Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- checkpoint-1000/config.json +32 -0
- checkpoint-1000/generation_config.json +7 -0
- checkpoint-1000/model.safetensors +3 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/rng_state_0.pth +3 -0
- checkpoint-1000/rng_state_1.pth +3 -0
- checkpoint-1000/rng_state_2.pth +3 -0
- checkpoint-1000/rng_state_3.pth +3 -0
- checkpoint-1000/rng_state_4.pth +3 -0
- checkpoint-1000/rng_state_5.pth +3 -0
- checkpoint-1000/rng_state_6.pth +3 -0
- checkpoint-1000/rng_state_7.pth +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/special_tokens_map.json +24 -0
- checkpoint-1000/tokenizer.json +0 -0
- checkpoint-1000/tokenizer_config.json +214 -0
- checkpoint-1000/trainer_state.json +110 -0
- checkpoint-1000/training_args.bin +3 -0
- checkpoint-10000/config.json +32 -0
- checkpoint-10000/generation_config.json +7 -0
- checkpoint-10000/model.safetensors +3 -0
- checkpoint-10000/optimizer.pt +3 -0
- checkpoint-10000/rng_state_0.pth +3 -0
- checkpoint-10000/rng_state_1.pth +3 -0
- checkpoint-10000/rng_state_2.pth +3 -0
- checkpoint-10000/rng_state_3.pth +3 -0
- checkpoint-10000/rng_state_4.pth +3 -0
- checkpoint-10000/rng_state_5.pth +3 -0
- checkpoint-10000/rng_state_6.pth +3 -0
- checkpoint-10000/rng_state_7.pth +3 -0
- checkpoint-10000/scheduler.pt +3 -0
- checkpoint-10000/special_tokens_map.json +24 -0
- checkpoint-10000/tokenizer.json +0 -0
- checkpoint-10000/tokenizer_config.json +214 -0
- checkpoint-10000/trainer_state.json +740 -0
- checkpoint-10000/training_args.bin +3 -0
- checkpoint-100000/config.json +32 -0
- checkpoint-100000/generation_config.json +7 -0
- checkpoint-100000/model.safetensors +3 -0
- checkpoint-100000/optimizer.pt +3 -0
- checkpoint-100000/rng_state_0.pth +3 -0
- checkpoint-100000/rng_state_1.pth +3 -0
- checkpoint-100000/rng_state_2.pth +3 -0
- checkpoint-100000/rng_state_3.pth +3 -0
- checkpoint-100000/rng_state_4.pth +3 -0
- checkpoint-100000/rng_state_5.pth +3 -0
- checkpoint-100000/rng_state_6.pth +3 -0
- checkpoint-100000/rng_state_7.pth +3 -0
- checkpoint-100000/scheduler.pt +3 -0
- checkpoint-100000/special_tokens_map.json +24 -0
checkpoint-1000/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "EleutherAI/pythia-14m",
|
| 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": 128,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 512,
|
| 16 |
+
"layer_norm_eps": 1e-05,
|
| 17 |
+
"max_position_embeddings": 2048,
|
| 18 |
+
"model_type": "gpt_neox",
|
| 19 |
+
"num_attention_heads": 4,
|
| 20 |
+
"num_hidden_layers": 6,
|
| 21 |
+
"partial_rotary_factor": 0.25,
|
| 22 |
+
"rope_scaling": null,
|
| 23 |
+
"rope_theta": 10000,
|
| 24 |
+
"rotary_emb_base": 10000,
|
| 25 |
+
"rotary_pct": 0.25,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.45.2",
|
| 29 |
+
"use_cache": false,
|
| 30 |
+
"use_parallel_residual": true,
|
| 31 |
+
"vocab_size": 50304
|
| 32 |
+
}
|
checkpoint-1000/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"transformers_version": "4.45.2",
|
| 6 |
+
"use_cache": false
|
| 7 |
+
}
|
checkpoint-1000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:638d03da1db382b44f2350d86858b78e81ed954c6e0c6044d5be9c2e6a37b4ea
|
| 3 |
+
size 56279344
|
checkpoint-1000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef85159f1d30dfa3094212aebace3966606a5a9aa0cc5abb4ae66ba5a37de000
|
| 3 |
+
size 112605707
|
checkpoint-1000/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff83006d85c789a73e3d5962b60a1ea20ea38374ebe54f6d5e8a5c5777efbb05
|
| 3 |
+
size 16325
|
checkpoint-1000/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4405d2b9aa7065e98bf1b965702b69709bef30d31b3257e2445623659424edc
|
| 3 |
+
size 16325
|
checkpoint-1000/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d63c51a9642e331eb3ab07696e2e11c88c29f4f34cf4f99f8ffa4fb55af453b
|
| 3 |
+
size 16325
|
