Spaces:
Build error
Build error
Upload 28 files
Browse files- flutter_codegen_model/checkpoint-1000/added_tokens.json +40 -0
- flutter_codegen_model/checkpoint-1000/config.json +42 -0
- flutter_codegen_model/checkpoint-1000/generation_config.json +6 -0
- flutter_codegen_model/checkpoint-1000/merges.txt +0 -0
- flutter_codegen_model/checkpoint-1000/model.safetensors +3 -0
- flutter_codegen_model/checkpoint-1000/optimizer.pt +3 -0
- flutter_codegen_model/checkpoint-1000/rng_state.pth +3 -0
- flutter_codegen_model/checkpoint-1000/scheduler.pt +3 -0
- flutter_codegen_model/checkpoint-1000/special_tokens_map.json +24 -0
- flutter_codegen_model/checkpoint-1000/tokenizer.json +0 -0
- flutter_codegen_model/checkpoint-1000/tokenizer_config.json +332 -0
- flutter_codegen_model/checkpoint-1000/trainer_state.json +733 -0
- flutter_codegen_model/checkpoint-1000/training_args.bin +3 -0
- flutter_codegen_model/checkpoint-1000/vocab.json +0 -0
- flutter_codegen_model/checkpoint-1500/added_tokens.json +40 -0
- flutter_codegen_model/checkpoint-1500/config.json +42 -0
- flutter_codegen_model/checkpoint-1500/generation_config.json +6 -0
- flutter_codegen_model/checkpoint-1500/merges.txt +0 -0
- flutter_codegen_model/checkpoint-1500/model.safetensors +3 -0
- flutter_codegen_model/checkpoint-1500/optimizer.pt +3 -0
- flutter_codegen_model/checkpoint-1500/rng_state.pth +3 -0
- flutter_codegen_model/checkpoint-1500/scheduler.pt +3 -0
- flutter_codegen_model/checkpoint-1500/special_tokens_map.json +24 -0
- flutter_codegen_model/checkpoint-1500/tokenizer.json +0 -0
- flutter_codegen_model/checkpoint-1500/tokenizer_config.json +332 -0
- flutter_codegen_model/checkpoint-1500/trainer_state.json +1083 -0
- flutter_codegen_model/checkpoint-1500/training_args.bin +3 -0
- flutter_codegen_model/checkpoint-1500/vocab.json +0 -0
flutter_codegen_model/checkpoint-1000/added_tokens.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"\t\t": 50294,
|
| 3 |
+
"\t\t\t": 50293,
|
| 4 |
+
"\t\t\t\t": 50292,
|
| 5 |
+
"\t\t\t\t\t": 50291,
|
| 6 |
+
"\t\t\t\t\t\t": 50290,
|
| 7 |
+
"\t\t\t\t\t\t\t": 50289,
|
| 8 |
+
"\t\t\t\t\t\t\t\t": 50288,
|
| 9 |
+
"\t\t\t\t\t\t\t\t\t": 50287,
|
| 10 |
+
" ": 50286,
|
| 11 |
+
" ": 50285,
|
| 12 |
+
" ": 50284,
|
| 13 |
+
" ": 50283,
|
| 14 |
+
" ": 50282,
|
| 15 |
+
" ": 50281,
|
| 16 |
+
" ": 50280,
|
| 17 |
+
" ": 50279,
|
| 18 |
+
" ": 50278,
|
| 19 |
+
" ": 50277,
|
| 20 |
+
" ": 50276,
|
| 21 |
+
" ": 50275,
|
| 22 |
+
" ": 50274,
|
| 23 |
+
" ": 50273,
|
| 24 |
+
" ": 50272,
|
| 25 |
+
" ": 50271,
|
| 26 |
+
" ": 50270,
|
| 27 |
+
" ": 50269,
|
| 28 |
+
" ": 50268,
|
| 29 |
+
" ": 50267,
|
| 30 |
+
" ": 50266,
|
| 31 |
+
" ": 50265,
|
| 32 |
+
" ": 50264,
|
| 33 |
+
" ": 50263,
|
| 34 |
+
" ": 50262,
|
| 35 |
+
" ": 50261,
|
| 36 |
+
" ": 50260,
|
| 37 |
+
" ": 50259,
|
| 38 |
+
" ": 50258,
|
| 39 |
+
" ": 50257
|
| 40 |
+
}
|
flutter_codegen_model/checkpoint-1000/config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./flutter_codegen_model/checkpoint-500",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"CodeGenForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"embd_pdrop": 0.0,
|
| 10 |
+
"eos_token_id": 50256,
|
| 11 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "codegen",
|
| 15 |
+
"n_ctx": 2048,
|
| 16 |
+
"n_embd": 1024,
|
| 17 |
+
"n_head": 16,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 20,
|
| 20 |
+
"n_positions": 2048,
|
| 21 |
+
"resid_pdrop": 0.0,
|
| 22 |
+
"rotary_dim": 32,
|
| 23 |
+
"scale_attn_weights": true,
|
| 24 |
+
"summary_activation": null,
|
| 25 |
+
"summary_first_dropout": 0.1,
|
| 26 |
+
"summary_proj_to_labels": true,
|
| 27 |
+
"summary_type": "cls_index",
|
| 28 |
+
"summary_use_proj": true,
|
| 29 |
+
"task_specific_params": {
|
| 30 |
+
"text-generation": {
|
| 31 |
+
"do_sample": true,
|
| 32 |
+
"max_length": 50,
|
| 33 |
+
"temperature": 1.0
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"tie_word_embeddings": false,
|
| 37 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 38 |
+
"torch_dtype": "float32",
|
| 39 |
+
"transformers_version": "4.46.3",
|
| 40 |
+
"use_cache": true,
|
| 41 |
+
"vocab_size": 51200
|
| 42 |
+
}
|
flutter_codegen_model/checkpoint-1000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.46.3"
|
| 6 |
+
}
|
flutter_codegen_model/checkpoint-1000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
flutter_codegen_model/checkpoint-1000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d9efdb939975a0509d94514d5c96aa9cd240ba89a1291dfb841be51cfa3820e
|
| 3 |
+
size 1426867192
|
flutter_codegen_model/checkpoint-1000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a808c42810a9dd898f9671ea318574e8916c1b02bb273fad82a0217ca81c4223
|
| 3 |
+
size 2853838010
|
flutter_codegen_model/checkpoint-1000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdf4d700cdd7ef81bf005d2842e2f669e1810471cfce670ab79872c6ee698af7
|
| 3 |
+
size 14244
|
flutter_codegen_model/checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67e662de0fdf218dd168de2e72a056a2eef909476d429619e5d83f10376e401f
|
| 3 |
+
size 1064
|
flutter_codegen_model/checkpoint-1000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|endoftext|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
flutter_codegen_model/checkpoint-1000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
flutter_codegen_model/checkpoint-1000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,332 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"50256": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"50257": {
|
| 13 |
+
"content": " ",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": false
|
| 19 |
+
},
|
| 20 |
+
"50258": {
|
| 21 |
+
"content": " ",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": false
|
| 27 |
+
},
|
| 28 |
+
"50259": {
|
| 29 |
+
"content": " ",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": false
|
| 35 |
+
},
|
| 36 |
+
"50260": {
|
| 37 |
+
"content": " ",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": false
|
| 43 |
+
},
|
| 44 |
+
"50261": {
|
| 45 |
+
"content": " ",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": false
|
| 51 |
+
},
|
| 52 |
+
"50262": {
|
| 53 |
+
"content": " ",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": true,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": false
|
| 59 |
+
},
|
| 60 |
+
"50263": {
|
| 61 |
+
"content": " ",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": true,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": false
|
| 67 |
+
},
|
| 68 |
+
"50264": {
|
| 69 |
+
"content": " ",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": true,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": false
|
| 75 |
+
},
|
| 76 |
+
"50265": {
|
| 77 |
+
"content": " ",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": true,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": false
|
| 83 |
+
},
|
| 84 |
+
"50266": {
|
| 85 |
+
"content": " ",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": true,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": false
|
| 91 |
+
},
|
| 92 |
+
"50267": {
|
| 93 |
+
"content": " ",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": true,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": false
|
| 99 |
+
},
|
| 100 |
+
"50268": {
|
| 101 |
+
"content": " ",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": true,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": false
|
| 107 |
+
},
|
| 108 |
+
"50269": {
|
| 109 |
+
"content": " ",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": true,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": false
|
| 115 |
+
},
|
| 116 |
+
"50270": {
|
| 117 |
+
"content": " ",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": true,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"50271": {
|
| 125 |
+
"content": " ",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": true,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"50272": {
|
| 133 |
+
"content": " ",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": true,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"50273": {
|
| 141 |
+
"content": " ",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": true,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"50274": {
|
| 149 |
+
"content": " ",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": true,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"50275": {
|
| 157 |
+
"content": " ",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": true,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"50276": {
|
| 165 |
+
"content": " ",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": true,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": false
|
| 171 |
+
},
|
| 172 |
+
"50277": {
|
| 173 |
+
"content": " ",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": true,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": false
|
| 179 |
+
},
|
| 180 |
+
"50278": {
|
| 181 |
+
"content": " ",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": true,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": false
|
| 187 |
+
},
|
| 188 |
+
"50279": {
|
| 189 |
+
"content": " ",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": true,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": false
|
| 195 |
+
},
|
| 196 |
+
"50280": {
|
| 197 |
+
"content": " ",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": true,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": false
|
| 203 |
+
},
|
| 204 |
+
"50281": {
|
| 205 |
+
"content": " ",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": true,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": false
