Hugging Face's logo

broadfield-dev
/
savant_2_gsm8k_final

Safetensors
Model card Files
xet
Community
broadfield-dev commited on
Commit
bb804a5
·
verified ·
1 Parent(s): 466ad96

Save benchmark: stable-run-sft-step-300

Browse files
Files changed (12) hide show
  1. checkpoints/stable-run-sft-step-300/config.json +45 -0
  2. checkpoints/stable-run-sft-step-300/generation_config.json +6 -0
  3. checkpoints/stable-run-sft-step-300/hyperparameters.json +17 -0
  4. checkpoints/stable-run-sft-step-300/merges.txt +0 -0
  5. checkpoints/stable-run-sft-step-300/model.safetensors +3 -0
  6. checkpoints/stable-run-sft-step-300/optimizer.pt +3 -0
  7. checkpoints/stable-run-sft-step-300/scheduler.pt +3 -0
  8. checkpoints/stable-run-sft-step-300/special_tokens_map.json +6 -0
  9. checkpoints/stable-run-sft-step-300/tokenizer.json +0 -0
  10. checkpoints/stable-run-sft-step-300/tokenizer_config.json +21 -0
  11. checkpoints/stable-run-sft-step-300/training_state.json +3007 -0
  12. checkpoints/stable-run-sft-step-300/vocab.json +0 -0
checkpoints/stable-run-sft-step-300/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_num_labels": 1,
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "dtype": "float32",
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 50256,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "LABEL_0": 0
18
+ },
19
+ "layer_norm_epsilon": 1e-05,
20
+ "model_type": "gpt2",
21
+ "n_ctx": 1024,
22
+ "n_embd": 768,
23
+ "n_head": 12,
24
+ "n_inner": null,
25
+ "n_layer": 6,
26
+ "n_positions": 1024,
27
+ "reorder_and_upcast_attn": false,
28
+ "resid_pdrop": 0.1,
29
+ "scale_attn_by_inverse_layer_idx": false,
30
+ "scale_attn_weights": true,
31
+ "summary_activation": null,
32
+ "summary_first_dropout": 0.1,
33
+ "summary_proj_to_labels": true,
34
+ "summary_type": "cls_index",
35
+ "summary_use_proj": true,
36
+ "task_specific_params": {
37
+ "text-generation": {
38
+ "do_sample": true,
39
+ "max_length": 50
40
+ }
41
+ },
42
+ "transformers_version": "4.56.1",
43
+ "use_cache": true,
44
+ "vocab_size": 50257
45
+ }
checkpoints/stable-run-sft-step-300/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.56.1"
6
+ }
checkpoints/stable-run-sft-step-300/hyperparameters.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "repo_id": "broadfield-dev/savant_2_gsm8k_final",
3
+ "resume_from_benchmark": "",
4
+ "benchmark_name_prefix": "stable-run",
5
+ "benchmark_interval": 20,
6
+ "sft_epochs": 4,
7
+ "sft_lr": 2e-05,
8
+ "sft_warmup_proportion": 0.1,
9
+ "rl_lr": 1.5e-06,
10
+ "sft_slice": "0:2000",
11
+ "rl_slice": "4000:7473",
12
+ "context_length": 1024,
13
+ "base_model_name": "distilgpt2",
14
+ "use_scheduler": true,
15
+ "sft_batch_size": 1,
16
+ "grad_accum_steps": 16
17
+ }
checkpoints/stable-run-sft-step-300/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/stable-run-sft-step-300/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0174b4a3acc641b653b7db8caeee88ff6f0530f8fcf5ce2c72e4b40292406ba2
3
+ size 327657928
checkpoints/stable-run-sft-step-300/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82391f89ded9f2c3cbec1c0cb61bae70a7f3b5f62d6df25dbb85265819fcc1a7
3
+ size 655362635
checkpoints/stable-run-sft-step-300/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b336e9bab051b9040c32f22fbbb077fe67130bccd77cbccd62af17bac33f0c4
3
+ size 1465
checkpoints/stable-run-sft-step-300/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
checkpoints/stable-run-sft-step-300/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/stable-run-sft-step-300/tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
checkpoints/stable-run-sft-step-300/training_state.json ADDED
@@ -0,0 +1,3007 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "phase": "SFT",
3
+ "total_optimizer_steps": 300,
4
+ "metrics": [
5
+ {
6
+ "Step": 1,
7
+ "Metric": "SFT Loss",
8
+ "Value": 10.806696891784668
9
+ },
10
+ {
11
+ "Step": 1,
12
+ "Metric": "Learning Rate",
13
+ "Value": 4.0000000000000003e-07
14
+ },
15
+ {
16
+ "Step": 2,
17
+ "Metric": "SFT Loss",
18
+ "Value": 20.197086334228516
19
+ },
20
+ {
21
+ "Step": 2,
22
+ "Metric": "Learning Rate",
23
+ "Value": 8.000000000000001e-07
24
+ },
25
+ {
26
+ "Step": 3,
27
+ "Metric": "SFT Loss",
28
+ "Value": 13.669203758239746
29
+ },
30
+ {
31
+ "Step": 3,
32
+ "Metric": "Learning Rate",
33
+ "Value": 1.2000000000000002e-06
34
+ },
35
+ {
36
+ "Step": 4,
37
+ "Metric": "SFT Loss",
38
+ "Value": 19.52617835998535
39
+ },
40
+ {
41
+ "Step": 4,
42
+ "Metric": "Learning Rate",
43
+ "Value": 1.6000000000000001e-06
44
+ },
45
+ {
46
+ "Step": 5,
47
+ "Metric": "SFT Loss",
48
+ "Value": 14.46614933013916
49
+ },
50
+ {
51
+ "Step": 5,
52
+ "Metric": "Learning Rate",
53
+ "Value": 2.0000000000000003e-06
54
+ },
55
+ {
56
+ "Step": 6,
57
+ "Metric": "SFT Loss",
58
+ "Value": 11.709370613098145
59
+ },
60
+ {
61
+ "Step": 6,
62
+ "Metric": "Learning Rate",
63
+ "Value": 2.4000000000000003e-06
64
+ },
65
+ {
66
+ "Step": 7,
67
+ "Metric": "SFT Loss",
68
+ "Value": 14.79263687133789
69
+ },
70
+ {
71
+ "Step": 7,
72
+ "Metric": "Learning Rate",
73
+ "Value": 2.8000000000000003e-06
74
+ },
75
+ {
76
+ "Step": 8,
77
+ "Metric": "SFT Loss",
78
+ "Value": 16.564573287963867
79
+ },
80
+ {
81
+ "Step": 8,
82
+ "Metric": "Learning Rate",
83
+ "Value": 3.2000000000000003e-06
84
+ },
85
+ {
86
+ "Step": 9,
87
+ "Metric": "SFT Loss",
88
+ "Value": 16.437776565551758
89
+ },
90
+ {
91
+ "Step": 9,
92
+ "Metric": "Learning Rate",
93
+ "Value": 3.6000000000000003e-06
94
+ },
95
+ {
96
+ "Step": 10,
97
+ "Metric": "SFT Loss",
98
+ "Value": 14.215919494628906
99
+ },
100
+ {
101
+ "Step": 10,
102
+ "Metric": "Learning Rate",
103
+ "Value": 4.000000000000001e-06
104
+ },
105
+ {
106
+ "Step": 11,
107
+ "Metric": "SFT Loss",
108
+ "Value": 13.728559494018555
109
+ },
110
+ {
111
+ "Step": 11,
112
+ "Metric": "Learning Rate",
113
+ "Value": 4.4e-06
114
+ },
115
+ {
116
+ "Step": 12,
117
+ "Metric": "SFT Loss",
118
+ "Value": 17.120494842529297
119
+ },
120
+ {
121
+ "Step": 12,
122
+ "Metric": "Learning Rate",
123
+ "Value": 4.800000000000001e-06
124
+ },
125
+ {
126
+ "Step": 13,
127
+ "Metric": "SFT Loss",
128
+ "Value": 12.443873405456543
129
+ },
130
+ {
131
+ "Step": 13,
132
+ "Metric": "Learning Rate",
133
+ "Value": 5.2e-06
134
+ },
135
+ {
136
+ "Step": 14,
137
+ "Metric": "SFT Loss",
138
+ "Value": 10.322935104370117
139
+ },
140
+ {
141
+ "Step": 14,
142
+ "Metric": "Learning Rate",
143
+ "Value": 5.600000000000001e-06
144
+ },
145
+ {
146
+ "Step": 15,
147
+ "Metric": "SFT Loss",
148
+ "Value": 10.010440826416016
149
+ },
150
+ {
151
+ "Step": 15,
152
+ "Metric": "Learning Rate",
153
+ "Value": 6e-06
154
+ },
155
+ {
156
+ "Step": 16,
157
+ "Metric": "SFT Loss",
158
+ "Value": 9.959354400634766
159
+ },
160
+ {
161
+ "Step": 16,
162
+ "Metric": "Learning Rate",
163
+ "Value": 6.4000000000000006e-06
164
+ },
165
+ {
166
+ "Step": 17,
167
+ "Metric": "SFT Loss",
168
+ "Value": 9.42132568359375
169
+ },
170
+ {
171
+ "Step": 17,
172
+ "Metric": "Learning Rate",
173
+ "Value": 6.800000000000001e-06
174
+ },
175
+ {
176
+ "Step": 18,
177
+ "Metric": "SFT Loss",
178
+ "Value": 10.809995651245117
179
+ },
180
+ {
181
+ "Step": 18,
182
+ "Metric": "Learning Rate",
183
+ "Value": 7.2000000000000005e-06
184
+ },
185
+ {
186
+ "Step": 19,
187
+ "Metric": "SFT Loss",
188
+ "Value": 11.641499519348145
189
+ },
190
+ {
191
+ "Step": 19,
192
+ "Metric": "Learning Rate",
193
+ "Value": 7.600000000000001e-06
194
+ },
195
+ {
196
+ "Step": 20,
197
+ "Metric": "SFT Loss",
198
+ "Value": 8.137388229370117
199
+ },
200
+ {
201
+ "Step": 20,
202
+ "Metric": "Learning Rate",
203
+ "Value": 8.000000000000001e-06
204
+ },
205
+ {
206
+ "Step": 21,
207
+ "Metric": "SFT Loss",
208
+ "Value": 11.187762260437012
209
+ },
210
+ {
211
+ "Step": 21,
212
+ "Metric": "Learning Rate",
213
+ "Value": 8.400000000000001e-06
214
+ },
215
+ {
216
+ "Step": 22,
217
+ "Metric": "SFT Loss",
218
+ "Value": 6.696204662322998
219
+ },
220
+ {
221
+ "Step": 22,
222
+ "Metric": "Learning Rate",
223
+ "Value": 8.8e-06
224
+ },
225
+ {
226
+ "Step": 23,
227
+ "Metric": "SFT Loss",
228
+ "Value": 9.350967407226562
229
+ },
230
+ {
231
+ "Step": 23,
232
+ "Metric": "Learning Rate",
233
+ "Value": 9.200000000000002e-06
234
+ },
235
+ {
236
+ "Step": 24,
237
+ "Metric": "SFT Loss",