checkpoint-1000/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba4e5ea853aa4898edd412a4da34a96b758f0f7218655949614277cb1910eb31
|
| 3 |
+
size 16325
|
checkpoint-1000/rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:481092ba472bbb5b59655c5d961d7f139eda9daf3bb24d9d6f7ef405894f2153
|
| 3 |
+
size 16325
|
checkpoint-1000/rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93e9df5970151da7ccada8e10c311cc4a6237c90a1701b6a5187bce10af76bd8
|
| 3 |
+
size 16325
|
checkpoint-1000/rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56e3382b0cee8a47b032dacb4635c6434a00b08b20843e7882b8fafa689b2bf0
|
| 3 |
+
size 16325
|
checkpoint-1000/rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e71863697b5311ef5c1666e4a06796a8f027fab8efa2dfff79a823e493506448
|
| 3 |
+
size 16325
|
checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5b05955bb197697f5a716e4c344035e12a4a81599fd3ab5b82077b37e185f6c
|
| 3 |
+
size 1465
|
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 |
+
}
|
checkpoint-1000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,214 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": false,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<|endoftext|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<|padding|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"50254": {
|
| 23 |
+
"content": " ",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"50255": {
|
| 31 |
+
"content": " ",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
},
|
| 38 |
+
"50256": {
|
| 39 |
+
"content": " ",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"50257": {
|
| 47 |
+
"content": " ",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": true,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"50258": {
|
| 55 |
+
"content": " ",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"50259": {
|
| 63 |
+
"content": " ",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": true,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"50260": {
|
| 71 |
+
"content": " ",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": true,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"50261": {
|
| 79 |
+
"content": " ",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": true,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
+
},
|
| 86 |
+
"50262": {
|
| 87 |
+
"content": " ",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": true,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": false
|
| 93 |
+
},
|
| 94 |
+
"50263": {
|
| 95 |
+
"content": " ",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": true,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"50264": {
|
| 103 |
+
"content": " ",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": true,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"50265": {
|
| 111 |
+
"content": " ",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": true,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": false
|
| 117 |
+
},
|
| 118 |
+
"50266": {
|
| 119 |
+
"content": " ",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": true,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
},
|
| 126 |
+
"50267": {
|
| 127 |
+
"content": " ",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": true,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"50268": {
|
| 135 |
+
"content": " ",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": true,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"50269": {
|
| 143 |
+
"content": " ",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": true,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"50270": {
|
| 151 |
+
"content": " ",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"50271": {
|
| 159 |
+
"content": " ",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": true,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"50272": {
|
| 167 |
+
