Training in progress, step 8000, checkpoint
Browse files- checkpoint-8000/config.json +30 -0
- checkpoint-8000/generation_config.json +6 -0
- checkpoint-8000/model.safetensors +3 -0
- checkpoint-8000/optimizer.pt +3 -0
- checkpoint-8000/rng_state.pth +3 -0
- checkpoint-8000/scheduler.pt +3 -0
- checkpoint-8000/special_tokens_map.json +24 -0
- checkpoint-8000/tokenizer.json +96 -0
- checkpoint-8000/tokenizer_config.json +38 -0
- checkpoint-8000/trainer_state.json +593 -0
- checkpoint-8000/training_args.bin +3 -0
checkpoint-8000/config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "EleutherAI/pythia-410m",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPTNeoXForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": true,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"classifier_dropout": 0.1,
|
| 10 |
+
"eos_token_id": 0,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout": 0.0,
|
| 13 |
+
"hidden_size": 1024,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 4096,
|
| 16 |
+
"layer_norm_eps": 1e-05,
|
| 17 |
+
"max_position_embeddings": 2048,
|
| 18 |
+
"model_type": "gpt_neox",
|
| 19 |
+
"num_attention_heads": 16,
|
| 20 |
+
"num_hidden_layers": 24,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rotary_emb_base": 10000,
|
| 23 |
+
"rotary_pct": 0.25,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.42.3",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"use_parallel_residual": true,
|
| 29 |
+
"vocab_size": 8
|
| 30 |
+
}
|
checkpoint-8000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"transformers_version": "4.42.3"
|
| 6 |
+
}
|
checkpoint-8000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:571210f5d0cd99abd08ad90e08a19c3d3a2364695b1b84ccacddecfc7e4d5606
|
| 3 |
+
size 1209345104
|
checkpoint-8000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c0fc6ba81b3d4e14d7c42d8041b1ddcb1af98f1899a69c2cd415cf0f7fbe079
|
| 3 |
+
size 2418866362
|
checkpoint-8000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:835f869ea325fd6edf27b48b589309fb66641cb92b45f2fc13d1bb6e8814106c
|
| 3 |
+
size 14244
|
checkpoint-8000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0738ec7e7458fa0193b58be501f2c485ec49362fb95c24e7acfa05745405312b
|
| 3 |
+
size 1064
|
checkpoint-8000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|beginoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 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": "<|unknown|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
checkpoint-8000/tokenizer.json
ADDED
|
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 0,
|
| 8 |
+
"content": "<|beginoftext|>",
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"special": true
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"id": 1,
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"special": true
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"id": 2,
|
| 26 |
+
"content": "<|unknown|>",
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"special": true
|
| 32 |
+
}
|
| 33 |
+
],
|
| 34 |
+
"normalizer": {
|
| 35 |
+
"type": "NFC"
|
| 36 |
+
},
|
| 37 |
+
"pre_tokenizer": {
|
| 38 |
+
"type": "ByteLevel",
|
| 39 |
+
"add_prefix_space": false,
|
| 40 |
+
"trim_offsets": true,
|
| 41 |
+
"use_regex": true
|
| 42 |
+
},
|
| 43 |
+
"post_processor": {
|
| 44 |
+
"type": "TemplateProcessing",
|
| 45 |
+
"single": [
|
| 46 |
+
{
|
| 47 |
+
"Sequence": {
|
| 48 |
+
"id": "A",