238
+ "Value": 7.601217269897461
239
+ },
240
+ {
241
+ "Step": 24,
242
+ "Metric": "Learning Rate",
243
+ "Value": 9.600000000000001e-06
244
+ },
245
+ {
246
+ "Step": 25,
247
+ "Metric": "SFT Loss",
248
+ "Value": 7.671919345855713
249
+ },
250
+ {
251
+ "Step": 25,
252
+ "Metric": "Learning Rate",
253
+ "Value": 1e-05
254
+ },
255
+ {
256
+ "Step": 26,
257
+ "Metric": "SFT Loss",
258
+ "Value": 5.797372341156006
259
+ },
260
+ {
261
+ "Step": 26,
262
+ "Metric": "Learning Rate",
263
+ "Value": 1.04e-05
264
+ },
265
+ {
266
+ "Step": 27,
267
+ "Metric": "SFT Loss",
268
+ "Value": 7.414616107940674
269
+ },
270
+ {
271
+ "Step": 27,
272
+ "Metric": "Learning Rate",
273
+ "Value": 1.0800000000000002e-05
274
+ },
275
+ {
276
+ "Step": 28,
277
+ "Metric": "SFT Loss",
278
+ "Value": 7.067437171936035
279
+ },
280
+ {
281
+ "Step": 28,
282
+ "Metric": "Learning Rate",
283
+ "Value": 1.1200000000000001e-05
284
+ },
285
+ {
286
+ "Step": 29,
287
+ "Metric": "SFT Loss",
288
+ "Value": 6.7167463302612305
289
+ },
290
+ {
291
+ "Step": 29,
292
+ "Metric": "Learning Rate",
293
+ "Value": 1.16e-05
294
+ },
295
+ {
296
+ "Step": 30,
297
+ "Metric": "SFT Loss",
298
+ "Value": 6.630039691925049
299
+ },
300
+ {
301
+ "Step": 30,
302
+ "Metric": "Learning Rate",
303
+ "Value": 1.2e-05
304
+ },
305
+ {
306
+ "Step": 31,
307
+ "Metric": "SFT Loss",
308
+ "Value": 6.276569366455078
309
+ },
310
+ {
311
+ "Step": 31,
312
+ "Metric": "Learning Rate",
313
+ "Value": 1.2400000000000002e-05
314
+ },
315
+ {
316
+ "Step": 32,
317
+ "Metric": "SFT Loss",
318
+ "Value": 7.236689567565918
319
+ },
320
+ {
321
+ "Step": 32,
322
+ "Metric": "Learning Rate",
323
+ "Value": 1.2800000000000001e-05
324
+ },
325
+ {
326
+ "Step": 33,
327
+ "Metric": "SFT Loss",
328
+ "Value": 6.829200267791748
329
+ },
330
+ {
331
+ "Step": 33,
332
+ "Metric": "Learning Rate",
333
+ "Value": 1.3200000000000002e-05
334
+ },
335
+ {
336
+ "Step": 34,
337
+ "Metric": "SFT Loss",
338
+ "Value": 6.348658561706543
339
+ },
340
+ {
341
+ "Step": 34,
342
+ "Metric": "Learning Rate",
343
+ "Value": 1.3600000000000002e-05
344
+ },
345
+ {
346
+ "Step": 35,
347
+ "Metric": "SFT Loss",
348
+ "Value": 6.114589691162109
349
+ },
350
+ {
351
+ "Step": 35,
352
+ "Metric": "Learning Rate",
353
+ "Value": 1.4e-05
354
+ },
355
+ {
356
+ "Step": 36,
357
+ "Metric": "SFT Loss",
358
+ "Value": 5.820864677429199
359
+ },
360
+ {
361
+ "Step": 36,
362
+ "Metric": "Learning Rate",
363
+ "Value": 1.4400000000000001e-05
364
+ },
365
+ {
366
+ "Step": 37,
367
+ "Metric": "SFT Loss",
368
+ "Value": 6.093341827392578
369
+ },
370
+ {
371
+ "Step": 37,
372
+ "Metric": "Learning Rate",
373
+ "Value": 1.48e-05
374
+ },
375
+ {
376
+ "Step": 38,
377
+ "Metric": "SFT Loss",
378
+ "Value": 6.195661544799805
379
+ },
380
+ {
381
+ "Step": 38,
382
+ "Metric": "Learning Rate",
383
+ "Value": 1.5200000000000002e-05
384
+ },
385
+ {
386
+ "Step": 39,
387
+ "Metric": "SFT Loss",
388
+ "Value": 7.604869365692139
389
+ },
390
+ {
391
+ "Step": 39,
392
+ "Metric": "Learning Rate",
393
+ "Value": 1.5600000000000003e-05
394
+ },
395
+ {
396
+ "Step": 40,
397
+ "Metric": "SFT Loss",
398
+ "Value": 5.295370101928711
399
+ },
400
+ {
401
+ "Step": 40,
402
+ "Metric": "Learning Rate",
403
+ "Value": 1.6000000000000003e-05
404
+ },
405
+ {
406
+ "Step": 41,
407
+ "Metric": "SFT Loss",
408
+ "Value": 6.263326644897461
409
+ },
410
+ {
411
+ "Step": 41,
412
+ "Metric": "Learning Rate",
413
+ "Value": 1.64e-05
414
+ },
415
+ {
416
+ "Step": 42,
417
+ "Metric": "SFT Loss",
418
+ "Value": 6.123704433441162
419
+ },
420
+ {
421
+ "Step": 42,
422
+ "Metric": "Learning Rate",
423
+ "Value": 1.6800000000000002e-05
424
+ },
425
+ {
426
+ "Step": 43,
427
+ "Metric": "SFT Loss",
428
+ "Value": 6.104567050933838
429
+ },
430
+ {
431
+ "Step": 43,
432
+ "Metric": "Learning Rate",
433
+ "Value": 1.72e-05
434
+ },
435
+ {
436
+ "Step": 44,
437
+ "Metric": "SFT Loss",
438
+ "Value": 6.757107257843018
439
+ },
440
+ {
441
+ "Step": 44,
442
+ "Metric": "Learning Rate",
443
+ "Value": 1.76e-05
444
+ },
445
+ {
446
+ "Step": 45,
447
+ "Metric": "SFT Loss",
448
+ "Value": 6.533822059631348
449
+ },
450
+ {
451
+ "Step": 45,
452
+ "Metric": "Learning Rate",
453
+ "Value": 1.8e-05
454
+ },
455
+ {
456
+ "Step": 46,
457
+ "Metric": "SFT Loss",
458
+ "Value": 6.507102012634277
459
+ },
460
+ {
461
+ "Step": 46,
462
+ "Metric": "Learning Rate",
463
+ "Value": 1.8400000000000003e-05
464
+ },
465
+ {
466
+ "Step": 47,
467
+ "Metric": "SFT Loss",
468
+ "Value": 6.377279758453369
469
+ },
470
+ {
471
+ "Step": 47,
472
+ "Metric": "Learning Rate",
473
+ "Value": 1.88e-05
474
+ },
475
+ {
476
+ "Step": 48,
477
+ "Metric": "SFT Loss",
478
+ "Value": 6.2640581130981445
479
+ },
480
+ {
481
+ "Step": 48,
482
+ "Metric": "Learning Rate",
483
+ "Value": 1.9200000000000003e-05
484
+ },
485
+ {
486
+ "Step": 49,
487
+ "Metric": "SFT Loss",
488
+ "Value": 5.53227424621582
489
+ },
490
+ {
491
+ "Step": 49,
492
+ "Metric": "Learning Rate",
493
+ "Value": 1.9600000000000002e-05
494
+ },
495
+ {
496
+ "Step": 50,
497
+ "Metric": "SFT Loss",
498
+ "Value": 6.743251800537109
499
+ },
500
+ {
501
+ "Step": 50,
502
+ "Metric": "Learning Rate",
503
+ "Value": 2e-05
504
+ },
505
+ {
506
+ "Step": 51,
507
+ "Metric": "SFT Loss",
508
+ "Value": 5.5736985206604
509
+ },
510
+ {
511
+ "Step": 51,
512
+ "Metric": "Learning Rate",
513
+ "Value": 1.9955555555555557e-05
514
+ },
515
+ {
516
+ "Step": 52,
517
+ "Metric": "SFT Loss",
518
+ "Value": 5.360650539398193
519
+ },
520
+ {
521
+ "Step": 52,
522
+ "Metric": "Learning Rate",
523
+ "Value": 1.9911111111111112e-05
524
+ },
525
+ {
526
+ "Step": 53,
527
+ "Metric": "SFT Loss",
528
+ "Value": 5.423285484313965
529
+ },
530
+ {
531
+ "Step": 53,
532
+ "Metric": "Learning Rate",
533
+ "Value": 1.9866666666666667e-05
534
+ },
535
+ {
536
+ "Step": 54,
537
+ "Metric": "SFT Loss",
538
+ "Value": 5.108491897583008
539
+ },
540
+ {
541
+ "Step": 54,
542
+ "Metric": "Learning Rate",
543
+ "Value": 1.9822222222222226e-05
544
+ },
545
+ {
546
+ "Step": 55,
547
+ "Metric": "SFT Loss",
548
+ "Value": 4.632509231567383
549
+ },
550
+ {
551
+ "Step": 55,
552
+ "Metric": "Learning Rate",
553
+ "Value": 1.977777777777778e-05
554
+ },
555
+ {
556
+ "Step": 56,
557
+ "Metric": "SFT Loss",
558
+ "Value": 4.9901933670043945
559
+ },
560
+ {
561
+ "Step": 56,
562
+ "Metric": "Learning Rate",
563
+ "Value": 1.9733333333333336e-05
564
+ },
565
+ {
566
+ "Step": 57,
567
+ "Metric": "SFT Loss",
568
+ "Value": 4.968444347381592
569
+ },
570
+ {
571
+ "Step": 57,
572
+ "Metric": "Learning Rate",
573
+ "Value": 1.968888888888889e-05
574
+ },
575
+ {
576
+ "Step": 58,
577
+ "Metric": "SFT Loss",
578
+ "Value": 5.028273582458496
579
+ },
580
+ {
581
+ "Step": 58,
582
+ "Metric": "Learning Rate",
583
+ "Value": 1.9644444444444447e-05
584
+ },
585
+ {
586
+ "Step": 59,
587
+ "Metric": "SFT Loss",
588
+ "Value": 5.093855381011963
589
+ },
590
+ {
591
+ "Step": 59,
592
+ "Metric": "Learning Rate",
593
+ "Value": 1.9600000000000002e-05
594
+ },
595
+ {
596
+ "Step": 60,
597
+ "Metric": "SFT Loss",
598
+ "Value": 4.720518112182617
599
+ },
600
+ {
601
+ "Step": 60,
602
+ "Metric": "Learning Rate",
603
+ "Value": 1.9555555555555557e-05
604
+ },
605
+ {
606
+ "Step": 61,
607
+ "Metric": "SFT Loss",
608
+ "Value": 4.872599124908447
609
+ },
610
+ {
611
+ "Step": 61,
612
+ "Metric": "Learning Rate",
613
+ "Value": 1.9511111111111113e-05
614
+ },
615
+ {
616
+ "Step": 62,
617
+ "Metric": "SFT Loss",
618
+ "Value": 4.398301124572754
619
+ },
620
+ {
621
+ "Step": 62,
622
+ "Metric": "Learning Rate",
623
+ "Value": 1.9466666666666668e-05
624
+ },
625
+ {
626
+ "Step": 63,
627
+ "Metric": "SFT Loss",
628
+ "Value": 5.259819030761719
629
+ },
630
+ {
631
+ "Step": 63,
632
+ "Metric": "Learning Rate",
633
+ "Value": 1.9422222222222223e-05
634
+ },
635
+ {
636
+ "Step": 64,
637
+ "Metric": "SFT Loss",
638
+ "Value": 5.536286354064941
639
+ },
640
+ {
641
+ "Step": 64,
642
+ "Metric": "Learning Rate",
643
+ "Value": 1.9377777777777778e-05
644
+ },
645
+ {
646
+ "Step": 65,
647
+ "Metric": "SFT Loss",
648
+ "Value": 4.998850345611572
649
+ },
650
+ {
651
+ "Step": 65,
652
+ "Metric": "Learning Rate",
653
+ "Value": 1.9333333333333333e-05
654
+ },
655
+ {
656
+ "Step": 66,
657
+ "Metric": "SFT Loss",