"content": " ",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": true,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"50273": {
|
| 175 |
+
"content": " ",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": true,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": false
|
| 181 |
+
},
|
| 182 |
+
"50274": {
|
| 183 |
+
"content": " ",
|
| 184 |
+
"lstrip": false,
|
| 185 |
+
"normalized": true,
|
| 186 |
+
"rstrip": false,
|
| 187 |
+
"single_word": false,
|
| 188 |
+
"special": false
|
| 189 |
+
},
|
| 190 |
+
"50275": {
|
| 191 |
+
"content": " ",
|
| 192 |
+
"lstrip": false,
|
| 193 |
+
"normalized": true,
|
| 194 |
+
"rstrip": false,
|
| 195 |
+
"single_word": false,
|
| 196 |
+
"special": false
|
| 197 |
+
},
|
| 198 |
+
"50276": {
|
| 199 |
+
"content": " ",
|
| 200 |
+
"lstrip": false,
|
| 201 |
+
"normalized": true,
|
| 202 |
+
"rstrip": false,
|
| 203 |
+
"single_word": false,
|
| 204 |
+
"special": false
|
| 205 |
+
}
|
| 206 |
+
},
|
| 207 |
+
"bos_token": "<|endoftext|>",
|
| 208 |
+
"clean_up_tokenization_spaces": true,
|
| 209 |
+
"eos_token": "<|endoftext|>",
|
| 210 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 211 |
+
"pad_token": "<|endoftext|>",
|
| 212 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
| 213 |
+
"unk_token": "<|endoftext|>"
|
| 214 |
+
}
|
checkpoint-1000/trainer_state.json
ADDED
|
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.03999840006399744,
|
| 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": 3.999840006399744e-05,
|
| 13 |
+
"grad_norm": 1.4777933359146118,
|
| 14 |
+
"learning_rate": 0.001,
|
| 15 |
+
"loss": 10.8399,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.003999840006399744,
|
| 20 |
+
"grad_norm": 0.22688856720924377,
|
| 21 |
+
"learning_rate": 0.001,
|
| 22 |
+
"loss": 7.558,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.007999680012799487,
|
| 27 |
+
"grad_norm": 0.24372541904449463,
|
| 28 |
+
"learning_rate": 0.001,
|
| 29 |
+
"loss": 6.3052,
|
| 30 |
+
"step": 200
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.011999520019199232,
|
| 34 |
+
"grad_norm": 0.5153403282165527,
|
| 35 |
+
"learning_rate": 0.001,
|
| 36 |
+
"loss": 5.9045,
|
| 37 |
+
"step": 300
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.015999360025598975,
|
| 41 |
+
"grad_norm": 0.5177266597747803,
|
| 42 |
+
"learning_rate": 0.001,
|
| 43 |
+
"loss": 5.6063,
|
| 44 |
+
"step": 400
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.01999920003199872,
|
| 48 |
+
"grad_norm": 0.6018334627151489,
|
| 49 |
+
"learning_rate": 0.001,
|
| 50 |
+
"loss": 5.4024,
|
| 51 |
+
"step": 500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.023999040038398464,
|
| 55 |
+
"grad_norm": 0.4220522940158844,
|
| 56 |
+
"learning_rate": 0.001,
|
| 57 |
+
"loss": 5.2604,
|
| 58 |
+
"step": 600
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.027998880044798207,
|
| 62 |
+
"grad_norm": 0.4826813042163849,
|
| 63 |
+
"learning_rate": 0.001,
|
| 64 |
+
"loss": 5.149,
|
| 65 |
+
"step": 700
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.03199872005119795,
|
| 69 |
+
"grad_norm": 0.5880510807037354,
|
| 70 |
+
"learning_rate": 0.001,
|
| 71 |
+
"loss": 5.0663,
|
| 72 |
+
"step": 800
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.035998560057597696,
|
| 76 |
+
"grad_norm": 0.4875524640083313,
|
| 77 |
+
"learning_rate": 0.001,
|
| 78 |
+
"loss": 5.0008,
|
| 79 |
+
"step": 900
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.03999840006399744,
|
| 83 |
+
"grad_norm": 0.526023805141449,
|
| 84 |
+
"learning_rate": 0.001,
|
| 85 |
+
"loss": 4.9403,
|
| 86 |
+
"step": 1000
|
| 87 |
+
}
|
| 88 |
+
],
|
| 89 |
+
"logging_steps": 100,
|
| 90 |
+
"max_steps": 150000,
|
| 91 |
+
"num_input_tokens_seen": 0,
|
| 92 |
+
"num_train_epochs": 6,
|
| 93 |
+
"save_steps": 500,
|
| 94 |
+
"stateful_callbacks": {
|
| 95 |
+
