
|
| 2318 |
+
"tokens_trained": 0.054176512
|
| 2319 |
+
},
|
| 2320 |
+
{
|
| 2321 |
+
"epoch": 0.1622695035460993,
|
| 2322 |
+
"grad_norm": 4.15974760055542,
|
| 2323 |
+
"loss": 5.6912,
|
| 2324 |
+
"lr": 0.00099006993006993,
|
| 2325 |
+
"step": 572,
|
| 2326 |
+
"tokens_trained": 0.054367072
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 0.16283687943262412,
|
| 2330 |
+
"grad_norm": 4.338894844055176,
|
| 2331 |
+
"loss": 5.6807,
|
| 2332 |
+
"lr": 0.0009897902097902099,
|
| 2333 |
+
"step": 574,
|
| 2334 |
+
"tokens_trained": 0.054559184
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 0.16340425531914893,
|
| 2338 |
+
"grad_norm": 5.535487174987793,
|
| 2339 |
+
"loss": 5.6765,
|
| 2340 |
+
"lr": 0.0009895104895104895,
|
| 2341 |
+
"step": 576,
|
| 2342 |
+
"tokens_trained": 0.054748904
|
| 2343 |
+
},
|
| 2344 |
+
{
|
| 2345 |
+
"epoch": 0.16397163120567376,
|
| 2346 |
+
"grad_norm": 4.379040241241455,
|
| 2347 |
+
"loss": 5.6884,
|
| 2348 |
+
"lr": 0.0009892307692307694,
|
| 2349 |
+
"step": 578,
|
| 2350 |
+
"tokens_trained": 0.054936136
|
| 2351 |
+
},
|
| 2352 |
+
{
|
| 2353 |
+
"epoch": 0.16453900709219857,
|
| 2354 |
+
"grad_norm": 4.746179103851318,
|
| 2355 |
+
"loss": 5.6885,
|
| 2356 |
+
"lr": 0.000988951048951049,
|
| 2357 |
+
"step": 580,
|
| 2358 |
+
"tokens_trained": 0.055125584
|
| 2359 |
+
},
|
| 2360 |
+
{
|
| 2361 |
+
"epoch": 0.1651063829787234,
|
| 2362 |
+
"grad_norm": 4.949806213378906,
|
| 2363 |
+
"loss": 5.7061,
|
| 2364 |
+
"lr": 0.0009886713286713286,
|
| 2365 |
+
"step": 582,
|
| 2366 |
+
"tokens_trained": 0.055314608
|
| 2367 |
+
},
|
| 2368 |
+
{
|
| 2369 |
+
"epoch": 0.16567375886524824,
|
| 2370 |
+
"grad_norm": 4.507448196411133,
|
| 2371 |
+
"loss": 5.6339,
|
| 2372 |
+
"lr": 0.0009883916083916085,
|
| 2373 |
+
"step": 584,
|
| 2374 |
+
"tokens_trained": 0.055503992
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"epoch": 0.16624113475177305,
|
| 2378 |
+
"grad_norm": 4.131013870239258,
|
| 2379 |
+
"loss": 5.7122,
|
| 2380 |
+
"lr": 0.0009881118881118881,
|
| 2381 |
+
"step": 586,
|
| 2382 |
+
"tokens_trained": 0.055693376
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 0.16680851063829788,
|
| 2386 |
+
"grad_norm": 5.32897424697876,
|
| 2387 |
+
"loss": 5.7192,
|
| 2388 |
+
"lr": 0.000987832167832168,
|
| 2389 |
+
"step": 588,
|
| 2390 |
+
"tokens_trained": 0.05588452
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 0.1673758865248227,
|
| 2394 |
+
"grad_norm": 4.166877746582031,
|
| 2395 |
+
"loss": 5.6666,
|
| 2396 |
+
"lr": 0.0009875524475524476,
|
| 2397 |
+
"step": 590,
|
| 2398 |
+
"tokens_trained": 0.056073936
|
| 2399 |
+
},
|
| 2400 |
+
{
|
| 2401 |
+
"epoch": 0.16794326241134752,
|