658
+ "Value": 4.723838806152344
659
+ },
660
+ {
661
+ "Step": 66,
662
+ "Metric": "Learning Rate",
663
+ "Value": 1.928888888888889e-05
664
+ },
665
+ {
666
+ "Step": 67,
667
+ "Metric": "SFT Loss",
668
+ "Value": 5.087211608886719
669
+ },
670
+ {
671
+ "Step": 67,
672
+ "Metric": "Learning Rate",
673
+ "Value": 1.9244444444444444e-05
674
+ },
675
+ {
676
+ "Step": 68,
677
+ "Metric": "SFT Loss",
678
+ "Value": 4.477473258972168
679
+ },
680
+ {
681
+ "Step": 68,
682
+ "Metric": "Learning Rate",
683
+ "Value": 1.9200000000000003e-05
684
+ },
685
+ {
686
+ "Step": 69,
687
+ "Metric": "SFT Loss",
688
+ "Value": 4.780407905578613
689
+ },
690
+ {
691
+ "Step": 69,
692
+ "Metric": "Learning Rate",
693
+ "Value": 1.9155555555555558e-05
694
+ },
695
+ {
696
+ "Step": 70,
697
+ "Metric": "SFT Loss",
698
+ "Value": 4.482248783111572
699
+ },
700
+ {
701
+ "Step": 70,
702
+ "Metric": "Learning Rate",
703
+ "Value": 1.9111111111111113e-05
704
+ },
705
+ {
706
+ "Step": 71,
707
+ "Metric": "SFT Loss",
708
+ "Value": 4.773695468902588
709
+ },
710
+ {
711
+ "Step": 71,
712
+ "Metric": "Learning Rate",
713
+ "Value": 1.9066666666666668e-05
714
+ },
715
+ {
716
+ "Step": 72,
717
+ "Metric": "SFT Loss",
718
+ "Value": 4.399933815002441
719
+ },
720
+ {
721
+ "Step": 72,
722
+ "Metric": "Learning Rate",
723
+ "Value": 1.9022222222222223e-05
724
+ },
725
+ {
726
+ "Step": 73,
727
+ "Metric": "SFT Loss",
728
+ "Value": 4.540095329284668
729
+ },
730
+ {
731
+ "Step": 73,
732
+ "Metric": "Learning Rate",
733
+ "Value": 1.897777777777778e-05
734
+ },
735
+ {
736
+ "Step": 74,
737
+ "Metric": "SFT Loss",
738
+ "Value": 4.6496663093566895
739
+ },
740
+ {
741
+ "Step": 74,
742
+ "Metric": "Learning Rate",
743
+ "Value": 1.8933333333333334e-05
744
+ },
745
+ {
746
+ "Step": 75,
747
+ "Metric": "SFT Loss",
748
+ "Value": 5.276064872741699
749
+ },
750
+ {
751
+ "Step": 75,
752
+ "Metric": "Learning Rate",
753
+ "Value": 1.888888888888889e-05
754
+ },
755
+ {
756
+ "Step": 76,
757
+ "Metric": "SFT Loss",
758
+ "Value": 4.346099853515625
759
+ },
760
+ {
761
+ "Step": 76,
762
+ "Metric": "Learning Rate",
763
+ "Value": 1.8844444444444444e-05
764
+ },
765
+ {
766
+ "Step": 77,
767
+ "Metric": "SFT Loss",
768
+ "Value": 4.5329694747924805
769
+ },
770
+ {
771
+ "Step": 77,
772
+ "Metric": "Learning Rate",
773
+ "Value": 1.88e-05
774
+ },
775
+ {
776
+ "Step": 78,
777
+ "Metric": "SFT Loss",
778
+ "Value": 4.541317939758301
779
+ },
780
+ {
781
+ "Step": 78,
782
+ "Metric": "Learning Rate",
783
+ "Value": 1.8755555555555558e-05
784
+ },
785
+ {
786
+ "Step": 79,
787
+ "Metric": "SFT Loss",
788
+ "Value": 4.832979202270508
789
+ },
790
+ {
791
+ "Step": 79,
792
+ "Metric": "Learning Rate",
793
+ "Value": 1.8711111111111113e-05
794
+ },
795
+ {
796
+ "Step": 80,
797
+ "Metric": "SFT Loss",
798
+ "Value": 4.471445560455322
799
+ },
800
+ {
801
+ "Step": 80,
802
+ "Metric": "Learning Rate",
803
+ "Value": 1.866666666666667e-05
804
+ },
805
+ {
806
+ "Step": 81,
807
+ "Metric": "SFT Loss",
808
+ "Value": 5.19096040725708
809
+ },
810
+ {
811
+ "Step": 81,
812
+ "Metric": "Learning Rate",
813
+ "Value": 1.8622222222222224e-05
814
+ },
815
+ {
816
+ "Step": 82,
817
+ "Metric": "SFT Loss",
818
+ "Value": 4.298245906829834
819
+ },
820
+ {
821
+ "Step": 82,
822
+ "Metric": "Learning Rate",
823
+ "Value": 1.857777777777778e-05
824
+ },
825
+ {
826
+ "Step": 83,
827
+ "Metric": "SFT Loss",
828
+ "Value": 5.057285785675049
829
+ },
830
+ {
831
+ "Step": 83,
832
+ "Metric": "Learning Rate",
833
+ "Value": 1.8533333333333334e-05
834
+ },
835
+ {
836
+ "Step": 84,
837
+ "Metric": "SFT Loss",
838
+ "Value": 4.01115083694458
839
+ },
840
+ {
841
+ "Step": 84,
842
+ "Metric": "Learning Rate",
843
+ "Value": 1.848888888888889e-05
844
+ },
845
+ {
846
+ "Step": 85,
847
+ "Metric": "SFT Loss",
848
+ "Value": 4.00934362411499
849
+ },
850
+ {
851
+ "Step": 85,
852
+ "Metric": "Learning Rate",
853
+ "Value": 1.8444444444444448e-05
854
+ },
855
+ {
856
+ "Step": 86,
857
+ "Metric": "SFT Loss",
858
+ "Value": 4.560959339141846
859
+ },
860
+ {
861
+ "Step": 86,
862
+ "Metric": "Learning Rate",
863
+ "Value": 1.8400000000000003e-05
864
+ },
865
+ {
866
+ "Step": 87,
867
+ "Metric": "SFT Loss",
868
+ "Value": 3.884817361831665
869
+ },
870
+ {
871
+ "Step": 87,
872
+ "Metric": "Learning Rate",
873
+ "Value": 1.835555555555556e-05
874
+ },
875
+ {
876
+ "Step": 88,
877
+ "Metric": "SFT Loss",
878
+ "Value": 4.446163177490234
879
+ },
880
+ {
881
+ "Step": 88,
882
+ "Metric": "Learning Rate",
883
+ "Value": 1.8311111111111114e-05
884
+ },
885
+ {
886
+ "Step": 89,
887
+ "Metric": "SFT Loss",
888
+ "Value": 4.543856143951416
889
+ },
890
+ {
891
+ "Step": 89,
892
+ "Metric": "Learning Rate",
893
+ "Value": 1.826666666666667e-05
894
+ },
895
+ {
896
+ "Step": 90,
897
+ "Metric": "SFT Loss",
898
+ "Value": 4.007848262786865
899
+ },
900
+ {
901
+ "Step": 90,
902
+ "Metric": "Learning Rate",
903
+ "Value": 1.8222222222222224e-05
904
+ },
905
+ {
906
+ "Step": 91,
907
+ "Metric": "SFT Loss",
908
+ "Value": 4.391502857208252
909
+ },
910
+ {
911
+ "Step": 91,
912
+ "Metric": "Learning Rate",
913
+ "Value": 1.817777777777778e-05
914
+ },
915
+ {
916
+ "Step": 92,
917
+ "Metric": "SFT Loss",
918
+ "Value": 4.319259166717529
919
+ },
920
+ {
921
+ "Step": 92,
922
+ "Metric": "Learning Rate",
923
+ "Value": 1.8133333333333335e-05
924
+ },
925
+ {
926
+ "Step": 93,
927
+ "Metric": "SFT Loss",
928
+ "Value": 4.551959991455078
929
+ },
930
+ {
931
+ "Step": 93,
932
+ "Metric": "Learning Rate",
933
+ "Value": 1.808888888888889e-05
934
+ },
935
+ {
936
+ "Step": 94,
937
+ "Metric": "SFT Loss",
938
+ "Value": 4.233450412750244
939
+ },
940
+ {
941
+ "Step": 94,
942
+ "Metric": "Learning Rate",
943
+ "Value": 1.8044444444444445e-05
944
+ },
945
+ {
946
+ "Step": 95,
947
+ "Metric": "SFT Loss",
948
+ "Value": 4.298363208770752
949
+ },
950
+ {
951
+ "Step": 95,
952
+ "Metric": "Learning Rate",
953
+ "Value": 1.8e-05
954
+ },
955
+ {
956
+ "Step": 96,
957
+ "Metric": "SFT Loss",
958
+ "Value": 4.241702079772949
959
+ },
960
+ {
961
+ "Step": 96,
962
+ "Metric": "Learning Rate",
963
+ "Value": 1.7955555555555556e-05
964
+ },
965
+ {
966
+ "Step": 97,
967
+ "Metric": "SFT Loss",
968
+ "Value": 3.702441692352295
969
+ },
970
+ {
971
+ "Step": 97,
972
+ "Metric": "Learning Rate",
973
+ "Value": 1.791111111111111e-05
974
+ },
975
+ {
976
+ "Step": 98,
977
+ "Metric": "SFT Loss",
978
+ "Value": 4.456193923950195
979
+ },
980
+ {
981
+ "Step": 98,
982
+ "Metric": "Learning Rate",
983
+ "Value": 1.7866666666666666e-05
984
+ },
985
+ {
986
+ "Step": 99,
987
+ "Metric": "SFT Loss",
988
+ "Value": 3.991964817047119
989
+ },
990
+ {
991
+ "Step": 99,
992
+ "Metric": "Learning Rate",
993
+ "Value": 1.782222222222222e-05
994
+ },
995
+ {
996
+ "Step": 100,
997
+ "Metric": "SFT Loss",
998
+ "Value": 3.4140963554382324
999
+ },
1000
+ {
1001
+ "Step": 100,
1002
+ "Metric": "Learning Rate",
1003
+ "Value": 1.7777777777777777e-05
1004
+ },
1005
+ {
1006
+ "Step": 101,
1007
+ "Metric": "SFT Loss",
1008
+ "Value": 4.197049140930176
1009
+ },
1010
+ {
1011
+ "Step": 101,
1012
+ "Metric": "Learning Rate",
1013
+ "Value": 1.7733333333333335e-05
1014
+ },
1015
+ {
1016
+ "Step": 102,
1017
+ "Metric": "SFT Loss",
1018
+ "Value": 4.2692036628723145
1019
+ },
1020
+ {
1021
+ "Step": 102,
1022
+ "Metric": "Learning Rate",
1023
+ "Value": 1.768888888888889e-05
1024
+ },
1025
+ {
1026
+ "Step": 103,
1027
+ "Metric": "SFT Loss",
1028
+ "Value": 3.8439722061157227
1029
+ },
1030
+ {
1031
+ "Step": 103,
1032
+ "Metric": "Learning Rate",
1033
+ "Value": 1.7644444444444446e-05
1034
+ },
1035
+ {
1036
+ "Step": 104,
1037
+ "Metric": "SFT Loss",
1038
+ "Value": 3.943871021270752
1039
+ },
1040
+ {
1041
+ "Step": 104,
1042
+ "Metric": "Learning Rate",
1043
+ "Value": 1.76e-05
1044
+ },
1045
+ {
1046
+ "Step": 105,
1047
+ "Metric": "SFT Loss",
1048
+ "Value": 4.58375358581543
1049
+ },
1050
+ {
1051
+ "Step": 105,
1052
+ "Metric": "Learning Rate",
1053
+ "Value": 1.7555555555555556e-05
1054
+ },
1055
+ {
1056
+ "Step": 106,
1057
+ "Metric": "SFT Loss",
1058
+ "Value": 3.6572935581207275
1059
+ },
1060
+ {
1061
+ "Step": 106,
1062
+ "Metric": "Learning Rate",
1063
+ "Value": 1.751111111111111e-05
1064
+ },
1065
+ {
1066
+ "Step": 107,
1067
+ "Metric": "SFT Loss",