"TrainerControl": {
|
| 96 |
+
"args": {
|
| 97 |
+
"should_epoch_stop": false,
|
| 98 |
+
"should_evaluate": false,
|
| 99 |
+
"should_log": false,
|
| 100 |
+
"should_save": true,
|
| 101 |
+
"should_training_stop": false
|
| 102 |
+
},
|
| 103 |
+
"attributes": {}
|
| 104 |
+
}
|
| 105 |
+
},
|
| 106 |
+
"total_flos": 2.39981297664e+16,
|
| 107 |
+
"train_batch_size": 64,
|
| 108 |
+
"trial_name": null,
|
| 109 |
+
"trial_params": null
|
| 110 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b573a96e19aa9061cdc1bcf783263829ca1386cefdf168bd82b7d605ad2594ec
|
| 3 |
+
size 5649
|
checkpoint-10000/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "EleutherAI/pythia-14m",
|
| 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": 128,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 512,
|
| 16 |
+
"layer_norm_eps": 1e-05,
|
| 17 |
+
"max_position_embeddings": 2048,
|
| 18 |
+
"model_type": "gpt_neox",
|
| 19 |
+
"num_attention_heads": 4,
|
| 20 |
+
"num_hidden_layers": 6,
|
| 21 |
+
"partial_rotary_factor": 0.25,
|
| 22 |
+
"rope_scaling": null,
|
| 23 |
+
"rope_theta": 10000,
|
| 24 |
+
"rotary_emb_base": 10000,
|
| 25 |
+
"rotary_pct": 0.25,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.45.2",
|
| 29 |
+
"use_cache": false,
|
| 30 |
+
"use_parallel_residual": true,
|
| 31 |
+
"vocab_size": 50304
|
| 32 |
+
}
|
checkpoint-10000/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"transformers_version": "4.45.2",
|
| 6 |
+
"use_cache": false
|
| 7 |
+
}
|
checkpoint-10000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1ba695e4e6f44c1c0039e6216a4d1b76d0b985b30ea80db415612ae547d6a44
|
| 3 |
+
size 56279344
|
checkpoint-10000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b1444ba3096ae4e5476e2001d41a571ada2256016444f62e6954c0ef46f5798
|
| 3 |
+
size 112605707
|
checkpoint-10000/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff83006d85c789a73e3d5962b60a1ea20ea38374ebe54f6d5e8a5c5777efbb05
|
| 3 |
+
size 16325
|
checkpoint-10000/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4405d2b9aa7065e98bf1b965702b69709bef30d31b3257e2445623659424edc
|
| 3 |
+
size 16325
|
checkpoint-10000/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d63c51a9642e331eb3ab07696e2e11c88c29f4f34cf4f99f8ffa4fb55af453b
|
| 3 |
+
size 16325
|
checkpoint-10000/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba4e5ea853aa4898edd412a4da34a96b758f0f7218655949614277cb1910eb31
|
| 3 |
+
size 16325
|
checkpoint-10000/rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:481092ba472bbb5b59655c5d961d7f139eda9daf3bb24d9d6f7ef405894f2153
|
| 3 |
+
size 16325
|
checkpoint-10000/rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93e9df5970151da7ccada8e10c311cc4a6237c90a1701b6a5187bce10af76bd8
|
| 3 |
+
size 16325
|
checkpoint-10000/rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56e3382b0cee8a47b032dacb4635c6434a00b08b20843e7882b8fafa689b2bf0
|
| 3 |
+
size 16325
|
checkpoint-10000/rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e71863697b5311ef5c1666e4a06796a8f027fab8efa2dfff79a823e493506448
|
| 3 |
+
size 16325
|
checkpoint-10000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a70183c36c2f7607bce16c3b85fa32b96b09ecfb511ff7236bc48e687d6b1c7
|
| 3 |
+
size 1465
|
checkpoint-10000/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 |
+
}
|
checkpoint-10000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-10000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,214 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": false,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<|endoftext|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<|padding|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"50254": {
|
| 23 |
+
"content": " ",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"50255": {
|
| 31 |
+
"content": " ",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