|
| 49 |
+
"type_id": 0
|
| 50 |
+
}
|
| 51 |
+
}
|
| 52 |
+
],
|
| 53 |
+
"pair": [
|
| 54 |
+
{
|
| 55 |
+
"Sequence": {
|
| 56 |
+
"id": "A",
|
| 57 |
+
"type_id": 0
|
| 58 |
+
}
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"Sequence": {
|
| 62 |
+
"id": "B",
|
| 63 |
+
"type_id": 1
|
| 64 |
+
}
|
| 65 |
+
}
|
| 66 |
+
],
|
| 67 |
+
"special_tokens": {}
|
| 68 |
+
},
|
| 69 |
+
"decoder": {
|
| 70 |
+
"type": "ByteLevel",
|
| 71 |
+
"add_prefix_space": false,
|
| 72 |
+
"trim_offsets": true,
|
| 73 |
+
"use_regex": true
|
| 74 |
+
},
|
| 75 |
+
"model": {
|
| 76 |
+
"type": "BPE",
|
| 77 |
+
"dropout": null,
|
| 78 |
+
"unk_token": "<|unknown|>",
|
| 79 |
+
"continuing_subword_prefix": null,
|
| 80 |
+
"end_of_word_suffix": null,
|
| 81 |
+
"fuse_unk": false,
|
| 82 |
+
"byte_fallback": false,
|
| 83 |
+
"ignore_merges": false,
|
| 84 |
+
"vocab": {
|
| 85 |
+
"<|beginoftext|>": 0,
|
| 86 |
+
"<|padding|>": 1,
|
| 87 |
+
"<|unknown|>": 2,
|
| 88 |
+
"a": 3,
|
| 89 |
+
"c": 4,
|
| 90 |
+
"g": 5,
|
| 91 |
+
"t": 6,
|
| 92 |
+
"n": 7
|
| 93 |
+
},
|
| 94 |
+
"merges": []
|
| 95 |
+
}
|
| 96 |
+
}
|
checkpoint-8000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": false,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<|beginoftext|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": true,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<|endoftext|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "<|unknown|>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"bos_token": "<|beginoftext|>",
|
| 32 |
+
"clean_up_tokenization_spaces": true,
|
| 33 |
+
"eos_token": "<|endoftext|>",
|
| 34 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 35 |
+
"pad_token": "<|endoftext|>",
|
| 36 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
| 37 |
+
"unk_token": "<|unknown|>"
|
| 38 |
+
}
|
checkpoint-8000/trainer_state.json
ADDED
|
@@ -0,0 +1,593 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.02605837727970085,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 8000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0003257297159962606,
|
| 13 |
+
"grad_norm": 2.2308592796325684,
|
| 14 |
+
"learning_rate": 4.99853416853153e-05,
|
| 15 |
+
"loss": 1.4483,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0006514594319925212,
|
| 20 |
+
"grad_norm": 2.3997225761413574,
|
| 21 |
+
"learning_rate": 4.996905466899897e-05,
|
| 22 |
+
"loss": 1.3276,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0009771891479887819,
|
| 27 |
+
"grad_norm": 1.4687339067459106,
|
| 28 |
+
"learning_rate": 4.995276765268264e-05,
|
| 29 |
+
"loss": 1.3394,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0013029188639850425,
|
| 34 |
+
"grad_norm": 0.6583470702171326,
|
| 35 |
+
"learning_rate": 4.993648063636631e-05,
|
| 36 |
+
"loss": 1.3245,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.0016286485799813031,
|
| 41 |
+
"grad_norm": 1.6252340078353882,
|
| 42 |
+
"learning_rate": 4.992019362004997e-05,
|
| 43 |
+
"loss": 1.3249,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.0019543782959775637,
|
| 48 |
+
"grad_norm": 2.0806777477264404,
|
| 49 |
+
"learning_rate": 4.9903906603733634e-05,
|
| 50 |
+
"loss": 1.32,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.002280108011973824,
|
| 55 |
+
"grad_norm": 1.376539707183838,
|
| 56 |
+
"learning_rate": 4.988761958741731e-05,
|
| 57 |
+