|
| 211 |
+
},
|
| 212 |
+
"50282": {
|
| 213 |
+
"content": " ",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": true,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": false
|
| 219 |
+
},
|
| 220 |
+
"50283": {
|
| 221 |
+
"content": " ",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": true,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": false
|
| 227 |
+
},
|
| 228 |
+
"50284": {
|
| 229 |
+
"content": " ",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": true,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": false
|
| 235 |
+
},
|
| 236 |
+
"50285": {
|
| 237 |
+
"content": " ",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": true,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": false
|
| 243 |
+
},
|
| 244 |
+
"50286": {
|
| 245 |
+
"content": " ",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": true,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": false
|
| 251 |
+
},
|
| 252 |
+
"50287": {
|
| 253 |
+
"content": "\t\t\t\t\t\t\t\t\t",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": true,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": false
|
| 259 |
+
},
|
| 260 |
+
"50288": {
|
| 261 |
+
"content": "\t\t\t\t\t\t\t\t",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": true,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": false
|
| 267 |
+
},
|
| 268 |
+
"50289": {
|
| 269 |
+
"content": "\t\t\t\t\t\t\t",
|
| 270 |
+
"lstrip": false,
|
| 271 |
+
"normalized": true,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": false
|
| 275 |
+
},
|
| 276 |
+
"50290": {
|
| 277 |
+
"content": "\t\t\t\t\t\t",
|
| 278 |
+
"lstrip": false,
|
| 279 |
+
"normalized": true,
|
| 280 |
+
"rstrip": false,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": false
|
| 283 |
+
},
|
| 284 |
+
"50291": {
|
| 285 |
+
"content": "\t\t\t\t\t",
|
| 286 |
+
"lstrip": false,
|
| 287 |
+
"normalized": true,
|
| 288 |
+
"rstrip": false,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": false
|
| 291 |
+
},
|
| 292 |
+
"50292": {
|
| 293 |
+
"content": "\t\t\t\t",
|
| 294 |
+
"lstrip": false,
|
| 295 |
+
"normalized": true,
|
| 296 |
+
"rstrip": false,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": false
|
| 299 |
+
},
|
| 300 |
+
"50293": {
|
| 301 |
+
"content": "\t\t\t",
|
| 302 |
+
"lstrip": false,
|
| 303 |
+
"normalized": true,
|
| 304 |
+
"rstrip": false,
|
| 305 |
+
"single_word": false,
|
| 306 |
+
"special": false
|
| 307 |
+
},
|
| 308 |
+
"50294": {
|
| 309 |
+
"content": "\t\t",
|
| 310 |
+
"lstrip": false,
|
| 311 |
+
"normalized": true,
|
| 312 |
+
"rstrip": false,
|
| 313 |
+
"single_word": false,
|
| 314 |
+
"special": false
|
| 315 |
+
}
|
| 316 |
+
},
|
| 317 |
+
"bos_token": "<|endoftext|>",
|
| 318 |
+
"clean_up_tokenization_spaces": false,
|
| 319 |
+
"eos_token": "<|endoftext|>",
|
| 320 |
+
"max_length": 512,
|
| 321 |
+
"model_max_length": 2048,
|
| 322 |
+
"pad_to_multiple_of": null,
|
| 323 |
+
"pad_token": "<|endoftext|>",
|
| 324 |
+
"pad_token_type_id": 0,
|
| 325 |
+
"padding_side": "right",
|
| 326 |
+
"return_token_type_ids": false,
|
| 327 |
+
"stride": 0,
|
| 328 |
+
"tokenizer_class": "CodeGenTokenizer",
|
| 329 |
+
"truncation_side": "right",
|
| 330 |
+
"truncation_strategy": "longest_first",
|
| 331 |
+
"unk_token": "<|endoftext|>"
|
| 332 |
+
}
|
flutter_codegen_model/checkpoint-1000/trainer_state.json
ADDED
|
@@ -0,0 +1,733 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.02620407735443635,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0002620407735443635,
|
| 13 |
+
"grad_norm": 1.2820378541946411,
|
| 14 |
+
"learning_rate": 4.999563265377426e-05,
|
| 15 |
+
"loss": 0.6609,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.000524081547088727,
|
| 20 |
+
"grad_norm": 1.3106062412261963,
|
| 21 |
+
"learning_rate": 4.999126530754852e-05,
|
| 22 |
+
"loss": 0.8066,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0007861223206330905,
|
| 27 |
+
"grad_norm": 1.6985974311828613,
|
| 28 |
+
"learning_rate": 4.9986897961322784e-05,
|
| 29 |
+
"loss": 0.6863,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.001048163094177454,
|
| 34 |
+
"grad_norm": 1.2552741765975952,
|
| 35 |
+
"learning_rate": 4.9982530615097044e-05,
|
| 36 |
+
"loss": 0.5674,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.0013102038677218176,
|
| 41 |
+
"grad_norm": 1.3928155899047852,
|
| 42 |
+
"learning_rate": 4.9978163268871304e-05,
|
| 43 |
+
"loss": 0.5992,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.001572244641266181,
|
| 48 |
+
"grad_norm": 1.5794411897659302,
|
| 49 |
+
"learning_rate": 4.9973795922645565e-05,
|
| 50 |
+
"loss": 0.7939,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.0018342854148105446,
|
| 55 |
+
"grad_norm": 1.4024512767791748,
|
| 56 |
+
"learning_rate": 4.9969428576419825e-05,
|
| 57 |
+
"loss": 0.6178,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.002096326188354908,
|
| 62 |
+
"grad_norm": 1.2232664823532104,
|
| 63 |
+
"learning_rate": 4.9965061230194085e-05,
|
| 64 |
+
"loss": 0.7544,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.0023583669618992714,
|
| 69 |
+
"grad_norm": 1.5368870496749878,
|
| 70 |
+
"learning_rate": 4.9960693883968346e-05,
|
| 71 |
+
"loss": 0.6645,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.002620407735443635,
|
| 76 |
+
"grad_norm": 1.6177372932434082,
|
| 77 |
+
"learning_rate": 4.9956326537742606e-05,
|
| 78 |
+
"loss": 0.6329,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.0028824485089879986,
|
| 83 |
+
"grad_norm": 1.3803173303604126,
|
| 84 |
+
"learning_rate": 4.995195919151687e-05,
|
| 85 |
+
"loss": 0.7114,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.003144489282532362,
|
| 90 |
+
"grad_norm": 1.5191670656204224,
|
| 91 |
+
"learning_rate": 4.9947591845291134e-05,
|
| 92 |
+
"loss": 0.8717,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.0034065300560767254,
|
| 97 |
+
"grad_norm": 1.2967548370361328,
|
| 98 |
+
"learning_rate": 4.994322449906539e-05,
|
| 99 |
+
"loss": 0.7618,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.003668570829621089,
|
| 104 |
+
"grad_norm": 1.8742738962173462,
|
| 105 |
+
"learning_rate": 4.9938857152839655e-05,
|
| 106 |
+
"loss": 0.5896,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.003930611603165452,
|
| 111 |
+
"grad_norm": 1.697966456413269,
|
| 112 |
+
"learning_rate": 4.993448980661391e-05,
|
| 113 |
+
"loss": 0.7493,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.004192652376709816,
|
| 118 |
+
"grad_norm": 1.5282775163650513,
|
| 119 |
+
"learning_rate": 4.9930122460388175e-05,
|
| 120 |
+
"loss": 0.6359,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.00445469315025418,
|
| 125 |
+
"grad_norm": 1.2776225805282593,
|
| 126 |
+
"learning_rate": 4.992575511416243e-05,
|
| 127 |
+
"loss": 0.7677,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.004716733923798543,
|
| 132 |
+
"grad_norm": 1.2036848068237305,
|
| 133 |
+
"learning_rate": 4.9921387767936696e-05,
|
| 134 |
+
"loss": 0.6234,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.0049787746973429066,
|
| 139 |
+
"grad_norm": 1.1325912475585938,
|
| 140 |
+
"learning_rate": 4.991702042171095e-05,
|
| 141 |
+
"loss": 0.624,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.00524081547088727,
|
| 146 |
+
"grad_norm": 1.3846409320831299,
|
| 147 |
+
"learning_rate": 4.991265307548522e-05,
|
| 148 |
+
"loss": 0.5979,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.005502856244431633,
|
| 153 |
+
"grad_norm": 1.9792439937591553,
|
| 154 |
+
"learning_rate": 4.990828572925948e-05,
|
| 155 |
+
"loss": 0.7897,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.005764897017975997,
|
| 160 |
+
"grad_norm": 1.8546253442764282,
|
| 161 |
+
"learning_rate": 4.990391838303374e-05,
|
| 162 |
+
"loss": 0.7035,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.006026937791520361,
|
| 167 |
+
"grad_norm": 1.5434975624084473,
|
| 168 |
+
"learning_rate": 4.9899551036808e-05,
|
| 169 |
+
"loss": 0.7092,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.006288978565064724,
|
| 174 |
+
"grad_norm": 1.0328209400177002,
|
| 175 |
+
"learning_rate": 4.989518369058226e-05,
|
| 176 |
+
"loss": 0.6239,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.006551019338609088,
|
| 181 |
+
"grad_norm": 0.9389006495475769,
|
| 182 |
+
"learning_rate": 4.989081634435652e-05,
|
| 183 |
+
"loss": 0.6957,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.006813060112153451,
|
| 188 |
+
"grad_norm": 1.0274962186813354,
|
| 189 |
+
"learning_rate": 4.988644899813078e-05,
|
| 190 |
+
"loss": 0.5302,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.0070751008856978145,
|
| 195 |
+
"grad_norm": 1.2626285552978516,
|
| 196 |
+
"learning_rate": 4.988208165190504e-05,
|
| 197 |
+
"loss": 0.6541,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.007337141659242178,
|
| 202 |
+
"grad_norm": 1.4558316469192505,
|
| 203 |
+
"learning_rate": 4.98777143056793e-05,
|
| 204 |
+
"loss": 0.7284,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.007599182432786541,
|
| 209 |
+
"grad_norm": 1.3997328281402588,
|
| 210 |
+
"learning_rate": 4.987334695945356e-05,
|
| 211 |
+
"loss": 0.6888,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.007861223206330904,
|
| 216 |
+
"grad_norm": 1.7742432355880737,
|
| 217 |
+
"learning_rate": 4.986897961322782e-05,
|
| 218 |
+
"loss": 0.6869,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.008123263979875268,
|
| 223 |
+
"grad_norm": 1.4925923347473145,
|
| 224 |
+
"learning_rate": 4.986461226700208e-05,
|
| 225 |
+
"loss": 0.731,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.008385304753419632,