},
|
| 38 |
+
"50256": {
|
| 39 |
+
"content": " ",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"50257": {
|
| 47 |
+
"content": " ",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": true,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"50258": {
|
| 55 |
+
"content": " ",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"50259": {
|
| 63 |
+
"content": " ",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": true,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"50260": {
|
| 71 |
+
"content": " ",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": true,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"50261": {
|
| 79 |
+
"content": " ",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": true,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
+
},
|
| 86 |
+
"50262": {
|
| 87 |
+
"content": " ",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": true,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": false
|
| 93 |
+
},
|
| 94 |
+
"50263": {
|
| 95 |
+
"content": " ",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": true,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"50264": {
|
| 103 |
+
"content": " ",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": true,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"50265": {
|
| 111 |
+
"content": " ",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": true,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": false
|
| 117 |
+
},
|
| 118 |
+
"50266": {
|
| 119 |
+
"content": " ",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": true,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
},
|
| 126 |
+
"50267": {
|
| 127 |
+
"content": " ",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": true,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"50268": {
|
| 135 |
+
"content": " ",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": true,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"50269": {
|
| 143 |
+
"content": " ",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": true,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"50270": {
|
| 151 |
+
"content": " ",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"50271": {
|
| 159 |
+
"content": " ",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": true,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"50272": {
|
| 167 |
+
"content": " ",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": true,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"50273": {
|
| 175 |
+
"content": " ",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": true,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": false
|
| 181 |
+
},
|
| 182 |
+
"50274": {
|
| 183 |
+
"content": " ",
|
| 184 |
+
"lstrip": false,
|
| 185 |
+
"normalized": true,
|
| 186 |
+
"rstrip": false,
|
| 187 |
+
"single_word": false,
|
| 188 |
+
"special": false
|
| 189 |
+
},
|
| 190 |
+
"50275": {
|
| 191 |
+
"content": " ",
|
| 192 |
+
"lstrip": false,
|
| 193 |
+
"normalized": true,
|
| 194 |
+
"rstrip": false,
|
| 195 |
+
"single_word": false,
|
| 196 |
+
"special": false
|
| 197 |
+
},
|
| 198 |
+
"50276": {
|
| 199 |
+
"content": " ",
|
| 200 |
+
"lstrip": false,
|
| 201 |
+
"normalized": true,
|
| 202 |
+
"rstrip": false,
|
| 203 |
+
"single_word": false,
|
| 204 |
+
"special": false
|
| 205 |
+
}
|
| 206 |
+
},
|
| 207 |
+
"bos_token": "<|endoftext|>",
|
| 208 |
+
"clean_up_tokenization_spaces": true,
|
| 209 |
+
"eos_token": "<|endoftext|>",
|
| 210 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 211 |
+
"pad_token": "<|endoftext|>",
|
| 212 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
| 213 |
+
"unk_token": "<|endoftext|>"
|
| 214 |
+
}
|
checkpoint-10000/trainer_state.json
ADDED
|