1068
+ "Value": 3.9028666019439697
1069
+ },
1070
+ {
1071
+ "Step": 107,
1072
+ "Metric": "Learning Rate",
1073
+ "Value": 1.7466666666666667e-05
1074
+ },
1075
+ {
1076
+ "Step": 108,
1077
+ "Metric": "SFT Loss",
1078
+ "Value": 4.1736321449279785
1079
+ },
1080
+ {
1081
+ "Step": 108,
1082
+ "Metric": "Learning Rate",
1083
+ "Value": 1.7422222222222222e-05
1084
+ },
1085
+ {
1086
+ "Step": 109,
1087
+ "Metric": "SFT Loss",
1088
+ "Value": 3.8696651458740234
1089
+ },
1090
+ {
1091
+ "Step": 109,
1092
+ "Metric": "Learning Rate",
1093
+ "Value": 1.737777777777778e-05
1094
+ },
1095
+ {
1096
+ "Step": 110,
1097
+ "Metric": "SFT Loss",
1098
+ "Value": 3.711902618408203
1099
+ },
1100
+ {
1101
+ "Step": 110,
1102
+ "Metric": "Learning Rate",
1103
+ "Value": 1.7333333333333336e-05
1104
+ },
1105
+ {
1106
+ "Step": 111,
1107
+ "Metric": "SFT Loss",
1108
+ "Value": 3.8743908405303955
1109
+ },
1110
+ {
1111
+ "Step": 111,
1112
+ "Metric": "Learning Rate",
1113
+ "Value": 1.728888888888889e-05
1114
+ },
1115
+ {
1116
+ "Step": 112,
1117
+ "Metric": "SFT Loss",
1118
+ "Value": 4.811700344085693
1119
+ },
1120
+ {
1121
+ "Step": 112,
1122
+ "Metric": "Learning Rate",
1123
+ "Value": 1.7244444444444446e-05
1124
+ },
1125
+ {
1126
+ "Step": 113,
1127
+ "Metric": "SFT Loss",
1128
+ "Value": 3.9556643962860107
1129
+ },
1130
+ {
1131
+ "Step": 113,
1132
+ "Metric": "Learning Rate",
1133
+ "Value": 1.72e-05
1134
+ },
1135
+ {
1136
+ "Step": 114,
1137
+ "Metric": "SFT Loss",
1138
+ "Value": 3.762240409851074
1139
+ },
1140
+ {
1141
+ "Step": 114,
1142
+ "Metric": "Learning Rate",
1143
+ "Value": 1.7155555555555557e-05
1144
+ },
1145
+ {
1146
+ "Step": 115,
1147
+ "Metric": "SFT Loss",
1148
+ "Value": 3.8440146446228027
1149
+ },
1150
+ {
1151
+ "Step": 115,
1152
+ "Metric": "Learning Rate",
1153
+ "Value": 1.7111111111111112e-05
1154
+ },
1155
+ {
1156
+ "Step": 116,
1157
+ "Metric": "SFT Loss",
1158
+ "Value": 3.7602431774139404
1159
+ },
1160
+ {
1161
+ "Step": 116,
1162
+ "Metric": "Learning Rate",
1163
+ "Value": 1.706666666666667e-05
1164
+ },
1165
+ {
1166
+ "Step": 117,
1167
+ "Metric": "SFT Loss",
1168
+ "Value": 3.3839704990386963
1169
+ },
1170
+ {
1171
+ "Step": 117,
1172
+ "Metric": "Learning Rate",
1173
+ "Value": 1.7022222222222226e-05
1174
+ },
1175
+ {
1176
+ "Step": 118,
1177
+ "Metric": "SFT Loss",
1178
+ "Value": 4.222746849060059
1179
+ },
1180
+ {
1181
+ "Step": 118,
1182
+ "Metric": "Learning Rate",
1183
+ "Value": 1.697777777777778e-05
1184
+ },
1185
+ {
1186
+ "Step": 119,
1187
+ "Metric": "SFT Loss",
1188
+ "Value": 4.096693515777588
1189
+ },
1190
+ {
1191
+ "Step": 119,
1192
+ "Metric": "Learning Rate",
1193
+ "Value": 1.6933333333333336e-05
1194
+ },
1195
+ {
1196
+ "Step": 120,
1197
+ "Metric": "SFT Loss",
1198
+ "Value": 3.2182490825653076
1199
+ },
1200
+ {
1201
+ "Step": 120,
1202
+ "Metric": "Learning Rate",
1203
+ "Value": 1.688888888888889e-05
1204
+ },
1205
+ {
1206
+ "Step": 121,
1207
+ "Metric": "SFT Loss",
1208
+ "Value": 4.5842437744140625
1209
+ },
1210
+ {
1211
+ "Step": 121,
1212
+ "Metric": "Learning Rate",
1213
+ "Value": 1.6844444444444447e-05
1214
+ },
1215
+ {
1216
+ "Step": 122,
1217
+ "Metric": "SFT Loss",
1218
+ "Value": 3.760061264038086
1219
+ },
1220
+ {
1221
+ "Step": 122,
1222
+ "Metric": "Learning Rate",
1223
+ "Value": 1.6800000000000002e-05
1224
+ },
1225
+ {
1226
+ "Step": 123,
1227
+ "Metric": "SFT Loss",
1228
+ "Value": 4.013190746307373
1229
+ },
1230
+ {
1231
+ "Step": 123,
1232
+ "Metric": "Learning Rate",
1233
+ "Value": 1.6755555555555557e-05
1234
+ },
1235
+ {
1236
+ "Step": 124,
1237
+ "Metric": "SFT Loss",
1238
+ "Value": 3.986571788787842
1239
+ },
1240
+ {
1241
+ "Step": 124,
1242
+ "Metric": "Learning Rate",
1243
+ "Value": 1.6711111111111112e-05
1244
+ },
1245
+ {
1246
+ "Step": 125,
1247
+ "Metric": "SFT Loss",
1248
+ "Value": 3.589707612991333
1249
+ },
1250
+ {
1251
+ "Step": 125,
1252
+ "Metric": "Learning Rate",
1253
+ "Value": 1.6666666666666667e-05
1254
+ },
1255
+ {
1256
+ "Step": 126,
1257
+ "Metric": "SFT Loss",
1258
+ "Value": 3.719574213027954
1259
+ },
1260
+ {
1261
+ "Step": 126,
1262
+ "Metric": "Learning Rate",
1263
+ "Value": 1.6622222222222223e-05
1264
+ },
1265
+ {
1266
+ "Step": 127,
1267
+ "Metric": "SFT Loss",
1268
+ "Value": 3.9422574043273926
1269
+ },
1270
+ {
1271
+ "Step": 127,
1272
+ "Metric": "Learning Rate",
1273
+ "Value": 1.6577777777777778e-05
1274
+ },
1275
+ {
1276
+ "Step": 128,
1277
+ "Metric": "SFT Loss",
1278
+ "Value": 3.654411792755127
1279
+ },
1280
+ {
1281
+ "Step": 128,
1282
+ "Metric": "Learning Rate",
1283
+ "Value": 1.6533333333333333e-05
1284
+ },
1285
+ {
1286
+ "Step": 129,
1287
+ "Metric": "SFT Loss",
1288
+ "Value": 3.6934542655944824
1289
+ },
1290
+ {
1291
+ "Step": 129,
1292
+ "Metric": "Learning Rate",
1293
+ "Value": 1.648888888888889e-05
1294
+ },
1295
+ {
1296
+ "Step": 130,
1297
+ "Metric": "SFT Loss",
1298
+ "Value": 3.9743876457214355
1299
+ },
1300
+ {
1301
+ "Step": 130,
1302
+ "Metric": "Learning Rate",
1303
+ "Value": 1.6444444444444444e-05
1304
+ },
1305
+ {
1306
+ "Step": 131,
1307
+ "Metric": "SFT Loss",
1308
+ "Value": 3.4909720420837402
1309
+ },
1310
+ {
1311
+ "Step": 131,
1312
+ "Metric": "Learning Rate",
1313
+ "Value": 1.64e-05
1314
+ },
1315
+ {
1316
+ "Step": 132,
1317
+ "Metric": "SFT Loss",
1318
+ "Value": 4.221559524536133
1319
+ },
1320
+ {
1321
+ "Step": 132,
1322
+ "Metric": "Learning Rate",
1323
+ "Value": 1.6355555555555557e-05
1324
+ },
1325
+ {
1326
+ "Step": 133,
1327
+ "Metric": "SFT Loss",
1328
+ "Value": 3.9914636611938477
1329
+ },
1330
+ {
1331
+ "Step": 133,
1332
+ "Metric": "Learning Rate",
1333
+ "Value": 1.6311111111111113e-05
1334
+ },
1335
+ {
1336
+ "Step": 134,
1337
+ "Metric": "SFT Loss",
1338
+ "Value": 3.7926385402679443
1339
+ },
1340
+ {
1341
+ "Step": 134,
1342
+ "Metric": "Learning Rate",
1343
+ "Value": 1.6266666666666668e-05
1344
+ },
1345
+ {
1346
+ "Step": 135,
1347
+ "Metric": "SFT Loss",
1348
+ "Value": 4.259970664978027
1349
+ },
1350
+ {
1351
+ "Step": 135,
1352
+ "Metric": "Learning Rate",
1353
+ "Value": 1.6222222222222223e-05
1354
+ },
1355
+ {
1356
+ "Step": 136,
1357
+ "Metric": "SFT Loss",
1358
+ "Value": 3.239041566848755
1359
+ },
1360
+ {
1361
+ "Step": 136,
1362
+ "Metric": "Learning Rate",
1363
+ "Value": 1.617777777777778e-05
1364
+ },
1365
+ {
1366
+ "Step": 137,
1367
+ "Metric": "SFT Loss",
1368
+ "Value": 3.918592691421509
1369
+ },
1370
+ {
1371
+ "Step": 137,
1372
+ "Metric": "Learning Rate",
1373
+ "Value": 1.6133333333333334e-05
1374
+ },
1375
+ {
1376
+ "Step": 138,
1377
+ "Metric": "SFT Loss",
1378
+ "Value": 4.1163763999938965
1379
+ },
1380
+ {
1381
+ "Step": 138,
1382
+ "Metric": "Learning Rate",
1383
+ "Value": 1.608888888888889e-05
1384
+ },
1385
+ {
1386
+ "Step": 139,
1387
+ "Metric": "SFT Loss",
1388
+ "Value": 3.4058291912078857
1389
+ },
1390
+ {
1391
+ "Step": 139,
1392
+ "Metric": "Learning Rate",
1393
+ "Value": 1.6044444444444444e-05
1394
+ },
1395
+ {
1396
+ "Step": 140,
1397
+ "Metric": "SFT Loss",
1398
+ "Value": 4.034569263458252
1399
+ },
1400
+ {
1401
+ "Step": 140,
1402
+ "Metric": "Learning Rate",
1403
+ "Value": 1.6000000000000003e-05
1404
+ },
1405
+ {
1406
+ "Step": 141,
1407
+ "Metric": "SFT Loss",
1408
+ "Value": 3.184511423110962
1409
+ },
1410
+ {
1411
+ "Step": 141,
1412
+ "Metric": "Learning Rate",
1413
+ "Value": 1.5955555555555558e-05
1414
+ },
1415
+ {
1416
+ "Step": 142,
1417
+ "Metric": "SFT Loss",
1418
+ "Value": 3.4227848052978516
1419
+ },
1420
+ {
1421
+ "Step": 142,
1422
+ "Metric": "Learning Rate",
1423
+ "Value": 1.5911111111111113e-05
1424
+ },
1425
+ {
1426
+ "Step": 143,
1427
+ "Metric": "SFT Loss",
1428
+ "Value": 3.349888324737549
1429
+ },
1430
+ {
1431
+ "Step": 143,
1432
+ "Metric": "Learning Rate",
1433
+ "Value": 1.586666666666667e-05
1434
+ },
1435
+ {
1436
+ "Step": 144,
1437
+ "Metric": "SFT Loss",
1438
+ "Value": 3.460050106048584
1439
+ },
1440
+ {
1441
+ "Step": 144,
1442
+ "Metric": "Learning Rate",
1443
+ "Value": 1.5822222222222224e-05
1444
+ },
1445
+ {
1446
+ "Step": 145,
1447
+ "Metric": "SFT Loss",
1448
+ "Value": 3.2790229320526123
1449
+ },
1450
+ {
1451
+ "Step": 145,
1452
+ "Metric": "Learning Rate",
1453
+ "Value": 1.577777777777778e-05
1454
+ },
1455
+ {
1456
+ "Step": 146,
1457