"loss": 1.3133,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.002605837727970085,
|
| 62 |
+
"grad_norm": 2.234644889831543,
|
| 63 |
+
"learning_rate": 4.987133257110097e-05,
|
| 64 |
+
"loss": 1.3179,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.0029315674439663454,
|
| 69 |
+
"grad_norm": 1.4599684476852417,
|
| 70 |
+
"learning_rate": 4.985504555478464e-05,
|
| 71 |
+
"loss": 1.3097,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.0032572971599626062,
|
| 76 |
+
"grad_norm": 1.7078094482421875,
|
| 77 |
+
"learning_rate": 4.9838758538468304e-05,
|
| 78 |
+
"loss": 1.3083,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.0035830268759588666,
|
| 83 |
+
"grad_norm": 0.6953567266464233,
|
| 84 |
+
"learning_rate": 4.9822471522151976e-05,
|
| 85 |
+
"loss": 1.3075,
|
| 86 |
+
"step": 1100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.0039087565919551275,
|
| 90 |
+
"grad_norm": 1.225602626800537,
|
| 91 |
+
"learning_rate": 4.980618450583564e-05,
|
| 92 |
+
"loss": 1.3054,
|
| 93 |
+
"step": 1200
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.004234486307951388,
|
| 97 |
+
"grad_norm": 1.3010519742965698,
|
| 98 |
+
"learning_rate": 4.978989748951931e-05,
|
| 99 |
+
"loss": 1.3066,
|
| 100 |
+
"step": 1300
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.004560216023947648,
|
| 104 |
+
"grad_norm": 0.6475724577903748,
|
| 105 |
+
"learning_rate": 4.9773610473202974e-05,
|
| 106 |
+
"loss": 1.3109,
|
| 107 |
+
"step": 1400
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.004885945739943909,
|
| 111 |
+
"grad_norm": 1.046614646911621,
|
| 112 |
+
"learning_rate": 4.975732345688664e-05,
|
| 113 |
+
"loss": 1.3074,
|
| 114 |
+
"step": 1500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.00521167545594017,
|
| 118 |
+
"grad_norm": 1.113573670387268,
|
| 119 |
+
"learning_rate": 4.974103644057031e-05,
|
| 120 |
+
"loss": 1.3083,
|
| 121 |
+
"step": 1600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.005537405171936431,
|
| 125 |
+
"grad_norm": 1.4273550510406494,
|
| 126 |
+
"learning_rate": 4.972474942425398e-05,
|
| 127 |
+
"loss": 1.3018,
|
| 128 |
+
"step": 1700
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.005863134887932691,
|
| 132 |
+
"grad_norm": 0.5519908666610718,
|
| 133 |
+
"learning_rate": 4.970846240793764e-05,
|
| 134 |
+
"loss": 1.2945,
|
| 135 |
+
"step": 1800
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.006188864603928952,
|
| 139 |
+
"grad_norm": 0.6653416156768799,
|
| 140 |
+
"learning_rate": 4.969217539162131e-05,
|
| 141 |
+
"loss": 1.3004,
|
| 142 |
+
"step": 1900
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.0065145943199252125,
|
| 146 |
+
"grad_norm": 0.732170581817627,
|
| 147 |
+
"learning_rate": 4.9675888375304975e-05,
|
| 148 |
+
"loss": 1.3014,
|
| 149 |
+
"step": 2000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.006840324035921473,
|
| 153 |
+
"grad_norm": 0.405608594417572,
|
| 154 |
+
"learning_rate": 4.965960135898865e-05,
|
| 155 |
+
"loss": 1.2939,
|
| 156 |
+
"step": 2100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.007166053751917733,
|
| 160 |
+
"grad_norm": 0.9849847555160522,
|
| 161 |
+
"learning_rate": 4.9643314342672306e-05,
|
| 162 |
+
"loss": 1.2922,
|
| 163 |
+
"step": 2200
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.007491783467913994,
|
| 167 |
+
"grad_norm": 0.7152832746505737,
|
| 168 |
+
"learning_rate": 4.962702732635598e-05,
|