|
| 230 |
+
"grad_norm": 1.5941082239151,
|
| 231 |
+
"learning_rate": 4.986024492077634e-05,
|
| 232 |
+
"loss": 0.7149,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.008647345526963996,
|
| 237 |
+
"grad_norm": 1.507450819015503,
|
| 238 |
+
"learning_rate": 4.98558775745506e-05,
|
| 239 |
+
"loss": 0.6443,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.00890938630050836,
|
| 244 |
+
"grad_norm": 0.9866214990615845,
|
| 245 |
+
"learning_rate": 4.985151022832487e-05,
|
| 246 |
+
"loss": 0.6003,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.009171427074052723,
|
| 251 |
+
"grad_norm": 0.9682250022888184,
|
| 252 |
+
"learning_rate": 4.984714288209912e-05,
|
| 253 |
+
"loss": 0.6602,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.009433467847597085,
|
| 258 |
+
"grad_norm": 1.7567181587219238,
|
| 259 |
+
"learning_rate": 4.984277553587338e-05,
|
| 260 |
+
"loss": 0.5647,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.00969550862114145,
|
| 265 |
+
"grad_norm": 1.4297257661819458,
|
| 266 |
+
"learning_rate": 4.9838408189647643e-05,
|
| 267 |
+
"loss": 0.6628,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.009957549394685813,
|
| 272 |
+
"grad_norm": 1.515763521194458,
|
| 273 |
+
"learning_rate": 4.9834040843421904e-05,
|
| 274 |
+
"loss": 0.568,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.010219590168230177,
|
| 279 |
+
"grad_norm": 1.1806342601776123,
|
| 280 |
+
"learning_rate": 4.9829673497196164e-05,
|
| 281 |
+
"loss": 0.6729,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.01048163094177454,
|
| 286 |
+
"grad_norm": 1.1328020095825195,
|
| 287 |
+
"learning_rate": 4.9825306150970425e-05,
|
| 288 |
+
"loss": 0.6963,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.010743671715318903,
|
| 293 |
+
"grad_norm": 0.7740004658699036,
|
| 294 |
+
"learning_rate": 4.9820938804744685e-05,
|
| 295 |
+
"loss": 0.6654,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.011005712488863267,
|
| 300 |
+
"grad_norm": 0.9519413113594055,
|
| 301 |
+
"learning_rate": 4.9816571458518945e-05,
|
| 302 |
+
"loss": 0.6487,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.01126775326240763,
|
| 307 |
+
"grad_norm": 0.8964847922325134,
|
| 308 |
+
"learning_rate": 4.981220411229321e-05,
|
| 309 |
+
"loss": 0.5667,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.011529794035951994,
|
| 314 |
+
"grad_norm": 1.428072452545166,
|
| 315 |
+
"learning_rate": 4.9807836766067466e-05,
|
| 316 |
+
"loss": 0.8164,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.011791834809496358,
|
| 321 |
+
"grad_norm": 1.4375147819519043,
|
| 322 |
+
"learning_rate": 4.980346941984173e-05,
|
| 323 |
+
"loss": 0.5476,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.012053875583040722,
|
| 328 |
+
"grad_norm": 1.1702146530151367,
|
| 329 |
+
"learning_rate": 4.979910207361599e-05,
|
| 330 |
+
"loss": 0.7342,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.012315916356585084,
|
| 335 |
+
"grad_norm": 1.2703320980072021,
|
| 336 |
+
"learning_rate": 4.9794734727390254e-05,
|
| 337 |
+
"loss": 0.5767,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.012577957130129448,
|
| 342 |
+
"grad_norm": 1.2520267963409424,
|
| 343 |
+
"learning_rate": 4.979036738116451e-05,
|
| 344 |
+
"loss": 0.5969,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.012839997903673812,
|
| 349 |
+
"grad_norm": 1.413979172706604,
|
| 350 |
+
"learning_rate": 4.9786000034938775e-05,
|
| 351 |
+
"loss": 0.7011,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.013102038677218176,
|
| 356 |
+
"grad_norm": 1.3918565511703491,
|
| 357 |
+
"learning_rate": 4.978163268871303e-05,
|
| 358 |
+
"loss": 0.6041,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.01336407945076254,
|
| 363 |
+
"grad_norm": 0.9175894260406494,
|
| 364 |
+
"learning_rate": 4.9777265342487296e-05,
|
| 365 |
+
"loss": 0.5052,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.013626120224306901,
|
| 370 |
+
"grad_norm": 1.296505331993103,
|
| 371 |
+
"learning_rate": 4.9772897996261556e-05,
|
| 372 |
+
"loss": 0.6076,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.013888160997851265,
|
| 377 |
+
"grad_norm": 1.2490183115005493,
|
| 378 |
+
"learning_rate": 4.9768530650035816e-05,
|
| 379 |
+
"loss": 0.6287,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.014150201771395629,
|
| 384 |
+
"grad_norm": 1.398285984992981,
|
| 385 |
+
"learning_rate": 4.976416330381008e-05,
|
| 386 |
+
"loss": 0.7905,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.014412242544939993,
|
| 391 |
+
"grad_norm": 1.3094829320907593,
|
| 392 |
+
"learning_rate": 4.975979595758434e-05,
|
| 393 |
+
"loss": 0.5133,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.014674283318484357,
|
| 398 |
+
"grad_norm": 1.7128199338912964,
|
| 399 |
+
"learning_rate": 4.97554286113586e-05,
|
| 400 |
+
"loss": 0.824,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.014936324092028719,
|
| 405 |
+
"grad_norm": 1.1319103240966797,
|
| 406 |
+
"learning_rate": 4.975106126513286e-05,
|
| 407 |
+
"loss": 0.5893,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.015198364865573083,
|
| 412 |
+
"grad_norm": 1.6176029443740845,
|
| 413 |
+
"learning_rate": 4.974669391890712e-05,
|
| 414 |
+
"loss": 0.581,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.015460405639117446,
|
| 419 |
+
"grad_norm": 1.590836524963379,
|
| 420 |
+
"learning_rate": 4.974232657268138e-05,
|
| 421 |
+
"loss": 0.5814,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.01572244641266181,
|
| 426 |
+
"grad_norm": 1.6922227144241333,
|
| 427 |
+
"learning_rate": 4.973795922645564e-05,
|
| 428 |
+
"loss": 0.5917,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.015984487186206174,
|
| 433 |
+
"grad_norm": 1.3479337692260742,
|
| 434 |
+
"learning_rate": 4.97335918802299e-05,
|
| 435 |
+
"loss": 0.7356,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.016246527959750536,
|
| 440 |
+
"grad_norm": 2.2019124031066895,
|
| 441 |
+
"learning_rate": 4.972922453400416e-05,
|
| 442 |
+
"loss": 0.6197,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.016508568733294902,
|
| 447 |
+
"grad_norm": 1.6211423873901367,
|
| 448 |
+
"learning_rate": 4.972485718777842e-05,
|
| 449 |
+
"loss": 0.6299,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.016770609506839264,
|
| 454 |
+
"grad_norm": 1.157416582107544,
|
| 455 |
+
"learning_rate": 4.972048984155268e-05,
|
| 456 |
+
"loss": 0.6343,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.01703265028038363,
|
| 461 |
+
"grad_norm": 1.2576712369918823,
|
| 462 |
+
"learning_rate": 4.971612249532695e-05,
|
| 463 |
+
"loss": 0.6126,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.01729469105392799,
|
| 468 |
+
"grad_norm": 1.3852715492248535,
|
| 469 |
+
"learning_rate": 4.97117551491012e-05,
|
| 470 |
+
"loss": 0.6352,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.017556731827472354,
|
| 475 |
+
"grad_norm": 1.0178048610687256,
|
| 476 |
+
"learning_rate": 4.970738780287547e-05,
|
| 477 |
+
"loss": 0.5923,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.01781877260101672,
|
| 482 |
+
"grad_norm": 0.8760583996772766,
|
| 483 |
+
"learning_rate": 4.970302045664972e-05,
|
| 484 |
+
"loss": 0.6158,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.01808081337456108,
|
| 489 |
+
"grad_norm": 0.8956984281539917,
|
| 490 |
+
"learning_rate": 4.969865311042398e-05,
|
| 491 |
+
"loss": 0.5746,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.018342854148105447,
|
| 496 |
+
"grad_norm": 1.1126501560211182,
|
| 497 |
+
"learning_rate": 4.969428576419824e-05,
|
| 498 |
+
"loss": 0.6254,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.01860489492164981,
|
| 503 |
+
"grad_norm": 1.168455958366394,
|
| 504 |
+
"learning_rate": 4.96899184179725e-05,
|
| 505 |
+
"loss": 0.652,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.01886693569519417,
|
| 510 |
+
"grad_norm": 1.3628567457199097,
|
| 511 |
+
"learning_rate": 4.9685551071746764e-05,
|
| 512 |
+
"loss": 0.5789,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.019128976468738536,
|
| 517 |
+
"grad_norm": 1.1971865892410278,
|
| 518 |
+
"learning_rate": 4.9681183725521024e-05,
|
| 519 |
+
"loss": 0.6408,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.0193910172422829,
|
| 524 |
+
"grad_norm": 1.1916868686676025,
|
| 525 |
+
"learning_rate": 4.9676816379295285e-05,
|
| 526 |
+
"loss": 0.6461,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.019653058015827264,
|
| 531 |
+
"grad_norm": 1.1797837018966675,
|
| 532 |
+
"learning_rate": 4.9672449033069545e-05,
|
| 533 |
+
"loss": 0.5843,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.019915098789371626,
|
| 538 |
+
"grad_norm": 0.7941935658454895,
|
| 539 |
+
"learning_rate": 4.966808168684381e-05,
|
| 540 |
+
"loss": 0.6165,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.02017713956291599,
|
| 545 |
+
"grad_norm": 1.4876329898834229,
|
| 546 |
+
"learning_rate": 4.9663714340618066e-05,
|
| 547 |
+
"loss": 0.6347,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.020439180336460354,
|
| 552 |
+
"grad_norm": 1.1482038497924805,
|
| 553 |
+
"learning_rate": 4.965934699439233e-05,
|
| 554 |
+
"loss": 0.5662,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.020701221110004716,
|
| 559 |
+
"grad_norm": 1.3942419290542603,
|
| 560 |
+
"learning_rate": 4.9654979648166586e-05,
|
| 561 |
+
"loss": 0.6189,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.02096326188354908,
|
| 566 |
+
"grad_norm": 0.8826277256011963,
|
| 567 |
+
"learning_rate": 4.9650612301940854e-05,
|
| 568 |
+