+ "Metric": "SFT Loss",
1458
+ "Value": 3.147298812866211
1459
+ },
1460
+ {
1461
+ "Step": 146,
1462
+ "Metric": "Learning Rate",
1463
+ "Value": 1.5733333333333334e-05
1464
+ },
1465
+ {
1466
+ "Step": 147,
1467
+ "Metric": "SFT Loss",
1468
+ "Value": 3.6869940757751465
1469
+ },
1470
+ {
1471
+ "Step": 147,
1472
+ "Metric": "Learning Rate",
1473
+ "Value": 1.5688888888888893e-05
1474
+ },
1475
+ {
1476
+ "Step": 148,
1477
+ "Metric": "SFT Loss",
1478
+ "Value": 3.6504058837890625
1479
+ },
1480
+ {
1481
+ "Step": 148,
1482
+ "Metric": "Learning Rate",
1483
+ "Value": 1.5644444444444448e-05
1484
+ },
1485
+ {
1486
+ "Step": 149,
1487
+ "Metric": "SFT Loss",
1488
+ "Value": 3.1365625858306885
1489
+ },
1490
+ {
1491
+ "Step": 149,
1492
+ "Metric": "Learning Rate",
1493
+ "Value": 1.5600000000000003e-05
1494
+ },
1495
+ {
1496
+ "Step": 150,
1497
+ "Metric": "SFT Loss",
1498
+ "Value": 3.612093448638916
1499
+ },
1500
+ {
1501
+ "Step": 150,
1502
+ "Metric": "Learning Rate",
1503
+ "Value": 1.555555555555556e-05
1504
+ },
1505
+ {
1506
+ "Step": 151,
1507
+ "Metric": "SFT Loss",
1508
+ "Value": 4.2104339599609375
1509
+ },
1510
+ {
1511
+ "Step": 151,
1512
+ "Metric": "Learning Rate",
1513
+ "Value": 1.5511111111111114e-05
1514
+ },
1515
+ {
1516
+ "Step": 152,
1517
+ "Metric": "SFT Loss",
1518
+ "Value": 3.953524351119995
1519
+ },
1520
+ {
1521
+ "Step": 152,
1522
+ "Metric": "Learning Rate",
1523
+ "Value": 1.546666666666667e-05
1524
+ },
1525
+ {
1526
+ "Step": 153,
1527
+ "Metric": "SFT Loss",
1528
+ "Value": 3.4974162578582764
1529
+ },
1530
+ {
1531
+ "Step": 153,
1532
+ "Metric": "Learning Rate",
1533
+ "Value": 1.5422222222222224e-05
1534
+ },
1535
+ {
1536
+ "Step": 154,
1537
+ "Metric": "SFT Loss",
1538
+ "Value": 3.590752124786377
1539
+ },
1540
+ {
1541
+ "Step": 154,
1542
+ "Metric": "Learning Rate",
1543
+ "Value": 1.537777777777778e-05
1544
+ },
1545
+ {
1546
+ "Step": 155,
1547
+ "Metric": "SFT Loss",
1548
+ "Value": 2.9614787101745605
1549
+ },
1550
+ {
1551
+ "Step": 155,
1552
+ "Metric": "Learning Rate",
1553
+ "Value": 1.5333333333333334e-05
1554
+ },
1555
+ {
1556
+ "Step": 156,
1557
+ "Metric": "SFT Loss",
1558
+ "Value": 3.2427453994750977
1559
+ },
1560
+ {
1561
+ "Step": 156,
1562
+ "Metric": "Learning Rate",
1563
+ "Value": 1.528888888888889e-05
1564
+ },
1565
+ {
1566
+ "Step": 157,
1567
+ "Metric": "SFT Loss",
1568
+ "Value": 3.41286563873291
1569
+ },
1570
+ {
1571
+ "Step": 157,
1572
+ "Metric": "Learning Rate",
1573
+ "Value": 1.5244444444444447e-05
1574
+ },
1575
+ {
1576
+ "Step": 158,
1577
+ "Metric": "SFT Loss",
1578
+ "Value": 3.0443198680877686
1579
+ },
1580
+ {
1581
+ "Step": 158,
1582
+ "Metric": "Learning Rate",
1583
+ "Value": 1.5200000000000002e-05
1584
+ },
1585
+ {
1586
+ "Step": 159,
1587
+ "Metric": "SFT Loss",
1588
+ "Value": 3.2566778659820557
1589
+ },
1590
+ {
1591
+ "Step": 159,
1592
+ "Metric": "Learning Rate",
1593
+ "Value": 1.5155555555555557e-05
1594
+ },
1595
+ {
1596
+ "Step": 160,
1597
+ "Metric": "SFT Loss",
1598
+ "Value": 3.367868185043335
1599
+ },
1600
+ {
1601
+ "Step": 160,
1602
+ "Metric": "Learning Rate",
1603
+ "Value": 1.5111111111111112e-05
1604
+ },
1605
+ {
1606
+ "Step": 161,
1607
+ "Metric": "SFT Loss",
1608
+ "Value": 3.5505459308624268
1609
+ },
1610
+ {
1611
+ "Step": 161,
1612
+ "Metric": "Learning Rate",
1613
+ "Value": 1.5066666666666668e-05
1614
+ },
1615
+ {
1616
+ "Step": 162,
1617
+ "Metric": "SFT Loss",
1618
+ "Value": 4.230403900146484
1619
+ },
1620
+ {
1621
+ "Step": 162,
1622
+ "Metric": "Learning Rate",
1623
+ "Value": 1.5022222222222223e-05
1624
+ },
1625
+ {
1626
+ "Step": 163,
1627
+ "Metric": "SFT Loss",
1628
+ "Value": 4.130524635314941
1629
+ },
1630
+ {
1631
+ "Step": 163,
1632
+ "Metric": "Learning Rate",
1633
+ "Value": 1.497777777777778e-05
1634
+ },
1635
+ {
1636
+ "Step": 164,
1637
+ "Metric": "SFT Loss",
1638
+ "Value": 3.2612688541412354
1639
+ },
1640
+ {
1641
+ "Step": 164,
1642
+ "Metric": "Learning Rate",
1643
+ "Value": 1.4933333333333335e-05
1644
+ },
1645
+ {
1646
+ "Step": 165,
1647
+ "Metric": "SFT Loss",
1648
+ "Value": 3.913285732269287
1649
+ },
1650
+ {
1651
+ "Step": 165,
1652
+ "Metric": "Learning Rate",
1653
+ "Value": 1.488888888888889e-05
1654
+ },
1655
+ {
1656
+ "Step": 166,
1657
+ "Metric": "SFT Loss",
1658
+ "Value": 4.044578552246094
1659
+ },
1660
+ {
1661
+ "Step": 166,
1662
+ "Metric": "Learning Rate",
1663
+ "Value": 1.4844444444444445e-05
1664
+ },
1665
+ {
1666
+ "Step": 167,
1667
+ "Metric": "SFT Loss",
1668
+ "Value": 4.185407638549805
1669
+ },
1670
+ {
1671
+ "Step": 167,
1672
+ "Metric": "Learning Rate",
1673
+ "Value": 1.48e-05
1674
+ },
1675
+ {
1676
+ "Step": 168,
1677
+ "Metric": "SFT Loss",
1678
+ "Value": 3.8282434940338135
1679
+ },
1680
+ {
1681
+ "Step": 168,
1682
+ "Metric": "Learning Rate",
1683
+ "Value": 1.4755555555555556e-05
1684
+ },
1685
+ {
1686
+ "Step": 169,
1687
+ "Metric": "SFT Loss",
1688
+ "Value": 3.7051658630371094
1689
+ },
1690
+ {
1691
+ "Step": 169,
1692
+ "Metric": "Learning Rate",
1693
+ "Value": 1.4711111111111111e-05
1694
+ },
1695
+ {
1696
+ "Step": 170,
1697
+ "Metric": "SFT Loss",
1698
+ "Value": 3.223768472671509
1699
+ },
1700
+ {
1701
+ "Step": 170,
1702
+ "Metric": "Learning Rate",
1703
+ "Value": 1.4666666666666666e-05
1704
+ },
1705
+ {
1706
+ "Step": 171,
1707
+ "Metric": "SFT Loss",
1708
+ "Value": 4.020519733428955
1709
+ },
1710
+ {
1711
+ "Step": 171,
1712
+ "Metric": "Learning Rate",
1713
+ "Value": 1.4622222222222225e-05
1714
+ },
1715
+ {
1716
+ "Step": 172,
1717
+ "Metric": "SFT Loss",
1718
+ "Value": 3.2840287685394287
1719
+ },
1720
+ {
1721
+ "Step": 172,
1722
+ "Metric": "Learning Rate",
1723
+ "Value": 1.457777777777778e-05
1724
+ },
1725
+ {
1726
+ "Step": 173,
1727
+ "Metric": "SFT Loss",
1728
+ "Value": 3.23078989982605
1729
+ },
1730
+ {
1731
+ "Step": 173,
1732
+ "Metric": "Learning Rate",
1733
+ "Value": 1.4533333333333335e-05
1734
+ },
1735
+ {
1736
+ "Step": 174,
1737
+ "Metric": "SFT Loss",
1738
+ "Value": 3.515049695968628
1739
+ },
1740
+ {
1741
+ "Step": 174,
1742
+ "Metric": "Learning Rate",
1743
+ "Value": 1.448888888888889e-05
1744
+ },
1745
+ {
1746
+ "Step": 175,
1747
+ "Metric": "SFT Loss",
1748
+ "Value": 3.5082690715789795
1749
+ },
1750
+ {
1751
+ "Step": 175,
1752
+ "Metric": "Learning Rate",
1753
+ "Value": 1.4444444444444446e-05
1754
+ },
1755
+ {
1756
+ "Step": 176,
1757
+ "Metric": "SFT Loss",
1758
+ "Value": 3.4804611206054688
1759
+ },
1760
+ {
1761
+ "Step": 176,
1762
+ "Metric": "Learning Rate",
1763
+ "Value": 1.4400000000000001e-05
1764
+ },
1765
+ {
1766
+ "Step": 177,
1767
+ "Metric": "SFT Loss",
1768
+ "Value": 3.502457857131958
1769
+ },
1770
+ {
1771
+ "Step": 177,
1772
+ "Metric": "Learning Rate",
1773
+ "Value": 1.4355555555555556e-05
1774
+ },
1775
+ {
1776
+ "Step": 178,
1777
+ "Metric": "SFT Loss",
1778
+ "Value": 3.583531379699707
1779
+ },
1780
+ {
1781
+ "Step": 178,
1782
+ "Metric": "Learning Rate",
1783
+ "Value": 1.4311111111111111e-05
1784
+ },
1785
+ {
1786
+ "Step": 179,
1787
+ "Metric": "SFT Loss",
1788
+ "Value": 3.4451260566711426
1789
+ },
1790
+ {
1791
+ "Step": 179,
1792
+ "Metric": "Learning Rate",
1793
+ "Value": 1.4266666666666668e-05
1794
+ },
1795
+ {
1796
+ "Step": 180,
1797
+ "Metric": "SFT Loss",
1798
+ "Value": 3.865382194519043
1799
+ },
1800
+ {
1801
+ "Step": 180,
1802
+ "Metric": "Learning Rate",
1803
+ "Value": 1.4222222222222224e-05
1804
+ },
1805
+ {
1806
+ "Step": 181,
1807
+ "Metric": "SFT Loss",
1808
+ "Value": 4.022767066955566
1809
+ },
1810
+ {
1811
+ "Step": 181,
1812
+ "Metric": "Learning Rate",
1813
+ "Value": 1.4177777777777779e-05
1814
+ },
1815
+ {
1816
+ "Step": 182,
1817
+ "Metric": "SFT Loss",
1818
+ "Value": 4.022114276885986
1819
+ },
1820
+ {
1821
+ "Step": 182,
1822
+ "Metric": "Learning Rate",
1823
+ "Value": 1.4133333333333334e-05
1824
+ },
1825
+ {
1826
+ "Step": 183,
1827
+ "Metric": "SFT Loss",
1828
+ "Value": 3.987689733505249
1829
+ },
1830
+ {
1831
+ "Step": 183,
1832
+ "Metric": "Learning Rate",
1833
+ "Value": 1.408888888888889e-05
1834
+ },
1835
+ {
1836
+ "Step": 184,
1837
+ "Metric": "SFT Loss",
1838
+ "Value": 2.855768918991089
1839
+ },
1840
+ {
1841
+ "Step": 184,
1842
+ "Metric": "Learning Rate",
1843
+ "Value": 1.4044444444444445e-05
1844
+ },
1845