| 169 |
+
"loss": 1.2905,
|
| 170 |
+
"step": 2300
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.007817513183910255,
|
| 174 |
+
"grad_norm": 1.1164734363555908,
|
| 175 |
+
"learning_rate": 4.9610740310039644e-05,
|
| 176 |
+
"loss": 1.3024,
|
| 177 |
+
"step": 2400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.008143242899906516,
|
| 181 |
+
"grad_norm": 0.574243426322937,
|
| 182 |
+
"learning_rate": 4.959445329372332e-05,
|
| 183 |
+
"loss": 1.2944,
|
| 184 |
+
"step": 2500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.008468972615902777,
|
| 188 |
+
"grad_norm": 0.6976324319839478,
|
| 189 |
+
"learning_rate": 4.9578166277406976e-05,
|
| 190 |
+
"loss": 1.2939,
|
| 191 |
+
"step": 2600
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.008794702331899037,
|
| 195 |
+
"grad_norm": 0.4648737609386444,
|
| 196 |
+
"learning_rate": 4.956187926109064e-05,
|
| 197 |
+
"loss": 1.2841,
|
| 198 |
+
"step": 2700
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.009120432047895297,
|
| 202 |
+
"grad_norm": 1.189271092414856,
|
| 203 |
+
"learning_rate": 4.9545592244774314e-05,
|
| 204 |
+
"loss": 1.294,
|
| 205 |
+
"step": 2800
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.009446161763891557,
|
| 209 |
+
"grad_norm": 0.6437670588493347,
|
| 210 |
+
"learning_rate": 4.952930522845798e-05,
|
| 211 |
+
"loss": 1.2882,
|
| 212 |
+
"step": 2900
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.009771891479887818,
|
| 216 |
+
"grad_norm": 1.591304898262024,
|
| 217 |
+
"learning_rate": 4.9513018212141646e-05,
|
| 218 |
+
"loss": 1.2805,
|
| 219 |
+
"step": 3000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.010097621195884079,
|
| 223 |
+
"grad_norm": 0.2836475670337677,
|
| 224 |
+
"learning_rate": 4.949673119582531e-05,
|
| 225 |
+
"loss": 1.2802,
|
| 226 |
+
"step": 3100
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.01042335091188034,
|
| 230 |
+
"grad_norm": 1.304417610168457,
|
| 231 |
+
"learning_rate": 4.9480444179508984e-05,
|
| 232 |
+
"loss": 1.2833,
|
| 233 |
+
"step": 3200
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.0107490806278766,
|
| 237 |
+
"grad_norm": 0.27579864859580994,
|
| 238 |
+
"learning_rate": 4.946415716319265e-05,
|
| 239 |
+
"loss": 1.2852,
|
| 240 |
+
"step": 3300
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.011074810343872862,
|
| 244 |
+
"grad_norm": 1.1080585718154907,
|
| 245 |
+
"learning_rate": 4.9447870146876315e-05,
|
| 246 |
+
"loss": 1.289,
|
| 247 |
+
"step": 3400
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.011400540059869122,
|
| 251 |
+
"grad_norm": 0.2783690392971039,
|
| 252 |
+
"learning_rate": 4.943158313055998e-05,
|
| 253 |
+
"loss": 1.2885,
|
| 254 |
+
"step": 3500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.011726269775865382,
|
| 258 |
+
"grad_norm": 0.6603112816810608,
|
| 259 |
+
"learning_rate": 4.941529611424365e-05,
|
| 260 |
+
"loss": 1.2882,
|
| 261 |
+
"step": 3600
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.012051999491861642,
|
| 265 |
+
"grad_norm": 0.9498095512390137,
|
| 266 |
+
"learning_rate": 4.939900909792732e-05,
|
| 267 |
+
"loss": 1.2835,
|
| 268 |
+
"step": 3700
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.012377729207857903,
|
| 272 |
+
"grad_norm": 0.5274548530578613,
|
| 273 |
+
"learning_rate": 4.9382722081610985e-05,
|
| 274 |
+
"loss": 1.279,
|
| 275 |
+
"step": 3800