"loss": 0.6801,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.021225302657093444,
|
| 573 |
+
"grad_norm": 1.3729712963104248,
|
| 574 |
+
"learning_rate": 4.964624495571511e-05,
|
| 575 |
+
"loss": 0.5789,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.021487343430637806,
|
| 580 |
+
"grad_norm": 0.747199296951294,
|
| 581 |
+
"learning_rate": 4.9641877609489374e-05,
|
| 582 |
+
"loss": 0.651,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.02174938420418217,
|
| 587 |
+
"grad_norm": 0.7911145091056824,
|
| 588 |
+
"learning_rate": 4.963751026326363e-05,
|
| 589 |
+
"loss": 0.6834,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.022011424977726533,
|
| 594 |
+
"grad_norm": 1.1725844144821167,
|
| 595 |
+
"learning_rate": 4.9633142917037895e-05,
|
| 596 |
+
"loss": 0.6687,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.0222734657512709,
|
| 601 |
+
"grad_norm": 1.2759829759597778,
|
| 602 |
+
"learning_rate": 4.9628775570812156e-05,
|
| 603 |
+
"loss": 0.6612,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.02253550652481526,
|
| 608 |
+
"grad_norm": 1.497684359550476,
|
| 609 |
+
"learning_rate": 4.9624408224586416e-05,
|
| 610 |
+
"loss": 0.686,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.022797547298359623,
|
| 615 |
+
"grad_norm": 1.4431102275848389,
|
| 616 |
+
"learning_rate": 4.9620040878360676e-05,
|
| 617 |
+
"loss": 0.5838,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.02305958807190399,
|
| 622 |
+
"grad_norm": 0.8864196538925171,
|
| 623 |
+
"learning_rate": 4.961567353213494e-05,
|
| 624 |
+
"loss": 0.6076,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.02332162884544835,
|
| 629 |
+
"grad_norm": 1.4421597719192505,
|
| 630 |
+
"learning_rate": 4.96113061859092e-05,
|
| 631 |
+
"loss": 0.6669,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.023583669618992716,
|
| 636 |
+
"grad_norm": 1.541601300239563,
|
| 637 |
+
"learning_rate": 4.960693883968346e-05,
|
| 638 |
+
"loss": 0.477,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.02384571039253708,
|
| 643 |
+
"grad_norm": 1.0725853443145752,
|
| 644 |
+
"learning_rate": 4.960257149345772e-05,
|
| 645 |
+
"loss": 0.5399,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.024107751166081444,
|
| 650 |
+
"grad_norm": 1.4579834938049316,
|
| 651 |
+
"learning_rate": 4.959820414723198e-05,
|
| 652 |
+
"loss": 0.636,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.024369791939625806,
|
| 657 |
+
"grad_norm": 1.1018449068069458,
|
| 658 |
+
"learning_rate": 4.959383680100624e-05,
|
| 659 |
+
"loss": 0.7731,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.024631832713170168,
|
| 664 |
+
"grad_norm": 1.3531861305236816,
|
| 665 |
+
"learning_rate": 4.95894694547805e-05,
|
| 666 |
+
"loss": 0.7017,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.024893873486714534,
|
| 671 |
+
"grad_norm": 1.1225773096084595,
|
| 672 |
+
"learning_rate": 4.958510210855476e-05,
|
| 673 |
+
"loss": 0.7228,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.025155914260258896,
|
| 678 |
+
"grad_norm": 0.6442508697509766,
|
| 679 |
+
"learning_rate": 4.958073476232902e-05,
|
| 680 |
+
"loss": 0.4421,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.02541795503380326,
|
| 685 |
+
"grad_norm": 1.1338638067245483,
|
| 686 |
+
"learning_rate": 4.957636741610328e-05,
|
| 687 |
+
"loss": 0.6533,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.025679995807347623,
|
| 692 |
+
"grad_norm": 1.0796573162078857,
|
| 693 |
+
"learning_rate": 4.957200006987755e-05,
|
| 694 |
+
"loss": 0.6407,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.025942036580891985,
|
| 699 |
+
"grad_norm": 1.001578450202942,
|
| 700 |
+
"learning_rate": 4.95676327236518e-05,
|
| 701 |
+
"loss": 0.652,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.02620407735443635,
|
| 706 |
+
"grad_norm": 1.521545648574829,
|
| 707 |
+
"learning_rate": 4.956326537742607e-05,
|
| 708 |
+
"loss": 0.4812,
|
| 709 |
+
"step": 1000
|
| 710 |
+
}
|
| 711 |
+
],
|
| 712 |
+
"logging_steps": 10,
|
| 713 |
+
"max_steps": 114486,
|
| 714 |
+
"num_input_tokens_seen": 0,
|
| 715 |
+
"num_train_epochs": 3,
|
| 716 |
+
"save_steps": 500,
|
| 717 |
+
"stateful_callbacks": {
|
| 718 |
+
"TrainerControl": {
|
| 719 |
+
"args": {
|
| 720 |
+
"should_epoch_stop": false,
|
| 721 |
+
"should_evaluate": false,
|
| 722 |
+
"should_log": false,
|
| 723 |
+
"should_save": true,
|
| 724 |
+
"should_training_stop": false
|
| 725 |
+
},
|
| 726 |
+
"attributes": {}
|
| 727 |
+
}
|
| 728 |
+
},
|
| 729 |
+
"total_flos": 3739037466624000.0,
|
| 730 |
+
"train_batch_size": 4,
|
| 731 |
+
"trial_name": null,
|
| 732 |
+
"trial_params": null
|
| 733 |
+
}
|
flutter_codegen_model/checkpoint-1000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da53cc9a018e467dc692093da1b9a59e8d739bedb689402e677cfe0810541434
|
| 3 |
+
size 5240
|
flutter_codegen_model/checkpoint-1000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
flutter_codegen_model/checkpoint-1500/added_tokens.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"\t\t": 50294,
|
| 3 |
+
"\t\t\t": 50293,
|
| 4 |
+
"\t\t\t\t": 50292,
|
| 5 |
+
"\t\t\t\t\t": 50291,
|
| 6 |
+
"\t\t\t\t\t\t": 50290,
|
| 7 |
+
"\t\t\t\t\t\t\t": 50289,
|
| 8 |
+
"\t\t\t\t\t\t\t\t": 50288,
|
| 9 |
+
"\t\t\t\t\t\t\t\t\t": 50287,
|
| 10 |
+
" ": 50286,
|
| 11 |
+
" ": 50285,
|
| 12 |
+
" ": 50284,
|
| 13 |
+
" ": 50283,
|
| 14 |
+
" ": 50282,
|
| 15 |
+
" ": 50281,
|
| 16 |
+
" ": 50280,
|
| 17 |
+
" ": 50279,
|
| 18 |
+
" ": 50278,
|
| 19 |
+
" ": 50277,
|
| 20 |
+
" ": 50276,
|
| 21 |
+
" ": 50275,
|
| 22 |
+
" ": 50274,
|
| 23 |
+
" ": 50273,
|
| 24 |
+
" ": 50272,
|
| 25 |
+
" ": 50271,
|
| 26 |
+
" ": 50270,
|
| 27 |
+
" ": 50269,
|
| 28 |
+
" ": 50268,
|
| 29 |
+
" ": 50267,
|
| 30 |
+
" ": 50266,
|
| 31 |
+
" ": 50265,
|
| 32 |
+
" ": 50264,
|
| 33 |
+
" ": 50263,
|
| 34 |
+
" ": 50262,
|
| 35 |
+
" ": 50261,
|
| 36 |
+
" ": 50260,
|
| 37 |
+
" ": 50259,
|
| 38 |
+
" ": 50258,
|
| 39 |
+
" ": 50257
|
| 40 |
+
}
|
flutter_codegen_model/checkpoint-1500/config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./flutter_codegen_model/checkpoint-500",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"CodeGenForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"embd_pdrop": 0.0,
|
| 10 |
+
"eos_token_id": 50256,
|
| 11 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "codegen",
|
| 15 |
+
"n_ctx": 2048,
|
| 16 |
+
"n_embd": 1024,
|
| 17 |
+
"n_head": 16,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 20,
|
| 20 |
+
"n_positions": 2048,
|
| 21 |
+
"resid_pdrop": 0.0,
|
| 22 |
+
"rotary_dim": 32,
|
| 23 |
+
"scale_attn_weights": true,
|
| 24 |
+
"summary_activation": null,
|
| 25 |
+
"summary_first_dropout": 0.1,
|
| 26 |
+
"summary_proj_to_labels": true,
|
| 27 |
+
"summary_type": "cls_index",
|
| 28 |
+
"summary_use_proj": true,
|
| 29 |
+
"task_specific_params": {
|
| 30 |
+
"text-generation": {
|
| 31 |
+
"do_sample": true,
|
| 32 |
+
"max_length": 50,
|
| 33 |
+
"temperature": 1.0
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"tie_word_embeddings": false,
|
| 37 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 38 |
+
"torch_dtype": "float32",
|
| 39 |
+
"transformers_version": "4.46.3",
|
| 40 |
+
"use_cache": true,
|
| 41 |
+
"vocab_size": 51200
|
| 42 |
+
}
|
flutter_codegen_model/checkpoint-1500/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.46.3"
|
| 6 |
+
}
|
flutter_codegen_model/checkpoint-1500/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
flutter_codegen_model/checkpoint-1500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78f591ad3269b4f50e1c9f87b6e2330de4fc1672522dae11bb362a2149ca1348
|
| 3 |
+
size 1426867192
|
flutter_codegen_model/checkpoint-1500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7281fe66fc45a9b2b2bf349a6c0e97585d4372b417b53b819c4e4acaa0959571
|
| 3 |
+
size 2853838010
|
flutter_codegen_model/checkpoint-1500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdf4d700cdd7ef81bf005d2842e2f669e1810471cfce670ab79872c6ee698af7
|
| 3 |
+
size 14244
|
flutter_codegen_model/checkpoint-1500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50e53cce2010b8d10917ee837774808926eef68f9dad453542a81370237a2b86
|
| 3 |
+
size 1064
|
flutter_codegen_model/checkpoint-1500/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|endoftext|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
flutter_codegen_model/checkpoint-1500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
flutter_codegen_model/checkpoint-1500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,332 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"50256": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"50257": {
|
| 13 |
+
"content": " ",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": false
|
| 19 |
+
},
|
| 20 |
+
"50258": {
|
| 21 |
+
"content": " ",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": false
|
| 27 |
+
},
|
| 28 |
+
"50259": {
|
| 29 |
+
"content": " ",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": false
|
| 35 |
+
},
|
| 36 |
+
"50260": {
|
| 37 |
+
"content": " ",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": false
|
| 43 |
+
},
|
| 44 |
+
"50261": {
|
| 45 |
+
"content": " ",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": false
|
| 51 |
+
},
|
| 52 |
+
"50262": {
|
| 53 |
+
"content": " ",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": true,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": false
|
| 59 |
+
},
|
| 60 |
+
"50263": {
|
| 61 |
+
"content": " ",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": true,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": false
|
| 67 |