+ {
1846
+ "Step": 185,
1847
+ "Metric": "SFT Loss",
1848
+ "Value": 3.7897403240203857
1849
+ },
1850
+ {
1851
+ "Step": 185,
1852
+ "Metric": "Learning Rate",
1853
+ "Value": 1.4e-05
1854
+ },
1855
+ {
1856
+ "Step": 186,
1857
+ "Metric": "SFT Loss",
1858
+ "Value": 2.9922335147857666
1859
+ },
1860
+ {
1861
+ "Step": 186,
1862
+ "Metric": "Learning Rate",
1863
+ "Value": 1.3955555555555558e-05
1864
+ },
1865
+ {
1866
+ "Step": 187,
1867
+ "Metric": "SFT Loss",
1868
+ "Value": 3.2567999362945557
1869
+ },
1870
+ {
1871
+ "Step": 187,
1872
+ "Metric": "Learning Rate",
1873
+ "Value": 1.3911111111111114e-05
1874
+ },
1875
+ {
1876
+ "Step": 188,
1877
+ "Metric": "SFT Loss",
1878
+ "Value": 3.975322961807251
1879
+ },
1880
+ {
1881
+ "Step": 188,
1882
+ "Metric": "Learning Rate",
1883
+ "Value": 1.3866666666666669e-05
1884
+ },
1885
+ {
1886
+ "Step": 189,
1887
+ "Metric": "SFT Loss",
1888
+ "Value": 3.8024675846099854
1889
+ },
1890
+ {
1891
+ "Step": 189,
1892
+ "Metric": "Learning Rate",
1893
+ "Value": 1.3822222222222224e-05
1894
+ },
1895
+ {
1896
+ "Step": 190,
1897
+ "Metric": "SFT Loss",
1898
+ "Value": 2.8855857849121094
1899
+ },
1900
+ {
1901
+ "Step": 190,
1902
+ "Metric": "Learning Rate",
1903
+ "Value": 1.377777777777778e-05
1904
+ },
1905
+ {
1906
+ "Step": 191,
1907
+ "Metric": "SFT Loss",
1908
+ "Value": 3.6997151374816895
1909
+ },
1910
+ {
1911
+ "Step": 191,
1912
+ "Metric": "Learning Rate",
1913
+ "Value": 1.3733333333333335e-05
1914
+ },
1915
+ {
1916
+ "Step": 192,
1917
+ "Metric": "SFT Loss",
1918
+ "Value": 3.1630804538726807
1919
+ },
1920
+ {
1921
+ "Step": 192,
1922
+ "Metric": "Learning Rate",
1923
+ "Value": 1.368888888888889e-05
1924
+ },
1925
+ {
1926
+ "Step": 193,
1927
+ "Metric": "SFT Loss",
1928
+ "Value": 3.7628540992736816
1929
+ },
1930
+ {
1931
+ "Step": 193,
1932
+ "Metric": "Learning Rate",
1933
+ "Value": 1.3644444444444445e-05
1934
+ },
1935
+ {
1936
+ "Step": 194,
1937
+ "Metric": "SFT Loss",
1938
+ "Value": 3.4926719665527344
1939
+ },
1940
+ {
1941
+ "Step": 194,
1942
+ "Metric": "Learning Rate",
1943
+ "Value": 1.3600000000000002e-05
1944
+ },
1945
+ {
1946
+ "Step": 195,
1947
+ "Metric": "SFT Loss",
1948
+ "Value": 3.5524115562438965
1949
+ },
1950
+ {
1951
+ "Step": 195,
1952
+ "Metric": "Learning Rate",
1953
+ "Value": 1.3555555555555557e-05
1954
+ },
1955
+ {
1956
+ "Step": 196,
1957
+ "Metric": "SFT Loss",
1958
+ "Value": 3.453152656555176
1959
+ },
1960
+ {
1961
+ "Step": 196,
1962
+ "Metric": "Learning Rate",
1963
+ "Value": 1.3511111111111112e-05
1964
+ },
1965
+ {
1966
+ "Step": 197,
1967
+ "Metric": "SFT Loss",
1968
+ "Value": 3.4464523792266846
1969
+ },
1970
+ {
1971
+ "Step": 197,
1972
+ "Metric": "Learning Rate",
1973
+ "Value": 1.3466666666666668e-05
1974
+ },
1975
+ {
1976
+ "Step": 198,
1977
+ "Metric": "SFT Loss",
1978
+ "Value": 3.3335554599761963
1979
+ },
1980
+ {
1981
+ "Step": 198,
1982
+ "Metric": "Learning Rate",
1983
+ "Value": 1.3422222222222223e-05
1984
+ },
1985
+ {
1986
+ "Step": 199,
1987
+ "Metric": "SFT Loss",
1988
+ "Value": 3.9463119506835938
1989
+ },
1990
+ {
1991
+ "Step": 199,
1992
+ "Metric": "Learning Rate",
1993
+ "Value": 1.3377777777777778e-05
1994
+ },
1995
+ {
1996
+ "Step": 200,
1997
+ "Metric": "SFT Loss",
1998
+ "Value": 3.413942813873291
1999
+ },
2000
+ {
2001
+ "Step": 200,
2002
+ "Metric": "Learning Rate",
2003
+ "Value": 1.3333333333333333e-05
2004
+ },
2005
+ {
2006
+ "Step": 201,
2007
+ "Metric": "SFT Loss",
2008
+ "Value": 3.0034801959991455
2009
+ },
2010
+ {
2011
+ "Step": 201,
2012
+ "Metric": "Learning Rate",
2013
+ "Value": 1.3288888888888889e-05
2014
+ },
2015
+ {
2016
+ "Step": 202,
2017
+ "Metric": "SFT Loss",
2018
+ "Value": 3.191375255584717
2019
+ },
2020
+ {
2021
+ "Step": 202,
2022
+ "Metric": "Learning Rate",
2023
+ "Value": 1.3244444444444447e-05
2024
+ },
2025
+ {
2026
+ "Step": 203,
2027
+ "Metric": "SFT Loss",
2028
+ "Value": 3.245238780975342
2029
+ },
2030
+ {
2031
+ "Step": 203,
2032
+ "Metric": "Learning Rate",
2033
+ "Value": 1.3200000000000002e-05
2034
+ },
2035
+ {
2036
+ "Step": 204,
2037
+ "Metric": "SFT Loss",
2038
+ "Value": 3.7792439460754395
2039
+ },
2040
+ {
2041
+ "Step": 204,
2042
+ "Metric": "Learning Rate",
2043
+ "Value": 1.3155555555555558e-05
2044
+ },
2045
+ {
2046
+ "Step": 205,
2047
+ "Metric": "SFT Loss",
2048
+ "Value": 3.1974034309387207
2049
+ },
2050
+ {
2051
+ "Step": 205,
2052
+ "Metric": "Learning Rate",
2053
+ "Value": 1.3111111111111113e-05
2054
+ },
2055
+ {
2056
+ "Step": 206,
2057
+ "Metric": "SFT Loss",
2058
+ "Value": 4.096724510192871
2059
+ },
2060
+ {
2061
+ "Step": 206,
2062
+ "Metric": "Learning Rate",
2063
+ "Value": 1.3066666666666668e-05
2064
+ },
2065
+ {
2066
+ "Step": 207,
2067
+ "Metric": "SFT Loss",
2068
+ "Value": 3.266791820526123
2069
+ },
2070
+ {
2071
+ "Step": 207,
2072
+ "Metric": "Learning Rate",
2073
+ "Value": 1.3022222222222223e-05
2074
+ },
2075
+ {
2076
+ "Step": 208,
2077
+ "Metric": "SFT Loss",
2078
+ "Value": 3.2096176147460938
2079
+ },
2080
+ {
2081
+ "Step": 208,
2082
+ "Metric": "Learning Rate",
2083
+ "Value": 1.2977777777777779e-05
2084
+ },
2085
+ {
2086
+ "Step": 209,
2087
+ "Metric": "SFT Loss",
2088
+ "Value": 3.0634963512420654
2089
+ },
2090
+ {
2091
+ "Step": 209,
2092
+ "Metric": "Learning Rate",
2093
+ "Value": 1.2933333333333334e-05
2094
+ },
2095
+ {
2096
+ "Step": 210,
2097
+ "Metric": "SFT Loss",
2098
+ "Value": 3.855539560317993
2099
+ },
2100
+ {
2101
+ "Step": 210,
2102
+ "Metric": "Learning Rate",
2103
+ "Value": 1.288888888888889e-05
2104
+ },
2105
+ {
2106
+ "Step": 211,
2107
+ "Metric": "SFT Loss",
2108
+ "Value": 3.5525221824645996
2109
+ },
2110
+ {
2111
+ "Step": 211,
2112
+ "Metric": "Learning Rate",
2113
+ "Value": 1.2844444444444446e-05
2114
+ },
2115
+ {
2116
+ "Step": 212,
2117
+ "Metric": "SFT Loss",
2118
+ "Value": 2.9955544471740723
2119
+ },
2120
+ {
2121
+ "Step": 212,
2122
+ "Metric": "Learning Rate",
2123
+ "Value": 1.2800000000000001e-05
2124
+ },
2125
+ {
2126
+ "Step": 213,
2127
+ "Metric": "SFT Loss",
2128
+ "Value": 3.2758891582489014
2129
+ },
2130
+ {
2131
+ "Step": 213,
2132
+ "Metric": "Learning Rate",
2133
+ "Value": 1.2755555555555556e-05
2134
+ },
2135
+ {
2136
+ "Step": 214,
2137
+ "Metric": "SFT Loss",
2138
+ "Value": 2.935875415802002
2139
+ },
2140
+ {
2141
+ "Step": 214,
2142
+ "Metric": "Learning Rate",
2143
+ "Value": 1.2711111111111112e-05
2144
+ },
2145
+ {
2146
+ "Step": 215,
2147
+ "Metric": "SFT Loss",
2148
+ "Value": 3.478888511657715
2149
+ },
2150
+ {
2151
+ "Step": 215,
2152
+ "Metric": "Learning Rate",
2153
+ "Value": 1.2666666666666667e-05
2154
+ },
2155
+ {
2156
+ "Step": 216,
2157
+ "Metric": "SFT Loss",
2158
+ "Value": 3.7201497554779053
2159
+ },
2160
+ {
2161
+ "Step": 216,
2162
+ "Metric": "Learning Rate",
2163
+ "Value": 1.2622222222222222e-05
2164
+ },
2165
+ {
2166
+ "Step": 217,
2167
+ "Metric": "SFT Loss",
2168
+ "Value": 2.8931407928466797
2169
+ },
2170
+ {
2171
+ "Step": 217,
2172
+ "Metric": "Learning Rate",
2173
+ "Value": 1.257777777777778e-05
2174
+ },
2175
+ {
2176
+ "Step": 218,
2177
+ "Metric": "SFT Loss",
2178
+ "Value": 3.194995403289795
2179
+ },
2180
+ {
2181
+ "Step": 218,
2182
+ "Metric": "Learning Rate",
2183
+ "Value": 1.2533333333333336e-05
2184
+ },
2185
+ {
2186
+ "Step": 219,
2187
+ "Metric": "SFT Loss",
2188
+ "Value": 3.0122687816619873
2189
+ },
2190
+ {
2191
+ "Step": 219,
2192
+ "Metric": "Learning Rate",
2193
+ "Value": 1.2488888888888891e-05
2194
+ },
2195
+ {
2196
+ "Step": 220,
2197
+ "Metric": "SFT Loss",
2198
+ "Value": 3.2899818420410156
2199
+ },
2200
+ {
2201
+ "Step": 220,
2202
+ "Metric": "Learning Rate",
2203
+ "Value": 1.2444444444444446e-05
2204
+ },
2205
+ {
2206
+ "Step": 221,
2207
+ "Metric": "SFT Loss",
2208
+ "Value": 3.661587953567505
2209
+ },
2210
+ {
2211
+ "Step": 221,
2212
+ "Metric": "Learning Rate",
2213
+ "Value": 1.2400000000000002e-05
2214
+ },
2215
+ {
2216
+ "Step": 222,
2217
+ "Metric": "SFT Loss",
2218
+ "Value": 2.7878847122192383
2219
+ },
2220
+ {
2221
+ "Step": 222,
2222
+ "Metric": "Learning Rate",
2223
+ "Value": 1.2355555555555557e-05
2224
+ },
2225
+ {
2226
+ "Step": 223,
2227
+ "Metric": "SFT Loss",
2228
+ "Value": 2.6448488235473633
2229
+ },
2230
+ {
2231
+ "Step": 223,
2232
+ "Metric": "Learning Rate",
2233