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.012703458923854164,
|
| 279 |
+
"grad_norm": 0.5299821496009827,
|
| 280 |
+
"learning_rate": 4.936643506529465e-05,
|
| 281 |
+
"loss": 1.2879,
|
| 282 |
+
"step": 3900
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.013029188639850425,
|
| 286 |
+
"grad_norm": 1.0898863077163696,
|
| 287 |
+
"learning_rate": 4.9350148048978316e-05,
|
| 288 |
+
"loss": 1.2913,
|
| 289 |
+
"step": 4000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.013354918355846686,
|
| 293 |
+
"grad_norm": 0.6892501711845398,
|
| 294 |
+
"learning_rate": 4.933386103266198e-05,
|
| 295 |
+
"loss": 1.2835,
|
| 296 |
+
"step": 4100
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.013680648071842947,
|
| 300 |
+
"grad_norm": 0.9103847146034241,
|
| 301 |
+
"learning_rate": 4.9317574016345655e-05,
|
| 302 |
+
"loss": 1.2876,
|
| 303 |
+
"step": 4200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.014006377787839207,
|
| 307 |
+
"grad_norm": 0.8750960826873779,
|
| 308 |
+
"learning_rate": 4.9301287000029314e-05,
|
| 309 |
+
"loss": 1.2761,
|
| 310 |
+
"step": 4300
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.014332107503835467,
|
| 314 |
+
"grad_norm": 1.7296843528747559,
|
| 315 |
+
"learning_rate": 4.9284999983712986e-05,
|
| 316 |
+
"loss": 1.2825,
|
| 317 |
+
"step": 4400
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.014657837219831727,
|
| 321 |
+
"grad_norm": 0.7019387483596802,
|
| 322 |
+
"learning_rate": 4.926871296739665e-05,
|
| 323 |
+
"loss": 1.2774,
|
| 324 |
+
"step": 4500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.014983566935827988,
|
| 328 |
+
"grad_norm": 0.9353660345077515,
|
| 329 |
+
"learning_rate": 4.9252425951080324e-05,
|
| 330 |
+
"loss": 1.2701,
|
| 331 |
+
"step": 4600
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.015309296651824249,
|
| 335 |
+
"grad_norm": 0.7081932425498962,
|
| 336 |
+
"learning_rate": 4.923613893476399e-05,
|
| 337 |
+
"loss": 1.276,
|
| 338 |
+
"step": 4700
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.01563502636782051,
|
| 342 |
+
"grad_norm": 0.8366962671279907,
|
| 343 |
+
"learning_rate": 4.9219851918447656e-05,
|
| 344 |
+
"loss": 1.2767,
|
| 345 |
+
"step": 4800
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.01596075608381677,
|
| 349 |
+
"grad_norm": 1.765871286392212,
|
| 350 |
+
"learning_rate": 4.920356490213132e-05,
|
| 351 |
+
"loss": 1.2617,
|
| 352 |
+
"step": 4900
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.01628648579981303,
|
| 356 |
+
"grad_norm": 0.2926379442214966,
|
| 357 |
+
"learning_rate": 4.918727788581499e-05,
|
| 358 |
+
"loss": 1.2762,
|
| 359 |
+
"step": 5000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.01661221551580929,
|
| 363 |
+
"grad_norm": 1.1176525354385376,
|
| 364 |
+
"learning_rate": 4.917099086949866e-05,
|
| 365 |
+
"loss": 1.2647,
|
| 366 |
+
"step": 5100
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.016937945231805553,
|
| 370 |
+
"grad_norm": 0.384264200925827,
|
| 371 |
+
"learning_rate": 4.915470385318232e-05,
|
| 372 |
+
"loss": 1.2628,
|
| 373 |
+
"step": 5200
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.017263674947801812,
|
| 377 |
+
"grad_norm": 1.5339140892028809,
|
| 378 |
+
"learning_rate": 4.913841683686599e-05,
|
| 379 |
+
"loss": 1.2692,
|
| 380 |
+
"step": 5300
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.017589404663798075,