+
},
|
| 68 |
+
"50264": {
|
| 69 |
+
"content": " ",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": true,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": false
|
| 75 |
+
},
|
| 76 |
+
"50265": {
|
| 77 |
+
"content": " ",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": true,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": false
|
| 83 |
+
},
|
| 84 |
+
"50266": {
|
| 85 |
+
"content": " ",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": true,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": false
|
| 91 |
+
},
|
| 92 |
+
"50267": {
|
| 93 |
+
"content": " ",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": true,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": false
|
| 99 |
+
},
|
| 100 |
+
"50268": {
|
| 101 |
+
"content": " ",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": true,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": false
|
| 107 |
+
},
|
| 108 |
+
"50269": {
|
| 109 |
+
"content": " ",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": true,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": false
|
| 115 |
+
},
|
| 116 |
+
"50270": {
|
| 117 |
+
"content": " ",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": true,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"50271": {
|
| 125 |
+
"content": " ",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": true,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"50272": {
|
| 133 |
+
"content": " ",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": true,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"50273": {
|
| 141 |
+
"content": " ",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": true,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"50274": {
|
| 149 |
+
"content": " ",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": true,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"50275": {
|
| 157 |
+
"content": " ",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": true,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"50276": {
|
| 165 |
+
"content": " ",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": true,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": false
|
| 171 |
+
},
|
| 172 |
+
"50277": {
|
| 173 |
+
"content": " ",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": true,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": false
|
| 179 |
+
},
|
| 180 |
+
"50278": {
|
| 181 |
+
"content": " ",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": true,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": false
|
| 187 |
+
},
|
| 188 |
+
"50279": {
|
| 189 |
+
"content": " ",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": true,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": false
|
| 195 |
+
},
|
| 196 |
+
"50280": {
|
| 197 |
+
"content": " ",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": true,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": false
|
| 203 |
+
},
|
| 204 |
+
"50281": {
|
| 205 |
+
"content": " ",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": true,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": false
|
| 211 |
+
},
|
| 212 |
+
"50282": {
|
| 213 |
+
"content": " ",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": true,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": false
|
| 219 |
+
},
|
| 220 |
+
"50283": {
|
| 221 |
+
"content": " ",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": true,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": false
|
| 227 |
+
},
|
| 228 |
+
"50284": {
|
| 229 |
+
"content": " ",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": true,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": false
|
| 235 |
+
},
|
| 236 |
+
"50285": {
|
| 237 |
+
"content": " ",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": true,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": false
|
| 243 |
+
},
|
| 244 |
+
"50286": {
|
| 245 |
+
"content": " ",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": true,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": false
|
| 251 |
+
},
|
| 252 |
+
"50287": {
|
| 253 |
+
"content": "\t\t\t\t\t\t\t\t\t",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": true,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": false
|
| 259 |
+
},
|
| 260 |
+
"50288": {
|
| 261 |
+
"content": "\t\t\t\t\t\t\t\t",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": true,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": false
|
| 267 |
+
},
|
| 268 |
+
"50289": {
|
| 269 |
+
"content": "\t\t\t\t\t\t\t",
|
| 270 |
+
"lstrip": false,
|
| 271 |
+
"normalized": true,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": false
|
| 275 |
+
},
|
| 276 |
+
"50290": {
|
| 277 |
+
"content": "\t\t\t\t\t\t",
|
| 278 |
+
"lstrip": false,
|
| 279 |
+
"normalized": true,
|
| 280 |
+
"rstrip": false,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": false
|
| 283 |
+
},
|
| 284 |
+
"50291": {
|
| 285 |
+
"content": "\t\t\t\t\t",
|
| 286 |
+
"lstrip": false,
|
| 287 |
+
"normalized": true,
|
| 288 |
+
"rstrip": false,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": false
|
| 291 |
+
},
|
| 292 |
+
"50292": {
|
| 293 |
+
"content": "\t\t\t\t",
|
| 294 |
+
"lstrip": false,
|
| 295 |
+
"normalized": true,
|
| 296 |
+
"rstrip": false,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": false
|
| 299 |
+
},
|
| 300 |
+
"50293": {
|
| 301 |
+
"content": "\t\t\t",
|
| 302 |
+
"lstrip": false,
|
| 303 |
+
"normalized": true,
|
| 304 |
+
"rstrip": false,
|
| 305 |
+
"single_word": false,
|
| 306 |
+
"special": false
|
| 307 |
+
},
|
| 308 |
+
"50294": {
|
| 309 |
+
"content": "\t\t",
|
| 310 |
+
"lstrip": false,
|
| 311 |
+
"normalized": true,
|
| 312 |
+
"rstrip": false,
|
| 313 |
+
"single_word": false,
|
| 314 |
+
"special": false
|
| 315 |
+
}
|
| 316 |
+
},
|
| 317 |
+
"bos_token": "<|endoftext|>",
|
| 318 |
+
"clean_up_tokenization_spaces": false,
|
| 319 |
+
"eos_token": "<|endoftext|>",
|
| 320 |
+
"max_length": 512,
|
| 321 |
+
"model_max_length": 2048,
|
| 322 |
+
"pad_to_multiple_of": null,
|
| 323 |
+
"pad_token": "<|endoftext|>",
|
| 324 |
+
"pad_token_type_id": 0,
|
| 325 |
+
"padding_side": "right",
|
| 326 |
+
"return_token_type_ids": false,
|
| 327 |
+
"stride": 0,
|
| 328 |
+
"tokenizer_class": "CodeGenTokenizer",
|
| 329 |
+
"truncation_side": "right",
|
| 330 |
+
"truncation_strategy": "longest_first",
|
| 331 |
+
"unk_token": "<|endoftext|>"
|
| 332 |
+
}
|
flutter_codegen_model/checkpoint-1500/trainer_state.json
ADDED
|
@@ -0,0 +1,1083 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.03930611603165453,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0002620407735443635,
|
| 13 |
+
"grad_norm": 1.2820378541946411,
|
| 14 |
+
"learning_rate": 4.999563265377426e-05,
|
| 15 |
+
"loss": 0.6609,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.000524081547088727,
|
| 20 |
+
"grad_norm": 1.3106062412261963,
|
| 21 |
+
"learning_rate": 4.999126530754852e-05,
|
| 22 |
+
"loss": 0.8066,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0007861223206330905,
|
| 27 |
+
"grad_norm": 1.6985974311828613,
|
| 28 |
+
"learning_rate": 4.9986897961322784e-05,
|
| 29 |
+
"loss": 0.6863,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.001048163094177454,
|
| 34 |
+
"grad_norm": 1.2552741765975952,
|
| 35 |
+
"learning_rate": 4.9982530615097044e-05,
|
| 36 |
+
"loss": 0.5674,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.0013102038677218176,
|
| 41 |
+
"grad_norm": 1.3928155899047852,
|
| 42 |
+
"learning_rate": 4.9978163268871304e-05,
|
| 43 |
+
"loss": 0.5992,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.001572244641266181,
|
| 48 |
+
"grad_norm": 1.5794411897659302,
|
| 49 |
+
"learning_rate": 4.9973795922645565e-05,
|
| 50 |
+
"loss": 0.7939,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.0018342854148105446,
|
| 55 |
+
"grad_norm": 1.4024512767791748,
|
| 56 |
+
"learning_rate": 4.9969428576419825e-05,
|
| 57 |
+
"loss": 0.6178,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.002096326188354908,
|
| 62 |
+
"grad_norm": 1.2232664823532104,
|
| 63 |
+
"learning_rate": 4.9965061230194085e-05,
|
| 64 |
+
"loss": 0.7544,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.0023583669618992714,
|
| 69 |
+
"grad_norm": 1.5368870496749878,
|
| 70 |
+
"learning_rate": 4.9960693883968346e-05,
|
| 71 |
+
"loss": 0.6645,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.002620407735443635,
|
| 76 |
+
"grad_norm": 1.6177372932434082,
|
| 77 |
+
"learning_rate": 4.9956326537742606e-05,
|
| 78 |
+
"loss": 0.6329,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.0028824485089879986,
|
| 83 |
+
"grad_norm": 1.3803173303604126,
|
| 84 |
+
"learning_rate": 4.995195919151687e-05,
|
| 85 |
+
"loss": 0.7114,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.003144489282532362,
|
| 90 |
+
"grad_norm": 1.5191670656204224,
|
| 91 |
+
"learning_rate": 4.9947591845291134e-05,
|
| 92 |
+
"loss": 0.8717,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.0034065300560767254,
|
| 97 |
+
"grad_norm": 1.2967548370361328,
|
| 98 |
+
"learning_rate": 4.994322449906539e-05,
|
| 99 |
+
"loss": 0.7618,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.003668570829621089,
|
| 104 |
+
"grad_norm": 1.8742738962173462,
|
| 105 |
+
"learning_rate": 4.9938857152839655e-05,
|
| 106 |
+
"loss": 0.5896,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.003930611603165452,
|
| 111 |
+
"grad_norm": 1.697966456413269,
|
| 112 |
+
"learning_rate": 4.993448980661391e-05,
|
| 113 |
+
"loss": 0.7493,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.004192652376709816,
|