| 2402 |
+
"grad_norm": 4.393389701843262,
|
| 2403 |
+
"loss": 5.6113,
|
| 2404 |
+
"lr": 0.0009872727272727273,
|
| 2405 |
+
"step": 592,
|
| 2406 |
+
"tokens_trained": 0.056262224
|
| 2407 |
+
},
|
| 2408 |
+
{
|
| 2409 |
+
"epoch": 0.16851063829787233,
|
| 2410 |
+
"grad_norm": 4.466696739196777,
|
| 2411 |
+
"loss": 5.6466,
|
| 2412 |
+
"lr": 0.000986993006993007,
|
| 2413 |
+
"step": 594,
|
| 2414 |
+
"tokens_trained": 0.056454008
|
| 2415 |
+
},
|
| 2416 |
+
{
|
| 2417 |
+
"epoch": 0.16907801418439716,
|
| 2418 |
+
"grad_norm": 3.9413373470306396,
|
| 2419 |
+
"loss": 5.6838,
|
| 2420 |
+
"lr": 0.0009867132867132867,
|
| 2421 |
+
"step": 596,
|
| 2422 |
+
"tokens_trained": 0.05664444
|
| 2423 |
+
},
|
| 2424 |
+
{
|
| 2425 |
+
"epoch": 0.169645390070922,
|
| 2426 |
+
"grad_norm": 3.594649314880371,
|
| 2427 |
+
"loss": 5.6684,
|
| 2428 |
+
"lr": 0.0009864335664335664,
|
| 2429 |
+
"step": 598,
|
| 2430 |
+
"tokens_trained": 0.056833864
|
| 2431 |
+
},
|
| 2432 |
+
{
|
| 2433 |
+
"epoch": 0.1702127659574468,
|
| 2434 |
+
"grad_norm": 3.5969483852386475,
|
| 2435 |
+
"loss": 5.6619,
|
| 2436 |
+
"lr": 0.0009861538461538462,
|
| 2437 |
+
"step": 600,
|
| 2438 |
+
"tokens_trained": 0.05702332
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 0.17078014184397164,
|
| 2442 |
+
"grad_norm": 3.845414638519287,
|
| 2443 |
+
"loss": 5.5855,
|
| 2444 |
+
"lr": 0.0009858741258741259,
|
| 2445 |
+
"step": 602,
|
| 2446 |
+
"tokens_trained": 0.057212776
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 0.17134751773049645,
|
| 2450 |
+
"grad_norm": 3.9198834896087646,
|
| 2451 |
+
"loss": 5.6551,
|
| 2452 |
+
"lr": 0.0009855944055944055,
|
| 2453 |
+
"step": 604,
|
| 2454 |
+
"tokens_trained": 0.05740152
|
| 2455 |
+
},
|
| 2456 |
+
{
|
| 2457 |
+
"epoch": 0.17191489361702128,
|
| 2458 |
+
"grad_norm": 3.6764986515045166,
|
| 2459 |
+
"loss": 5.6228,
|
| 2460 |
+
"lr": 0.0009853146853146854,
|
| 2461 |
+
"step": 606,
|
| 2462 |
+
"tokens_trained": 0.057595616
|
| 2463 |
+
},
|
| 2464 |
+
{
|
| 2465 |
+
"epoch": 0.1724822695035461,
|
| 2466 |
+
"grad_norm": 3.8210043907165527,
|
| 2467 |
+
"loss": 5.6557,
|
| 2468 |
+
"lr": 0.000985034965034965,
|
| 2469 |
+
"step": 608,
|
| 2470 |
+
"tokens_trained": 0.057783968
|
| 2471 |
+
},
|
| 2472 |
+
{
|
| 2473 |
+
"epoch": 0.17304964539007092,
|
| 2474 |
+
"grad_norm": 3.893644094467163,
|
| 2475 |
+
"loss": 5.6675,
|
| 2476 |
+
"lr": 0.0009847552447552449,
|
| 2477 |
+
"step": 610,
|
| 2478 |
+
"tokens_trained": 0.057974832
|
| 2479 |
+
},
|
| 2480 |
+
{
|
| 2481 |
+
"epoch": 0.17361702127659576,
|
| 2482 |
+
"grad_norm": 3.280839681625366,
|
| 2483 |
+
"loss": 5.6442,
|
| 2484 |
+
"lr": 0.0009844755244755245,
|
| 2485 |
+