|
| 384 |
+
"grad_norm": 1.2026703357696533,
|
| 385 |
+
"learning_rate": 4.912212982054966e-05,
|
| 386 |
+
"loss": 1.2618,
|
| 387 |
+
"step": 5400
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.017915134379794334,
|
| 391 |
+
"grad_norm": 0.6754997968673706,
|
| 392 |
+
"learning_rate": 4.910584280423333e-05,
|
| 393 |
+
"loss": 1.2495,
|
| 394 |
+
"step": 5500
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.018240864095790593,
|
| 398 |
+
"grad_norm": 0.8240428566932678,
|
| 399 |
+
"learning_rate": 4.908955578791699e-05,
|
| 400 |
+
"loss": 1.2498,
|
| 401 |
+
"step": 5600
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.018566593811786856,
|
| 405 |
+
"grad_norm": 0.6363087892532349,
|
| 406 |
+
"learning_rate": 4.9073268771600654e-05,
|
| 407 |
+
"loss": 1.2514,
|
| 408 |
+
"step": 5700
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.018892323527783115,
|
| 412 |
+
"grad_norm": 1.393833875656128,
|
| 413 |
+
"learning_rate": 4.905698175528433e-05,
|
| 414 |
+
"loss": 1.2509,
|
| 415 |
+
"step": 5800
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.019218053243779377,
|
| 419 |
+
"grad_norm": 0.6422170996665955,
|
| 420 |
+
"learning_rate": 4.904069473896799e-05,
|
| 421 |
+
"loss": 1.2405,
|
| 422 |
+
"step": 5900
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.019543782959775637,
|
| 426 |
+
"grad_norm": 0.7575420141220093,
|
| 427 |
+
"learning_rate": 4.902440772265166e-05,
|
| 428 |
+
"loss": 1.2241,
|
| 429 |
+
"step": 6000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.0198695126757719,
|
| 433 |
+
"grad_norm": 0.7148196697235107,
|
| 434 |
+
"learning_rate": 4.9008120706335324e-05,
|
| 435 |
+
"loss": 1.2372,
|
| 436 |
+
"step": 6100
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.020195242391768158,
|
| 440 |
+
"grad_norm": 1.1207329034805298,
|
| 441 |
+
"learning_rate": 4.8991833690018996e-05,
|
| 442 |
+
"loss": 1.2372,
|
| 443 |
+
"step": 6200
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.02052097210776442,
|
| 447 |
+
"grad_norm": 1.3915568590164185,
|
| 448 |
+
"learning_rate": 4.897554667370266e-05,
|
| 449 |
+
"loss": 1.2129,
|
| 450 |
+
"step": 6300
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.02084670182376068,
|
| 454 |
+
"grad_norm": 0.8674553036689758,
|
| 455 |
+
"learning_rate": 4.895925965738633e-05,
|
| 456 |
+
"loss": 1.2262,
|
| 457 |
+
"step": 6400
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.02117243153975694,
|
| 461 |
+
"grad_norm": 0.7640644311904907,
|
| 462 |
+
"learning_rate": 4.8942972641069994e-05,
|
| 463 |
+
"loss": 1.1998,
|
| 464 |
+
"step": 6500
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.0214981612557532,
|
| 468 |
+
"grad_norm": 0.7928606271743774,
|
| 469 |
+
"learning_rate": 4.892668562475366e-05,
|
| 470 |
+
"loss": 1.1776,
|
| 471 |
+
"step": 6600
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.02182389097174946,
|
| 475 |
+
"grad_norm": 1.1644946336746216,
|
| 476 |
+
"learning_rate": 4.891039860843733e-05,
|
| 477 |
+
"loss": 1.1916,
|
| 478 |
+
"step": 6700
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.022149620687745723,
|
| 482 |
+
"grad_norm": 1.1310213804244995,
|
| 483 |
+
"learning_rate": 4.8894111592121e-05,
|
| 484 |
+
"loss": 1.1786,
|
| 485 |
+
"step": 6800
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.022475350403741982,
|
| 489 |
+
"grad_norm": 1.3858141899108887,
|
| 490 |
+