| 118 |
+
"grad_norm": 1.5282775163650513,
|
| 119 |
+
"learning_rate": 4.9930122460388175e-05,
|
| 120 |
+
"loss": 0.6359,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.00445469315025418,
|
| 125 |
+
"grad_norm": 1.2776225805282593,
|
| 126 |
+
"learning_rate": 4.992575511416243e-05,
|
| 127 |
+
"loss": 0.7677,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.004716733923798543,
|
| 132 |
+
"grad_norm": 1.2036848068237305,
|
| 133 |
+
"learning_rate": 4.9921387767936696e-05,
|
| 134 |
+
"loss": 0.6234,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.0049787746973429066,
|
| 139 |
+
"grad_norm": 1.1325912475585938,
|
| 140 |
+
"learning_rate": 4.991702042171095e-05,
|
| 141 |
+
"loss": 0.624,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.00524081547088727,
|
| 146 |
+
"grad_norm": 1.3846409320831299,
|
| 147 |
+
"learning_rate": 4.991265307548522e-05,
|
| 148 |
+
"loss": 0.5979,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.005502856244431633,
|
| 153 |
+
"grad_norm": 1.9792439937591553,
|
| 154 |
+
"learning_rate": 4.990828572925948e-05,
|
| 155 |
+
"loss": 0.7897,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.005764897017975997,
|
| 160 |
+
"grad_norm": 1.8546253442764282,
|
| 161 |
+
"learning_rate": 4.990391838303374e-05,
|
| 162 |
+
"loss": 0.7035,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.006026937791520361,
|
| 167 |
+
"grad_norm": 1.5434975624084473,
|
| 168 |
+
"learning_rate": 4.9899551036808e-05,
|
| 169 |
+
"loss": 0.7092,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.006288978565064724,
|
| 174 |
+
"grad_norm": 1.0328209400177002,
|
| 175 |
+
"learning_rate": 4.989518369058226e-05,
|
| 176 |
+
"loss": 0.6239,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.006551019338609088,
|
| 181 |
+
"grad_norm": 0.9389006495475769,
|
| 182 |
+
"learning_rate": 4.989081634435652e-05,
|
| 183 |
+
"loss": 0.6957,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.006813060112153451,
|
| 188 |
+
"grad_norm": 1.0274962186813354,
|
| 189 |
+
"learning_rate": 4.988644899813078e-05,
|
| 190 |
+
"loss": 0.5302,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.0070751008856978145,
|
| 195 |
+
"grad_norm": 1.2626285552978516,
|
| 196 |
+
"learning_rate": 4.988208165190504e-05,
|
| 197 |
+
"loss": 0.6541,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.007337141659242178,
|
| 202 |
+
"grad_norm": 1.4558316469192505,
|
| 203 |
+
"learning_rate": 4.98777143056793e-05,
|
| 204 |
+
"loss": 0.7284,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.007599182432786541,
|
| 209 |
+
"grad_norm": 1.3997328281402588,
|
| 210 |
+
"learning_rate": 4.987334695945356e-05,
|
| 211 |
+
"loss": 0.6888,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.007861223206330904,
|
| 216 |
+
"grad_norm": 1.7742432355880737,
|
| 217 |
+
"learning_rate": 4.986897961322782e-05,
|
| 218 |
+
"loss": 0.6869,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.008123263979875268,
|
| 223 |
+
"grad_norm": 1.4925923347473145,
|
| 224 |
+
"learning_rate": 4.986461226700208e-05,
|
| 225 |
+
"loss": 0.731,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.008385304753419632,
|
| 230 |
+
"grad_norm": 1.5941082239151,
|
| 231 |
+
"learning_rate": 4.986024492077634e-05,
|
| 232 |
+
"loss": 0.7149,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.008647345526963996,
|
| 237 |
+
"grad_norm": 1.507450819015503,
|
| 238 |
+
"learning_rate": 4.98558775745506e-05,
|
| 239 |
+
"loss": 0.6443,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.00890938630050836,
|
| 244 |
+
"grad_norm": 0.9866214990615845,
|
| 245 |
+
"learning_rate": 4.985151022832487e-05,
|
| 246 |
+
"loss": 0.6003,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.009171427074052723,
|
| 251 |
+
"grad_norm": 0.9682250022888184,
|
| 252 |
+
"learning_rate": 4.984714288209912e-05,
|
| 253 |
+
"loss": 0.6602,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.009433467847597085,
|
| 258 |
+
"grad_norm": 1.7567181587219238,
|
| 259 |
+
"learning_rate": 4.984277553587338e-05,
|
| 260 |
+
"loss": 0.5647,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.00969550862114145,
|
| 265 |
+
"grad_norm": 1.4297257661819458,
|
| 266 |
+
"learning_rate": 4.9838408189647643e-05,
|
| 267 |
+
"loss": 0.6628,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.009957549394685813,
|
| 272 |
+
"grad_norm": 1.515763521194458,
|
| 273 |
+
"learning_rate": 4.9834040843421904e-05,
|
| 274 |
+
"loss": 0.568,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.010219590168230177,
|
| 279 |
+
"grad_norm": 1.1806342601776123,
|
| 280 |
+
"learning_rate": 4.9829673497196164e-05,
|
| 281 |
+
"loss": 0.6729,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.01048163094177454,
|
| 286 |
+
"grad_norm": 1.1328020095825195,
|
| 287 |
+
"learning_rate": 4.9825306150970425e-05,
|
| 288 |
+
"loss": 0.6963,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.010743671715318903,
|
| 293 |
+
"grad_norm": 0.7740004658699036,
|
| 294 |
+
"learning_rate": 4.9820938804744685e-05,
|
| 295 |
+
"loss": 0.6654,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.011005712488863267,
|
| 300 |
+
"grad_norm": 0.9519413113594055,
|
| 301 |
+
"learning_rate": 4.9816571458518945e-05,
|
| 302 |
+
"loss": 0.6487,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.01126775326240763,
|
| 307 |
+
"grad_norm": 0.8964847922325134,
|
| 308 |
+
"learning_rate": 4.981220411229321e-05,
|
| 309 |
+
"loss": 0.5667,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.011529794035951994,
|
| 314 |
+
"grad_norm": 1.428072452545166,
|
| 315 |
+
"learning_rate": 4.9807836766067466e-05,
|
| 316 |
+
"loss": 0.8164,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.011791834809496358,
|
| 321 |
+
"grad_norm": 1.4375147819519043,
|
| 322 |
+
"learning_rate": 4.980346941984173e-05,
|
| 323 |
+
"loss": 0.5476,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.012053875583040722,
|
| 328 |
+
"grad_norm": 1.1702146530151367,
|
| 329 |
+
"learning_rate": 4.979910207361599e-05,
|
| 330 |
+
"loss": 0.7342,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.012315916356585084,
|
| 335 |
+
"grad_norm": 1.2703320980072021,
|
| 336 |
+
"learning_rate": 4.9794734727390254e-05,
|
| 337 |
+
"loss": 0.5767,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.012577957130129448,
|
| 342 |
+
"grad_norm": 1.2520267963409424,
|
| 343 |
+
"learning_rate": 4.979036738116451e-05,
|
| 344 |
+
"loss": 0.5969,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.012839997903673812,
|
| 349 |
+
"grad_norm": 1.413979172706604,
|
| 350 |
+
"learning_rate": 4.9786000034938775e-05,
|
| 351 |
+
"loss": 0.7011,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.013102038677218176,
|
| 356 |
+
"grad_norm": 1.3918565511703491,
|
| 357 |
+
"learning_rate": 4.978163268871303e-05,
|
| 358 |
+
"loss": 0.6041,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.01336407945076254,
|
| 363 |
+
"grad_norm": 0.9175894260406494,
|
| 364 |
+
"learning_rate": 4.9777265342487296e-05,
|
| 365 |
+
"loss": 0.5052,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.013626120224306901,
|
| 370 |
+
"grad_norm": 1.296505331993103,
|
| 371 |
+
"learning_rate": 4.9772897996261556e-05,
|
| 372 |
+
"loss": 0.6076,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.013888160997851265,
|
| 377 |
+
"grad_norm": 1.2490183115005493,
|
| 378 |
+
"learning_rate": 4.9768530650035816e-05,
|
| 379 |
+
"loss": 0.6287,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.014150201771395629,
|
| 384 |
+
"grad_norm": 1.398285984992981,
|
| 385 |
+
"learning_rate": 4.976416330381008e-05,
|
| 386 |
+
"loss": 0.7905,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.014412242544939993,
|
| 391 |
+
"grad_norm": 1.3094829320907593,
|
| 392 |
+
"learning_rate": 4.975979595758434e-05,
|
| 393 |
+
"loss": 0.5133,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.014674283318484357,
|
| 398 |
+
"grad_norm": 1.7128199338912964,
|
| 399 |
+
"learning_rate": 4.97554286113586e-05,
|
| 400 |
+
"loss": 0.824,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.014936324092028719,
|
| 405 |
+
"grad_norm": 1.1319103240966797,
|
| 406 |
+
"learning_rate": 4.975106126513286e-05,
|
| 407 |
+
"loss": 0.5893,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.015198364865573083,
|
| 412 |
+
"grad_norm": 1.6176029443740845,
|
| 413 |
+
"learning_rate": 4.974669391890712e-05,
|
| 414 |
+
"loss": 0.581,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.015460405639117446,
|
| 419 |
+
"grad_norm": 1.590836524963379,
|
| 420 |
+
"learning_rate": 4.974232657268138e-05,
|
| 421 |
+
"loss": 0.5814,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.01572244641266181,
|
| 426 |
+
"grad_norm": 1.6922227144241333,
|
| 427 |
+
"learning_rate": 4.973795922645564e-05,
|
| 428 |
+
"loss": 0.5917,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.015984487186206174,
|
| 433 |
+
"grad_norm": 1.3479337692260742,
|
| 434 |
+
"learning_rate": 4.97335918802299e-05,
|
| 435 |
+
"loss": 0.7356,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.016246527959750536,
|
| 440 |
+
"grad_norm": 2.2019124031066895,
|
| 441 |
+
"learning_rate": 4.972922453400416e-05,
|
| 442 |
+
"loss": 0.6197,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.016508568733294902,
|
| 447 |
+
"grad_norm": 1.6211423873901367,
|
| 448 |
+
"learning_rate": 4.972485718777842e-05,
|
| 449 |
+
"loss": 0.6299,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.016770609506839264,
|
| 454 |
+
"grad_norm": 1.157416582107544,
|
| 455 |
+
"learning_rate": 4.972048984155268e-05,
|
| 456 |
+
"loss": 0.6343,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.01703265028038363,