"step": 612,
|
| 2486 |
+
"tokens_trained": 0.058166272
|
| 2487 |
+
},
|
| 2488 |
+
{
|
| 2489 |
+
"epoch": 0.17418439716312056,
|
| 2490 |
+
"grad_norm": 3.4350404739379883,
|
| 2491 |
+
"loss": 5.6555,
|
| 2492 |
+
"lr": 0.0009841958041958043,
|
| 2493 |
+
"step": 614,
|
| 2494 |
+
"tokens_trained": 0.058356008
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 0.1747517730496454,
|
| 2498 |
+
"grad_norm": 3.7700448036193848,
|
| 2499 |
+
"loss": 5.6138,
|
| 2500 |
+
"lr": 0.000983916083916084,
|
| 2501 |
+
"step": 616,
|
| 2502 |
+
"tokens_trained": 0.058546792
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 0.1753191489361702,
|
| 2506 |
+
"grad_norm": 3.8182730674743652,
|
| 2507 |
+
"loss": 5.6931,
|
| 2508 |
+
"lr": 0.0009836363636363636,
|
| 2509 |
+
"step": 618,
|
| 2510 |
+
"tokens_trained": 0.058736296
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"epoch": 0.17588652482269504,
|
| 2514 |
+
"grad_norm": 3.9105372428894043,
|
| 2515 |
+
"loss": 5.6431,
|
| 2516 |
+
"lr": 0.0009833566433566435,
|
| 2517 |
+
"step": 620,
|
| 2518 |
+
"tokens_trained": 0.058927576
|
| 2519 |
+
},
|
| 2520 |
+
{
|
| 2521 |
+
"epoch": 0.17645390070921985,
|
| 2522 |
+
"grad_norm": 3.8897712230682373,
|
| 2523 |
+
"loss": 5.6203,
|
| 2524 |
+
"lr": 0.000983076923076923,
|
| 2525 |
+
"step": 622,
|
| 2526 |
+
"tokens_trained": 0.059118416
|
| 2527 |
+
},
|
| 2528 |
+
{
|
| 2529 |
+
"epoch": 0.17702127659574468,
|
| 2530 |
+
"grad_norm": 3.512194871902466,
|
| 2531 |
+
"loss": 5.6292,
|
| 2532 |
+
"lr": 0.000982797202797203,
|
| 2533 |
+
"step": 624,
|
| 2534 |
+
"tokens_trained": 0.059308568
|
| 2535 |
+
},
|
| 2536 |
+
{
|
| 2537 |
+
"epoch": 0.1773049645390071,
|
| 2538 |
+
"eval_loss": 5.630118370056152,
|
| 2539 |
+
"eval_runtime": 21.1591,
|
| 2540 |
+
"step": 625,
|
| 2541 |
+
"tokens_trained": 0.059404056
|
| 2542 |
+
}
|
| 2543 |
+
],
|
| 2544 |
+
"logging_steps": 2,
|
| 2545 |
+
"max_steps": 7650,
|
| 2546 |
+
"num_input_tokens_seen": 0,
|
| 2547 |
+
"num_train_epochs": 3,
|
| 2548 |
+
"save_steps": 125,
|
| 2549 |
+
"stateful_callbacks": {
|
| 2550 |
+
"TrainerControl": {
|
| 2551 |
+
"args": {
|
| 2552 |
+
"should_epoch_stop": false,
|
| 2553 |
+
"should_evaluate": false,
|
| 2554 |
+
"should_log": false,
|
| 2555 |
+
"should_save": true,
|
| 2556 |
+
"should_training_stop": false
|
| 2557 |
+
},
|
| 2558 |
+
"attributes": {}
|
| 2559 |
+
}
|
| 2560 |
+
},
|
| 2561 |
+
"total_flos": 0.0,
|
| 2562 |
+
"train_batch_size": 32,
|
| 2563 |
+
"trial_name": null,
|
| 2564 |
+
"trial_params": null
|
| 2565 |
+
}
|
checkpoint-625/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c9833ede7e0bc4a67116e2be49e665ef793dc257b8d78c77b367cb70647f355
|
| 3 |
+
size 5969
|