"learning_rate": 4.887782457580466e-05,
|
| 491 |
+
"loss": 1.1728,
|
| 492 |
+
"step": 6900
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.022801080119738245,
|
| 496 |
+
"grad_norm": 3.814767360687256,
|
| 497 |
+
"learning_rate": 4.886153755948833e-05,
|
| 498 |
+
"loss": 1.1384,
|
| 499 |
+
"step": 7000
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.023126809835734504,
|
| 503 |
+
"grad_norm": 1.2411885261535645,
|
| 504 |
+
"learning_rate": 4.8845250543171995e-05,
|
| 505 |
+
"loss": 1.1588,
|
| 506 |
+
"step": 7100
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.023452539551730763,
|
| 510 |
+
"grad_norm": 1.4492881298065186,
|
| 511 |
+
"learning_rate": 4.882896352685567e-05,
|
| 512 |
+
"loss": 1.1266,
|
| 513 |
+
"step": 7200
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.023778269267727026,
|
| 517 |
+
"grad_norm": 0.8389878869056702,
|
| 518 |
+
"learning_rate": 4.8812676510539326e-05,
|
| 519 |
+
"loss": 1.1446,
|
| 520 |
+
"step": 7300
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.024103998983723285,
|
| 524 |
+
"grad_norm": 0.33955487608909607,
|
| 525 |
+
"learning_rate": 4.8796389494223e-05,
|
| 526 |
+
"loss": 1.1111,
|
| 527 |
+
"step": 7400
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.024429728699719547,
|
| 531 |
+
"grad_norm": 0.7004753351211548,
|
| 532 |
+
"learning_rate": 4.8780102477906664e-05,
|
| 533 |
+
"loss": 1.0954,
|
| 534 |
+
"step": 7500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.024755458415715807,
|
| 538 |
+
"grad_norm": 0.7213209271430969,
|
| 539 |
+
"learning_rate": 4.876381546159034e-05,
|
| 540 |
+
"loss": 1.1123,
|
| 541 |
+
"step": 7600
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.02508118813171207,
|
| 545 |
+
"grad_norm": 0.960991382598877,
|
| 546 |
+
"learning_rate": 4.8747528445273996e-05,
|
| 547 |
+
"loss": 1.0982,
|
| 548 |
+
"step": 7700
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.025406917847708328,
|
| 552 |
+
"grad_norm": 0.6955804228782654,
|
| 553 |
+
"learning_rate": 4.873124142895766e-05,
|
| 554 |
+
"loss": 1.0827,
|
| 555 |
+
"step": 7800
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.02573264756370459,
|
| 559 |
+
"grad_norm": 0.47498619556427,
|
| 560 |
+
"learning_rate": 4.8714954412641334e-05,
|
| 561 |
+
"loss": 1.1043,
|
| 562 |
+
"step": 7900
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.02605837727970085,
|
| 566 |
+
"grad_norm": 0.304063618183136,
|
| 567 |
+
"learning_rate": 4.8698667396325e-05,
|
| 568 |
+
"loss": 1.0699,
|
| 569 |
+
"step": 8000
|
| 570 |
+
}
|
| 571 |
+
],
|
| 572 |
+
"logging_steps": 100,
|
| 573 |
+
"max_steps": 307003,
|
| 574 |
+
"num_input_tokens_seen": 0,
|
| 575 |
+
"num_train_epochs": 1,
|
| 576 |
+
"save_steps": 500,
|
| 577 |
+
"stateful_callbacks": {
|
| 578 |
+
"TrainerControl": {
|
| 579 |
+
"args": {
|
| 580 |
+
"should_epoch_stop": false,
|
| 581 |
+
"should_evaluate": false,
|
| 582 |
+
"should_log": false,
|
| 583 |
+
"should_save": true,
|
| 584 |
+
"should_training_stop": false
|
| 585 |
+
},
|
| 586 |
+
"attributes": {}
|
| 587 |
+
}
|
| 588 |
+
},
|
| 589 |
+
"total_flos": 1.18876910125056e+17,
|
| 590 |
+
"train_batch_size": 4,
|
| 591 |
+
"trial_name": null,
|
| 592 |
+
"trial_params": null
|
| 593 |
+
}
|
checkpoint-8000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1be2d5594a22f4bff72c544c78dc0a47a5bb1e2a1e204a42972561dc45351391
|
| 3 |
+
size 5176
|