|
| 461 |
+
"grad_norm": 1.2576712369918823,
|
| 462 |
+
"learning_rate": 4.971612249532695e-05,
|
| 463 |
+
"loss": 0.6126,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.01729469105392799,
|
| 468 |
+
"grad_norm": 1.3852715492248535,
|
| 469 |
+
"learning_rate": 4.97117551491012e-05,
|
| 470 |
+
"loss": 0.6352,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.017556731827472354,
|
| 475 |
+
"grad_norm": 1.0178048610687256,
|
| 476 |
+
"learning_rate": 4.970738780287547e-05,
|
| 477 |
+
"loss": 0.5923,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.01781877260101672,
|
| 482 |
+
"grad_norm": 0.8760583996772766,
|
| 483 |
+
"learning_rate": 4.970302045664972e-05,
|
| 484 |
+
"loss": 0.6158,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.01808081337456108,
|
| 489 |
+
"grad_norm": 0.8956984281539917,
|
| 490 |
+
"learning_rate": 4.969865311042398e-05,
|
| 491 |
+
"loss": 0.5746,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.018342854148105447,
|
| 496 |
+
"grad_norm": 1.1126501560211182,
|
| 497 |
+
"learning_rate": 4.969428576419824e-05,
|
| 498 |
+
"loss": 0.6254,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.01860489492164981,
|
| 503 |
+
"grad_norm": 1.168455958366394,
|
| 504 |
+
"learning_rate": 4.96899184179725e-05,
|
| 505 |
+
"loss": 0.652,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.01886693569519417,
|
| 510 |
+
"grad_norm": 1.3628567457199097,
|
| 511 |
+
"learning_rate": 4.9685551071746764e-05,
|
| 512 |
+
"loss": 0.5789,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.019128976468738536,
|
| 517 |
+
"grad_norm": 1.1971865892410278,
|
| 518 |
+
"learning_rate": 4.9681183725521024e-05,
|
| 519 |
+
"loss": 0.6408,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.0193910172422829,
|
| 524 |
+
"grad_norm": 1.1916868686676025,
|
| 525 |
+
"learning_rate": 4.9676816379295285e-05,
|
| 526 |
+
"loss": 0.6461,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.019653058015827264,
|
| 531 |
+
"grad_norm": 1.1797837018966675,
|
| 532 |
+
"learning_rate": 4.9672449033069545e-05,
|
| 533 |
+
"loss": 0.5843,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.019915098789371626,
|
| 538 |
+
"grad_norm": 0.7941935658454895,
|
| 539 |
+
"learning_rate": 4.966808168684381e-05,
|
| 540 |
+
"loss": 0.6165,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.02017713956291599,
|
| 545 |
+
"grad_norm": 1.4876329898834229,
|
| 546 |
+
"learning_rate": 4.9663714340618066e-05,
|
| 547 |
+
"loss": 0.6347,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.020439180336460354,
|
| 552 |
+
"grad_norm": 1.1482038497924805,
|
| 553 |
+
"learning_rate": 4.965934699439233e-05,
|
| 554 |
+
"loss": 0.5662,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.020701221110004716,
|
| 559 |
+
"grad_norm": 1.3942419290542603,
|
| 560 |
+
"learning_rate": 4.9654979648166586e-05,
|
| 561 |
+
"loss": 0.6189,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.02096326188354908,
|
| 566 |
+
"grad_norm": 0.8826277256011963,
|
| 567 |
+
"learning_rate": 4.9650612301940854e-05,
|
| 568 |
+
"loss": 0.6801,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.021225302657093444,
|
| 573 |
+
"grad_norm": 1.3729712963104248,
|
| 574 |
+
"learning_rate": 4.964624495571511e-05,
|
| 575 |
+
"loss": 0.5789,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.021487343430637806,
|
| 580 |
+
"grad_norm": 0.747199296951294,
|
| 581 |
+
"learning_rate": 4.9641877609489374e-05,
|
| 582 |
+
"loss": 0.651,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.02174938420418217,
|
| 587 |
+
"grad_norm": 0.7911145091056824,
|
| 588 |
+
"learning_rate": 4.963751026326363e-05,
|
| 589 |
+
"loss": 0.6834,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.022011424977726533,
|
| 594 |
+
"grad_norm": 1.1725844144821167,
|
| 595 |
+
"learning_rate": 4.9633142917037895e-05,
|
| 596 |
+
"loss": 0.6687,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.0222734657512709,
|
| 601 |
+
"grad_norm": 1.2759829759597778,
|
| 602 |
+
"learning_rate": 4.9628775570812156e-05,
|
| 603 |
+
"loss": 0.6612,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.02253550652481526,
|
| 608 |
+
"grad_norm": 1.497684359550476,
|
| 609 |
+
"learning_rate": 4.9624408224586416e-05,
|
| 610 |
+
"loss": 0.686,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.022797547298359623,
|
| 615 |
+
"grad_norm": 1.4431102275848389,
|
| 616 |
+
"learning_rate": 4.9620040878360676e-05,
|
| 617 |
+
"loss": 0.5838,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.02305958807190399,
|
| 622 |
+
"grad_norm": 0.8864196538925171,
|
| 623 |
+
"learning_rate": 4.961567353213494e-05,
|
| 624 |
+
"loss": 0.6076,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.02332162884544835,
|
| 629 |
+
"grad_norm": 1.4421597719192505,
|
| 630 |
+
"learning_rate": 4.96113061859092e-05,
|
| 631 |
+
"loss": 0.6669,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.023583669618992716,
|
| 636 |
+
"grad_norm": 1.541601300239563,
|
| 637 |
+
"learning_rate": 4.960693883968346e-05,
|
| 638 |
+
"loss": 0.477,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.02384571039253708,
|
| 643 |
+
"grad_norm": 1.0725853443145752,
|
| 644 |
+
"learning_rate": 4.960257149345772e-05,
|
| 645 |
+
"loss": 0.5399,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.024107751166081444,
|
| 650 |
+
"grad_norm": 1.4579834938049316,
|
| 651 |
+
"learning_rate": 4.959820414723198e-05,
|
| 652 |
+
"loss": 0.636,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.024369791939625806,
|
| 657 |
+
"grad_norm": 1.1018449068069458,
|
| 658 |
+
"learning_rate": 4.959383680100624e-05,
|
| 659 |
+
"loss": 0.7731,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.024631832713170168,
|
| 664 |
+
"grad_norm": 1.3531861305236816,
|
| 665 |
+
"learning_rate": 4.95894694547805e-05,
|
| 666 |
+
"loss": 0.7017,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.024893873486714534,
|
| 671 |
+
"grad_norm": 1.1225773096084595,
|
| 672 |
+
"learning_rate": 4.958510210855476e-05,
|
| 673 |
+
"loss": 0.7228,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.025155914260258896,
|
| 678 |
+
"grad_norm": 0.6442508697509766,
|
| 679 |
+
"learning_rate": 4.958073476232902e-05,
|
| 680 |
+
"loss": 0.4421,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.02541795503380326,
|
| 685 |
+
"grad_norm": 1.1338638067245483,
|
| 686 |
+
"learning_rate": 4.957636741610328e-05,
|
| 687 |
+
"loss": 0.6533,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.025679995807347623,
|
| 692 |
+
"grad_norm": 1.0796573162078857,
|
| 693 |
+
"learning_rate": 4.957200006987755e-05,
|
| 694 |
+
"loss": 0.6407,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.025942036580891985,
|
| 699 |
+
"grad_norm": 1.001578450202942,
|
| 700 |
+
"learning_rate": 4.95676327236518e-05,
|
| 701 |
+
"loss": 0.652,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.02620407735443635,
|
| 706 |
+
"grad_norm": 1.521545648574829,
|
| 707 |
+
"learning_rate": 4.956326537742607e-05,
|
| 708 |
+
"loss": 0.4812,
|
| 709 |
+
"step": 1000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.026466118127980713,
|
| 713 |
+
"grad_norm": 1.1855580806732178,
|
| 714 |
+
"learning_rate": 4.955889803120032e-05,
|
| 715 |
+
"loss": 0.5927,
|
| 716 |
+
"step": 1010
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.02672815890152508,
|
| 720 |
+
"grad_norm": 1.3463046550750732,
|
| 721 |
+
"learning_rate": 4.955453068497459e-05,
|
| 722 |
+
"loss": 0.7304,
|
| 723 |
+
"step": 1020
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.02699019967506944,
|
| 727 |
+
"grad_norm": 1.0500322580337524,
|
| 728 |
+
"learning_rate": 4.955016333874884e-05,
|
| 729 |
+
"loss": 0.5409,
|
| 730 |
+
"step": 1030
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.027252240448613803,
|
| 734 |
+
"grad_norm": 1.4060779809951782,
|
| 735 |
+
"learning_rate": 4.95457959925231e-05,
|
| 736 |
+
"loss": 0.7348,
|
| 737 |
+
"step": 1040
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.02751428122215817,
|
| 741 |
+
"grad_norm": 1.433759331703186,
|
| 742 |
+
"learning_rate": 4.954142864629736e-05,
|
| 743 |
+
"loss": 0.6079,
|
| 744 |
+
"step": 1050
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.02777632199570253,
|
| 748 |
+
"grad_norm": 2.5895800590515137,
|
| 749 |
+
"learning_rate": 4.9537061300071624e-05,
|
| 750 |
+
"loss": 0.5789,
|
| 751 |
+
"step": 1060
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.028038362769246896,
|
| 755 |
+
"grad_norm": 1.1626940965652466,
|
| 756 |
+
"learning_rate": 4.953269395384589e-05,
|
| 757 |
+
"loss": 0.5478,
|
| 758 |
+
"step": 1070
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.028300403542791258,
|
| 762 |
+
"grad_norm": 1.6183115243911743,
|
| 763 |
+
"learning_rate": 4.9528326607620144e-05,
|
| 764 |
+
"loss": 0.6782,
|
| 765 |
+
"step": 1080
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.02856244431633562,
|
| 769 |
+
"grad_norm": 1.5321258306503296,
|
| 770 |
+
"learning_rate": 4.952395926139441e-05,
|
| 771 |
+
"loss": 0.5878,
|
| 772 |
+
"step": 1090
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.028824485089879986,
|
| 776 |
+
"grad_norm": 0.9456602334976196,
|
| 777 |
+
"learning_rate": 4.9519591915168665e-05,
|
| 778 |
+
"loss": 0.6277,
|
| 779 |
+
"step": 1100
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.029086525863424348,
|
| 783 |
+
"grad_norm": 1.0988554954528809,
|
| 784 |
+
"learning_rate": 4.951522456894293e-05,
|
| 785 |
+
"loss": 0.5019,
|
| 786 |
+
"step": 1110
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.029348566636968713,
|
| 790 |
+