+ "Value": 1.2311111111111112e-05
2234
+ },
2235
+ {
2236
+ "Step": 224,
2237
+ "Metric": "SFT Loss",
2238
+ "Value": 2.8379292488098145
2239
+ },
2240
+ {
2241
+ "Step": 224,
2242
+ "Metric": "Learning Rate",
2243
+ "Value": 1.2266666666666667e-05
2244
+ },
2245
+ {
2246
+ "Step": 225,
2247
+ "Metric": "SFT Loss",
2248
+ "Value": 3.395052194595337
2249
+ },
2250
+ {
2251
+ "Step": 225,
2252
+ "Metric": "Learning Rate",
2253
+ "Value": 1.2222222222222224e-05
2254
+ },
2255
+ {
2256
+ "Step": 226,
2257
+ "Metric": "SFT Loss",
2258
+ "Value": 3.166818380355835
2259
+ },
2260
+ {
2261
+ "Step": 226,
2262
+ "Metric": "Learning Rate",
2263
+ "Value": 1.217777777777778e-05
2264
+ },
2265
+ {
2266
+ "Step": 227,
2267
+ "Metric": "SFT Loss",
2268
+ "Value": 2.65335750579834
2269
+ },
2270
+ {
2271
+ "Step": 227,
2272
+ "Metric": "Learning Rate",
2273
+ "Value": 1.2133333333333335e-05
2274
+ },
2275
+ {
2276
+ "Step": 228,
2277
+ "Metric": "SFT Loss",
2278
+ "Value": 3.295043706893921
2279
+ },
2280
+ {
2281
+ "Step": 228,
2282
+ "Metric": "Learning Rate",
2283
+ "Value": 1.208888888888889e-05
2284
+ },
2285
+ {
2286
+ "Step": 229,
2287
+ "Metric": "SFT Loss",
2288
+ "Value": 3.303004741668701
2289
+ },
2290
+ {
2291
+ "Step": 229,
2292
+ "Metric": "Learning Rate",
2293
+ "Value": 1.2044444444444445e-05
2294
+ },
2295
+ {
2296
+ "Step": 230,
2297
+ "Metric": "SFT Loss",
2298
+ "Value": 2.2866604328155518
2299
+ },
2300
+ {
2301
+ "Step": 230,
2302
+ "Metric": "Learning Rate",
2303
+ "Value": 1.2e-05
2304
+ },
2305
+ {
2306
+ "Step": 231,
2307
+ "Metric": "SFT Loss",
2308
+ "Value": 3.2540199756622314
2309
+ },
2310
+ {
2311
+ "Step": 231,
2312
+ "Metric": "Learning Rate",
2313
+ "Value": 1.1955555555555556e-05
2314
+ },
2315
+ {
2316
+ "Step": 232,
2317
+ "Metric": "SFT Loss",
2318
+ "Value": 3.387773036956787
2319
+ },
2320
+ {
2321
+ "Step": 232,
2322
+ "Metric": "Learning Rate",
2323
+ "Value": 1.191111111111111e-05
2324
+ },
2325
+ {
2326
+ "Step": 233,
2327
+ "Metric": "SFT Loss",
2328
+ "Value": 2.32340931892395
2329
+ },
2330
+ {
2331
+ "Step": 233,
2332
+ "Metric": "Learning Rate",
2333
+ "Value": 1.186666666666667e-05
2334
+ },
2335
+ {
2336
+ "Step": 234,
2337
+ "Metric": "SFT Loss",
2338
+ "Value": 2.9949324131011963
2339
+ },
2340
+ {
2341
+ "Step": 234,
2342
+ "Metric": "Learning Rate",
2343
+ "Value": 1.1822222222222225e-05
2344
+ },
2345
+ {
2346
+ "Step": 235,
2347
+ "Metric": "SFT Loss",
2348
+ "Value": 3.218907117843628
2349
+ },
2350
+ {
2351
+ "Step": 235,
2352
+ "Metric": "Learning Rate",
2353
+ "Value": 1.177777777777778e-05
2354
+ },
2355
+ {
2356
+ "Step": 236,
2357
+ "Metric": "SFT Loss",
2358
+ "Value": 2.4533286094665527
2359
+ },
2360
+ {
2361
+ "Step": 236,
2362
+ "Metric": "Learning Rate",
2363
+ "Value": 1.1733333333333335e-05
2364
+ },
2365
+ {
2366
+ "Step": 237,
2367
+ "Metric": "SFT Loss",
2368
+ "Value": 3.1037936210632324
2369
+ },
2370
+ {
2371
+ "Step": 237,
2372
+ "Metric": "Learning Rate",
2373
+ "Value": 1.168888888888889e-05
2374
+ },
2375
+ {
2376
+ "Step": 238,
2377
+ "Metric": "SFT Loss",
2378
+ "Value": 3.326571226119995
2379
+ },
2380
+ {
2381
+ "Step": 238,
2382
+ "Metric": "Learning Rate",
2383
+ "Value": 1.1644444444444446e-05
2384
+ },
2385
+ {
2386
+ "Step": 239,
2387
+ "Metric": "SFT Loss",
2388
+ "Value": 3.1017205715179443
2389
+ },
2390
+ {
2391
+ "Step": 239,
2392
+ "Metric": "Learning Rate",
2393
+ "Value": 1.16e-05
2394
+ },
2395
+ {
2396
+ "Step": 240,
2397
+ "Metric": "SFT Loss",
2398
+ "Value": 3.1740329265594482
2399
+ },
2400
+ {
2401
+ "Step": 240,
2402
+ "Metric": "Learning Rate",
2403
+ "Value": 1.1555555555555556e-05
2404
+ },
2405
+ {
2406
+ "Step": 241,
2407
+ "Metric": "SFT Loss",
2408
+ "Value": 3.321049928665161
2409
+ },
2410
+ {
2411
+ "Step": 241,
2412
+ "Metric": "Learning Rate",
2413
+ "Value": 1.1511111111111113e-05
2414
+ },
2415
+ {
2416
+ "Step": 242,
2417
+ "Metric": "SFT Loss",
2418
+ "Value": 3.5035271644592285
2419
+ },
2420
+ {
2421
+ "Step": 242,
2422
+ "Metric": "Learning Rate",
2423
+ "Value": 1.1466666666666668e-05
2424
+ },
2425
+ {
2426
+ "Step": 243,
2427
+ "Metric": "SFT Loss",
2428
+ "Value": 2.8271918296813965
2429
+ },
2430
+ {
2431
+ "Step": 243,
2432
+ "Metric": "Learning Rate",
2433
+ "Value": 1.1422222222222223e-05
2434
+ },
2435
+ {
2436
+ "Step": 244,
2437
+ "Metric": "SFT Loss",
2438
+ "Value": 2.893418788909912
2439
+ },
2440
+ {
2441
+ "Step": 244,
2442
+ "Metric": "Learning Rate",
2443
+ "Value": 1.1377777777777779e-05
2444
+ },
2445
+ {
2446
+ "Step": 245,
2447
+ "Metric": "SFT Loss",
2448
+ "Value": 3.2262649536132812
2449
+ },
2450
+ {
2451
+ "Step": 245,
2452
+ "Metric": "Learning Rate",
2453
+ "Value": 1.1333333333333334e-05
2454
+ },
2455
+ {
2456
+ "Step": 246,
2457
+ "Metric": "SFT Loss",
2458
+ "Value": 3.0120890140533447
2459
+ },
2460
+ {
2461
+ "Step": 246,
2462
+ "Metric": "Learning Rate",
2463
+ "Value": 1.1288888888888889e-05
2464
+ },
2465
+ {
2466
+ "Step": 247,
2467
+ "Metric": "SFT Loss",
2468
+ "Value": 3.378352165222168
2469
+ },
2470
+ {
2471
+ "Step": 247,
2472
+ "Metric": "Learning Rate",
2473
+ "Value": 1.1244444444444444e-05
2474
+ },
2475
+ {
2476
+ "Step": 248,
2477
+ "Metric": "SFT Loss",
2478
+ "Value": 3.5415189266204834
2479
+ },
2480
+ {
2481
+ "Step": 248,
2482
+ "Metric": "Learning Rate",
2483
+ "Value": 1.1200000000000001e-05
2484
+ },
2485
+ {
2486
+ "Step": 249,
2487
+ "Metric": "SFT Loss",
2488
+ "Value": 3.340938091278076
2489
+ },
2490
+ {
2491
+ "Step": 249,
2492
+ "Metric": "Learning Rate",
2493
+ "Value": 1.1155555555555556e-05
2494
+ },
2495
+ {
2496
+ "Step": 250,
2497
+ "Metric": "SFT Loss",
2498
+ "Value": 3.040834903717041
2499
+ },
2500
+ {
2501
+ "Step": 250,
2502
+ "Metric": "Learning Rate",
2503
+ "Value": 1.1111111111111113e-05
2504
+ },
2505
+ {
2506
+ "Step": 251,
2507
+ "Metric": "SFT Loss",
2508
+ "Value": 3.807276487350464
2509
+ },
2510
+ {
2511
+ "Step": 251,
2512
+ "Metric": "Learning Rate",
2513
+ "Value": 1.1066666666666669e-05
2514
+ },
2515
+ {
2516
+ "Step": 252,
2517
+ "Metric": "SFT Loss",
2518
+ "Value": 2.9890310764312744
2519
+ },
2520
+ {
2521
+ "Step": 252,
2522
+ "Metric": "Learning Rate",
2523
+ "Value": 1.1022222222222224e-05
2524
+ },
2525
+ {
2526
+ "Step": 253,
2527
+ "Metric": "SFT Loss",
2528
+ "Value": 3.0921576023101807
2529
+ },
2530
+ {
2531
+ "Step": 253,
2532
+ "Metric": "Learning Rate",
2533
+ "Value": 1.0977777777777779e-05
2534
+ },
2535
+ {
2536
+ "Step": 254,
2537
+ "Metric": "SFT Loss",
2538
+ "Value": 3.1762592792510986
2539
+ },
2540
+ {
2541
+ "Step": 254,
2542
+ "Metric": "Learning Rate",
2543
+ "Value": 1.0933333333333334e-05
2544
+ },
2545
+ {
2546
+ "Step": 255,
2547
+ "Metric": "SFT Loss",
2548
+ "Value": 3.2332329750061035
2549
+ },
2550
+ {
2551
+ "Step": 255,
2552
+ "Metric": "Learning Rate",
2553
+ "Value": 1.088888888888889e-05
2554
+ },
2555
+ {
2556
+ "Step": 256,
2557
+ "Metric": "SFT Loss",
2558
+ "Value": 3.2774930000305176
2559
+ },
2560
+ {
2561
+ "Step": 256,
2562
+ "Metric": "Learning Rate",
2563
+ "Value": 1.0844444444444446e-05
2564
+ },
2565
+ {
2566
+ "Step": 257,
2567
+ "Metric": "SFT Loss",
2568
+ "Value": 3.8374476432800293
2569
+ },
2570
+ {
2571
+ "Step": 257,
2572
+ "Metric": "Learning Rate",
2573
+ "Value": 1.0800000000000002e-05
2574
+ },
2575
+ {
2576
+ "Step": 258,
2577
+ "Metric": "SFT Loss",
2578
+ "Value": 3.8780386447906494
2579
+ },
2580
+ {
2581
+ "Step": 258,
2582
+ "Metric": "Learning Rate",
2583
+ "Value": 1.0755555555555557e-05
2584
+ },
2585
+ {
2586
+ "Step": 259,
2587
+ "Metric": "SFT Loss",
2588
+ "Value": 2.746340274810791
2589
+ },
2590
+ {
2591
+ "Step": 259,
2592
+ "Metric": "Learning Rate",
2593
+ "Value": 1.0711111111111112e-05
2594
+ },
2595
+ {
2596
+ "Step": 260,
2597
+ "Metric": "SFT Loss",
2598
+ "Value": 3.047837495803833
2599
+ },
2600
+ {
2601
+ "Step": 260,
2602
+ "Metric": "Learning Rate",
2603
+ "Value": 1.0666666666666667e-05
2604
+ },
2605
+ {
2606
+ "Step": 261,
2607
+ "Metric": "SFT Loss",
2608
+ "Value": 3.156785488128662
2609
+ },
2610
+ {
2611
+ "Step": 261,
2612
+ "Metric": "Learning Rate",
2613
+ "Value": 1.0622222222222223e-05
2614
+ },
2615
+ {
2616
+ "Step": 262,
2617
+ "Metric": "SFT Loss",
2618
+ "Value": 3.3767294883728027
2619
+ },
2620
+ {
2621
+ "Step": 262,
2622
+ "Metric": "Learning Rate",