"grad_norm": 1.053934931755066,
|
| 791 |
+
"learning_rate": 4.9510857222717186e-05,
|
| 792 |
+
"loss": 0.6578,
|
| 793 |
+
"step": 1120
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.029610607410513076,
|
| 797 |
+
"grad_norm": 1.292533040046692,
|
| 798 |
+
"learning_rate": 4.950648987649145e-05,
|
| 799 |
+
"loss": 0.6115,
|
| 800 |
+
"step": 1130
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.029872648184057438,
|
| 804 |
+
"grad_norm": 0.8503355383872986,
|
| 805 |
+
"learning_rate": 4.950212253026571e-05,
|
| 806 |
+
"loss": 0.56,
|
| 807 |
+
"step": 1140
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.030134688957601803,
|
| 811 |
+
"grad_norm": 1.5698297023773193,
|
| 812 |
+
"learning_rate": 4.9497755184039974e-05,
|
| 813 |
+
"loss": 0.6208,
|
| 814 |
+
"step": 1150
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.030396729731146165,
|
| 818 |
+
"grad_norm": 1.3464306592941284,
|
| 819 |
+
"learning_rate": 4.9493387837814234e-05,
|
| 820 |
+
"loss": 0.5812,
|
| 821 |
+
"step": 1160
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.03065877050469053,
|
| 825 |
+
"grad_norm": 0.9388158321380615,
|
| 826 |
+
"learning_rate": 4.9489020491588495e-05,
|
| 827 |
+
"loss": 0.5684,
|
| 828 |
+
"step": 1170
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.030920811278234893,
|
| 832 |
+
"grad_norm": 1.271061897277832,
|
| 833 |
+
"learning_rate": 4.9484653145362755e-05,
|
| 834 |
+
"loss": 0.5456,
|
| 835 |
+
"step": 1180
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.03118285205177926,
|
| 839 |
+
"grad_norm": 0.8666424751281738,
|
| 840 |
+
"learning_rate": 4.9480285799137015e-05,
|
| 841 |
+
"loss": 0.5418,
|
| 842 |
+
"step": 1190
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.03144489282532362,
|
| 846 |
+
"grad_norm": 1.2482844591140747,
|
| 847 |
+
"learning_rate": 4.9475918452911276e-05,
|
| 848 |
+
"loss": 0.7439,
|
| 849 |
+
"step": 1200
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.03170693359886798,
|
| 853 |
+
"grad_norm": 1.226784110069275,
|
| 854 |
+
"learning_rate": 4.9471551106685536e-05,
|
| 855 |
+
"loss": 0.5813,
|
| 856 |
+
"step": 1210
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.03196897437241235,
|
| 860 |
+
"grad_norm": 1.1704344749450684,
|
| 861 |
+
"learning_rate": 4.9467183760459797e-05,
|
| 862 |
+
"loss": 0.757,
|
| 863 |
+
"step": 1220
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.032231015145956714,
|
| 867 |
+
"grad_norm": 1.0429288148880005,
|
| 868 |
+
"learning_rate": 4.946281641423406e-05,
|
| 869 |
+
"loss": 0.5162,
|
| 870 |
+
"step": 1230
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.03249305591950107,
|
| 874 |
+
"grad_norm": 1.3331559896469116,
|
| 875 |
+
"learning_rate": 4.945844906800832e-05,
|
| 876 |
+
"loss": 0.6224,
|
| 877 |
+
"step": 1240
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.03275509669304544,
|
| 881 |
+
"grad_norm": 1.2090318202972412,
|
| 882 |
+
"learning_rate": 4.945408172178258e-05,
|
| 883 |
+
"loss": 0.6473,
|
| 884 |
+
"step": 1250
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.033017137466589803,
|
| 888 |
+
"grad_norm": 1.3969329595565796,
|
| 889 |
+
"learning_rate": 4.944971437555684e-05,
|
| 890 |
+
"loss": 0.5806,
|
| 891 |
+
"step": 1260
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.03327917824013416,
|
| 895 |
+
"grad_norm": 1.6032638549804688,
|
| 896 |
+
"learning_rate": 4.94453470293311e-05,
|
| 897 |
+
"loss": 0.5766,
|
| 898 |
+
"step": 1270
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.03354121901367853,
|
| 902 |
+
"grad_norm": 1.0155426263809204,
|
| 903 |
+
"learning_rate": 4.944097968310536e-05,
|
| 904 |
+
"loss": 0.5711,
|
| 905 |
+
"step": 1280
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.03380325978722289,
|
| 909 |
+
"grad_norm": 1.2512564659118652,
|
| 910 |
+
"learning_rate": 4.9436612336879626e-05,
|
| 911 |
+
"loss": 0.6783,
|
| 912 |
+
"step": 1290
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.03406530056076726,
|
| 916 |
+
"grad_norm": 1.0756443738937378,
|
| 917 |
+
"learning_rate": 4.943224499065388e-05,
|
| 918 |
+
"loss": 0.6255,
|
| 919 |
+
"step": 1300
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.03432734133431162,
|
| 923 |
+
"grad_norm": 1.2002949714660645,
|
| 924 |
+
"learning_rate": 4.942787764442815e-05,
|
| 925 |
+
"loss": 0.6057,
|
| 926 |
+
"step": 1310
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.03458938210785598,
|
| 930 |
+
"grad_norm": 0.6843838691711426,
|
| 931 |
+
"learning_rate": 4.94235102982024e-05,
|
| 932 |
+
"loss": 0.5411,
|
| 933 |
+
"step": 1320
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.03485142288140035,
|
| 937 |
+
"grad_norm": 0.8038992285728455,
|
| 938 |
+
"learning_rate": 4.941914295197667e-05,
|
| 939 |
+
"loss": 0.6097,
|
| 940 |
+
"step": 1330
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.03511346365494471,
|
| 944 |
+
"grad_norm": 1.2226810455322266,
|
| 945 |
+
"learning_rate": 4.941477560575092e-05,
|
| 946 |
+
"loss": 0.5731,
|
| 947 |
+
"step": 1340
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.03537550442848907,
|
| 951 |
+
"grad_norm": 1.236194372177124,
|
| 952 |
+
"learning_rate": 4.941040825952519e-05,
|
| 953 |
+
"loss": 0.5677,
|
| 954 |
+
"step": 1350
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.03563754520203344,
|
| 958 |
+
"grad_norm": 1.2129302024841309,
|
| 959 |
+
"learning_rate": 4.940604091329944e-05,
|
| 960 |
+
"loss": 0.6031,
|
| 961 |
+
"step": 1360
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.0358995859755778,
|
| 965 |
+
"grad_norm": 1.5371068716049194,
|
| 966 |
+
"learning_rate": 4.94016735670737e-05,
|
| 967 |
+
"loss": 0.5957,
|
| 968 |
+
"step": 1370
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.03616162674912216,
|
| 972 |
+
"grad_norm": 1.6025753021240234,
|
| 973 |
+
"learning_rate": 4.939730622084797e-05,
|
| 974 |
+
"loss": 0.6261,
|
| 975 |
+
"step": 1380
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.03642366752266653,
|
| 979 |
+
"grad_norm": 1.3252272605895996,
|
| 980 |
+
"learning_rate": 4.939293887462222e-05,
|
| 981 |
+
"loss": 0.626,
|
| 982 |
+
"step": 1390
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.036685708296210894,
|
| 986 |
+
"grad_norm": 1.0813733339309692,
|
| 987 |
+
"learning_rate": 4.938857152839649e-05,
|
| 988 |
+
"loss": 0.6659,
|
| 989 |
+
"step": 1400
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.03694774906975525,
|
| 993 |
+
"grad_norm": 1.280362844467163,
|
| 994 |
+
"learning_rate": 4.9384204182170744e-05,
|
| 995 |
+
"loss": 0.5828,
|
| 996 |
+
"step": 1410
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.03720978984329962,
|
| 1000 |
+
"grad_norm": 0.7822287082672119,
|
| 1001 |
+
"learning_rate": 4.937983683594501e-05,
|
| 1002 |
+
"loss": 0.4939,
|
| 1003 |
+
"step": 1420
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.03747183061684398,
|
| 1007 |
+
"grad_norm": 1.0170814990997314,
|
| 1008 |
+
"learning_rate": 4.9375469489719265e-05,
|
| 1009 |
+
"loss": 0.5846,
|
| 1010 |
+
"step": 1430
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.03773387139038834,
|
| 1014 |
+
"grad_norm": 1.4380531311035156,
|
| 1015 |
+
"learning_rate": 4.937110214349353e-05,
|
| 1016 |
+
"loss": 0.5203,
|
| 1017 |
+
"step": 1440
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.03799591216393271,
|
| 1021 |
+
"grad_norm": 0.9485931396484375,
|
| 1022 |
+
"learning_rate": 4.9366734797267785e-05,
|
| 1023 |
+
"loss": 0.4703,
|
| 1024 |
+
"step": 1450
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.03825795293747707,
|
| 1028 |
+
"grad_norm": 1.4566253423690796,
|
| 1029 |
+
"learning_rate": 4.936236745104205e-05,
|
| 1030 |
+
"loss": 0.6879,
|
| 1031 |
+
"step": 1460
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.03851999371102143,
|
| 1035 |
+
"grad_norm": 1.3309845924377441,
|
| 1036 |
+
"learning_rate": 4.935800010481631e-05,
|
| 1037 |
+
"loss": 0.6359,
|
| 1038 |
+
"step": 1470
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.0387820344845658,
|
| 1042 |
+
"grad_norm": 0.8272371292114258,
|
| 1043 |
+
"learning_rate": 4.9353632758590573e-05,
|
| 1044 |
+
"loss": 0.5521,
|
| 1045 |
+
"step": 1480
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.03904407525811016,
|
| 1049 |
+
"grad_norm": 1.122835397720337,
|
| 1050 |
+
"learning_rate": 4.9349265412364834e-05,
|
| 1051 |
+
"loss": 0.5871,
|
| 1052 |
+
"step": 1490
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.03930611603165453,
|
| 1056 |
+
"grad_norm": 1.701686978340149,
|
| 1057 |
+
"learning_rate": 4.9344898066139094e-05,
|
| 1058 |
+
"loss": 0.5549,
|
| 1059 |
+
"step": 1500
|
| 1060 |
+
}
|
| 1061 |
+
],
|
| 1062 |
+
"logging_steps": 10,
|
| 1063 |
+
"max_steps": 114486,
|
| 1064 |
+
"num_input_tokens_seen": 0,
|
| 1065 |
+
"num_train_epochs": 3,
|
| 1066 |
+
"save_steps": 500,
|
| 1067 |
+
"stateful_callbacks": {
|
| 1068 |
+
"TrainerControl": {
|
| 1069 |
+
"args": {
|
| 1070 |
+
"should_epoch_stop": false,
|
| 1071 |
+
"should_evaluate": false,
|
| 1072 |
+
"should_log": false,
|
| 1073 |
+
"should_save": true,
|
| 1074 |
+
"should_training_stop": false
|
| 1075 |
+
},
|
| 1076 |
+
"attributes": {}
|
| 1077 |
+
}
|
| 1078 |
+
},
|
| 1079 |
+
"total_flos": 5608556199936000.0,
|
| 1080 |
+
"train_batch_size": 4,
|
| 1081 |
+
"trial_name": null,
|
| 1082 |
+
"trial_params": null
|
| 1083 |
+
}
|
flutter_codegen_model/checkpoint-1500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da53cc9a018e467dc692093da1b9a59e8d739bedb689402e677cfe0810541434
|
| 3 |
+
size 5240
|
flutter_codegen_model/checkpoint-1500/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|