2623
+ "Value": 1.0577777777777778e-05
2624
+ },
2625
+ {
2626
+ "Step": 263,
2627
+ "Metric": "SFT Loss",
2628
+ "Value": 3.2302098274230957
2629
+ },
2630
+ {
2631
+ "Step": 263,
2632
+ "Metric": "Learning Rate",
2633
+ "Value": 1.0533333333333333e-05
2634
+ },
2635
+ {
2636
+ "Step": 264,
2637
+ "Metric": "SFT Loss",
2638
+ "Value": 3.2449042797088623
2639
+ },
2640
+ {
2641
+ "Step": 264,
2642
+ "Metric": "Learning Rate",
2643
+ "Value": 1.048888888888889e-05
2644
+ },
2645
+ {
2646
+ "Step": 265,
2647
+ "Metric": "SFT Loss",
2648
+ "Value": 3.0952882766723633
2649
+ },
2650
+ {
2651
+ "Step": 265,
2652
+ "Metric": "Learning Rate",
2653
+ "Value": 1.0444444444444445e-05
2654
+ },
2655
+ {
2656
+ "Step": 266,
2657
+ "Metric": "SFT Loss",
2658
+ "Value": 3.3554625511169434
2659
+ },
2660
+ {
2661
+ "Step": 266,
2662
+ "Metric": "Learning Rate",
2663
+ "Value": 1.04e-05
2664
+ },
2665
+ {
2666
+ "Step": 267,
2667
+ "Metric": "SFT Loss",
2668
+ "Value": 2.955810308456421
2669
+ },
2670
+ {
2671
+ "Step": 267,
2672
+ "Metric": "Learning Rate",
2673
+ "Value": 1.0355555555555557e-05
2674
+ },
2675
+ {
2676
+ "Step": 268,
2677
+ "Metric": "SFT Loss",
2678
+ "Value": 3.1960465908050537
2679
+ },
2680
+ {
2681
+ "Step": 268,
2682
+ "Metric": "Learning Rate",
2683
+ "Value": 1.0311111111111113e-05
2684
+ },
2685
+ {
2686
+ "Step": 269,
2687
+ "Metric": "SFT Loss",
2688
+ "Value": 2.9257442951202393
2689
+ },
2690
+ {
2691
+ "Step": 269,
2692
+ "Metric": "Learning Rate",
2693
+ "Value": 1.0266666666666668e-05
2694
+ },
2695
+ {
2696
+ "Step": 270,
2697
+ "Metric": "SFT Loss",
2698
+ "Value": 2.616386651992798
2699
+ },
2700
+ {
2701
+ "Step": 270,
2702
+ "Metric": "Learning Rate",
2703
+ "Value": 1.0222222222222223e-05
2704
+ },
2705
+ {
2706
+ "Step": 271,
2707
+ "Metric": "SFT Loss",
2708
+ "Value": 3.0699880123138428
2709
+ },
2710
+ {
2711
+ "Step": 271,
2712
+ "Metric": "Learning Rate",
2713
+ "Value": 1.0177777777777778e-05
2714
+ },
2715
+ {
2716
+ "Step": 272,
2717
+ "Metric": "SFT Loss",
2718
+ "Value": 3.08463716506958
2719
+ },
2720
+ {
2721
+ "Step": 272,
2722
+ "Metric": "Learning Rate",
2723
+ "Value": 1.0133333333333335e-05
2724
+ },
2725
+ {
2726
+ "Step": 273,
2727
+ "Metric": "SFT Loss",
2728
+ "Value": 2.990201473236084
2729
+ },
2730
+ {
2731
+ "Step": 273,
2732
+ "Metric": "Learning Rate",
2733
+ "Value": 1.008888888888889e-05
2734
+ },
2735
+ {
2736
+ "Step": 274,
2737
+ "Metric": "SFT Loss",
2738
+ "Value": 2.6472647190093994
2739
+ },
2740
+ {
2741
+ "Step": 274,
2742
+ "Metric": "Learning Rate",
2743
+ "Value": 1.0044444444444446e-05
2744
+ },
2745
+ {
2746
+ "Step": 275,
2747
+ "Metric": "SFT Loss",
2748
+ "Value": 2.471708059310913
2749
+ },
2750
+ {
2751
+ "Step": 275,
2752
+ "Metric": "Learning Rate",
2753
+ "Value": 1e-05
2754
+ },
2755
+ {
2756
+ "Step": 276,
2757
+ "Metric": "SFT Loss",
2758
+ "Value": 3.031165838241577
2759
+ },
2760
+ {
2761
+ "Step": 276,
2762
+ "Metric": "Learning Rate",
2763
+ "Value": 9.955555555555556e-06
2764
+ },
2765
+ {
2766
+ "Step": 277,
2767
+ "Metric": "SFT Loss",
2768
+ "Value": 3.1698713302612305
2769
+ },
2770
+ {
2771
+ "Step": 277,
2772
+ "Metric": "Learning Rate",
2773
+ "Value": 9.911111111111113e-06
2774
+ },
2775
+ {
2776
+ "Step": 278,
2777
+ "Metric": "SFT Loss",
2778
+ "Value": 3.241370439529419
2779
+ },
2780
+ {
2781
+ "Step": 278,
2782
+ "Metric": "Learning Rate",
2783
+ "Value": 9.866666666666668e-06
2784
+ },
2785
+ {
2786
+ "Step": 279,
2787
+ "Metric": "SFT Loss",
2788
+ "Value": 3.054928779602051
2789
+ },
2790
+ {
2791
+ "Step": 279,
2792
+ "Metric": "Learning Rate",
2793
+ "Value": 9.822222222222223e-06
2794
+ },
2795
+ {
2796
+ "Step": 280,
2797
+ "Metric": "SFT Loss",
2798
+ "Value": 2.959183931350708
2799
+ },
2800
+ {
2801
+ "Step": 280,
2802
+ "Metric": "Learning Rate",
2803
+ "Value": 9.777777777777779e-06
2804
+ },
2805
+ {
2806
+ "Step": 281,
2807
+ "Metric": "SFT Loss",
2808
+ "Value": 3.029250383377075
2809
+ },
2810
+ {
2811
+ "Step": 281,
2812
+ "Metric": "Learning Rate",
2813
+ "Value": 9.733333333333334e-06
2814
+ },
2815
+ {
2816
+ "Step": 282,
2817
+ "Metric": "SFT Loss",
2818
+ "Value": 3.160806655883789
2819
+ },
2820
+ {
2821
+ "Step": 282,
2822
+ "Metric": "Learning Rate",
2823
+ "Value": 9.688888888888889e-06
2824
+ },
2825
+ {
2826
+ "Step": 283,
2827
+ "Metric": "SFT Loss",
2828
+ "Value": 2.948809862136841
2829
+ },
2830
+ {
2831
+ "Step": 283,
2832
+ "Metric": "Learning Rate",
2833
+ "Value": 9.644444444444444e-06
2834
+ },
2835
+ {
2836
+ "Step": 284,
2837
+ "Metric": "SFT Loss",
2838
+ "Value": 3.104466438293457
2839
+ },
2840
+ {
2841
+ "Step": 284,
2842
+ "Metric": "Learning Rate",
2843
+ "Value": 9.600000000000001e-06
2844
+ },
2845
+ {
2846
+ "Step": 285,
2847
+ "Metric": "SFT Loss",
2848
+ "Value": 2.5996103286743164
2849
+ },
2850
+ {
2851
+ "Step": 285,
2852
+ "Metric": "Learning Rate",
2853
+ "Value": 9.555555555555556e-06
2854
+ },
2855
+ {
2856
+ "Step": 286,
2857
+ "Metric": "SFT Loss",
2858
+ "Value": 3.4258909225463867
2859
+ },
2860
+ {
2861
+ "Step": 286,
2862
+ "Metric": "Learning Rate",
2863
+ "Value": 9.511111111111112e-06
2864
+ },
2865
+ {
2866
+ "Step": 287,
2867
+ "Metric": "SFT Loss",
2868
+ "Value": 3.152139902114868
2869
+ },
2870
+ {
2871
+ "Step": 287,
2872
+ "Metric": "Learning Rate",
2873
+ "Value": 9.466666666666667e-06
2874
+ },
2875
+ {
2876
+ "Step": 288,
2877
+ "Metric": "SFT Loss",
2878
+ "Value": 2.747861623764038
2879
+ },
2880
+ {
2881
+ "Step": 288,
2882
+ "Metric": "Learning Rate",
2883
+ "Value": 9.422222222222222e-06
2884
+ },
2885
+ {
2886
+ "Step": 289,
2887
+ "Metric": "SFT Loss",
2888
+ "Value": 3.230604648590088
2889
+ },
2890
+ {
2891
+ "Step": 289,
2892
+ "Metric": "Learning Rate",
2893
+ "Value": 9.377777777777779e-06
2894
+ },
2895
+ {
2896
+ "Step": 290,
2897
+ "Metric": "SFT Loss",
2898
+ "Value": 3.055142641067505
2899
+ },
2900
+ {
2901
+ "Step": 290,
2902
+ "Metric": "Learning Rate",
2903
+ "Value": 9.333333333333334e-06
2904
+ },
2905
+ {
2906
+ "Step": 291,
2907
+ "Metric": "SFT Loss",
2908
+ "Value": 2.650326728820801
2909
+ },
2910
+ {
2911
+ "Step": 291,
2912
+ "Metric": "Learning Rate",
2913
+ "Value": 9.28888888888889e-06
2914
+ },
2915
+ {
2916
+ "Step": 292,
2917
+ "Metric": "SFT Loss",
2918
+ "Value": 2.9059743881225586
2919
+ },
2920
+ {
2921
+ "Step": 292,
2922
+ "Metric": "Learning Rate",
2923
+ "Value": 9.244444444444445e-06
2924
+ },
2925
+ {
2926
+ "Step": 293,
2927
+ "Metric": "SFT Loss",
2928
+ "Value": 2.6497573852539062
2929
+ },
2930
+ {
2931
+ "Step": 293,
2932
+ "Metric": "Learning Rate",
2933
+ "Value": 9.200000000000002e-06
2934
+ },
2935
+ {
2936
+ "Step": 294,
2937
+ "Metric": "SFT Loss",
2938
+ "Value": 3.347966194152832
2939
+ },
2940
+ {
2941
+ "Step": 294,
2942
+ "Metric": "Learning Rate",
2943
+ "Value": 9.155555555555557e-06
2944
+ },
2945
+ {
2946
+ "Step": 295,
2947
+ "Metric": "SFT Loss",
2948
+ "Value": 2.986372947692871
2949
+ },
2950
+ {
2951
+ "Step": 295,
2952
+ "Metric": "Learning Rate",
2953
+ "Value": 9.111111111111112e-06
2954
+ },
2955
+ {
2956
+ "Step": 296,
2957
+ "Metric": "SFT Loss",
2958
+ "Value": 3.5772852897644043
2959
+ },
2960
+ {
2961
+ "Step": 296,
2962
+ "Metric": "Learning Rate",
2963
+ "Value": 9.066666666666667e-06
2964
+ },
2965
+ {
2966
+ "Step": 297,
2967
+ "Metric": "SFT Loss",
2968
+ "Value": 2.457728624343872
2969
+ },
2970
+ {
2971
+ "Step": 297,
2972
+ "Metric": "Learning Rate",
2973
+ "Value": 9.022222222222223e-06
2974
+ },
2975
+ {
2976
+ "Step": 298,
2977
+ "Metric": "SFT Loss",
2978
+ "Value": 2.9353466033935547
2979
+ },
2980
+ {
2981
+ "Step": 298,
2982
+ "Metric": "Learning Rate",
2983
+ "Value": 8.977777777777778e-06
2984
+ },
2985
+ {
2986
+ "Step": 299,
2987
+ "Metric": "SFT Loss",
2988
+ "Value": 3.1257174015045166
2989
+ },
2990
+ {
2991
+ "Step": 299,
2992
+ "Metric": "Learning Rate",
2993
+ "Value": 8.933333333333333e-06
2994
+ },
2995
+ {
2996
+ "Step": 300,
2997
+ "Metric": "SFT Loss",
2998
+ "Value": 2.9193637371063232
2999
+ },
3000
+ {
3001
+ "Step": 300,
3002
+ "Metric": "Learning Rate",
3003
+ "Value": 8.888888888888888e-06
3004
+ }
3005
+ ],
3006
+ "sft_complete": false
3007
+ }
checkpoints/stable-run-sft-step-300/vocab.json ADDED
The diff for this file is too large to render. See raw diff