@@ -0,0 +1,740 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.3999840006399744,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 10000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 3.999840006399744e-05,
|
| 13 |
+
"grad_norm": 1.4777933359146118,
|
| 14 |
+
"learning_rate": 0.001,
|
| 15 |
+
"loss": 10.8399,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.003999840006399744,
|
| 20 |
+
"grad_norm": 0.22688856720924377,
|
| 21 |
+
"learning_rate": 0.001,
|
| 22 |
+
"loss": 7.558,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.007999680012799487,
|
| 27 |
+
"grad_norm": 0.24372541904449463,
|
| 28 |
+
"learning_rate": 0.001,
|
| 29 |
+
"loss": 6.3052,
|
| 30 |
+
"step": 200
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.011999520019199232,
|
| 34 |
+
"grad_norm": 0.5153403282165527,
|
| 35 |
+
"learning_rate": 0.001,
|
| 36 |
+
"loss": 5.9045,
|
| 37 |
+
"step": 300
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.015999360025598975,
|
| 41 |
+
"grad_norm": 0.5177266597747803,
|
| 42 |
+
"learning_rate": 0.001,
|
| 43 |
+
"loss": 5.6063,
|
| 44 |
+
"step": 400
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.01999920003199872,
|
| 48 |
+
"grad_norm": 0.6018334627151489,
|
| 49 |
+
"learning_rate": 0.001,
|
| 50 |
+
"loss": 5.4024,
|
| 51 |
+
"step": 500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.023999040038398464,
|
| 55 |
+
"grad_norm": 0.4220522940158844,
|
| 56 |
+
"learning_rate": 0.001,
|
| 57 |
+
"loss": 5.2604,
|
| 58 |
+
"step": 600
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.027998880044798207,
|
| 62 |
+
"grad_norm": 0.4826813042163849,
|
| 63 |
+
"learning_rate": 0.001,
|
| 64 |
+
"loss": 5.149,
|
| 65 |
+
"step": 700
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.03199872005119795,
|
| 69 |
+
"grad_norm": 0.5880510807037354,
|
| 70 |
+
"learning_rate": 0.001,
|
| 71 |
+
"loss": 5.0663,
|
| 72 |
+
"step": 800
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.035998560057597696,
|
| 76 |
+
"grad_norm": 0.4875524640083313,
|
| 77 |
+
"learning_rate": 0.001,
|
| 78 |
+
"loss": 5.0008,
|
| 79 |
+
"step": 900
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.03999840006399744,
|
| 83 |
+
"grad_norm": 0.526023805141449,
|
| 84 |
+
"learning_rate": 0.001,
|
| 85 |
+
"loss": 4.9403,
|
| 86 |
+
"step": 1000
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.04399824007039718,
|
| 90 |
+
"grad_norm": 0.4925878942012787,
|
| 91 |
+
"learning_rate": 0.001,
|
| 92 |
+
"loss": 4.8988,
|
| 93 |
+
"step": 1100
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.04799808007679693,
|
| 97 |
+
"grad_norm": 0.5051125884056091,
|
| 98 |
+
"learning_rate": 0.001,
|
| 99 |
+
"loss": 4.8552,
|
| 100 |
+
"step": 1200
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.051997920083196675,
|
| 104 |
+
"grad_norm": 0.6583888530731201,
|
| 105 |
+
"learning_rate": 0.001,
|
| 106 |
+
"loss": 4.8247,
|
| 107 |
+
"step": 1300
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.055997760089596414,
|
| 111 |
+
"grad_norm": 0.4777211546897888,
|
| 112 |
+
"learning_rate": 0.001,
|
| 113 |
+
"loss": 4.7899,
|
| 114 |
+
"step": 1400
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.05999760009599616,
|
| 118 |
+
"grad_norm": 0.5130186080932617,
|
| 119 |
+
"learning_rate": 0.001,
|
| 120 |
+
"loss": 4.7612,
|
| 121 |
+
"step": 1500
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.0639974401023959,
|
| 125 |
+
"grad_norm": 0.5315548777580261,
|
| 126 |
+
"learning_rate": 0.001,
|
| 127 |
+
"loss": 4.7361,
|
| 128 |
+
"step": 1600
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.06799728010879565,
|
| 132 |
+
"grad_norm": 0.47726863622665405,
|
| 133 |
+
"learning_rate": 0.001,
|
| 134 |
+
"loss": 4.7013,
|
| 135 |
+
"step": 1700
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.07199712011519539,
|
| 139 |
+
"grad_norm": 0.5642004013061523,
|
| 140 |
+
"learning_rate": 0.001,
|
| 141 |
+
"loss": 4.6645,
|
| 142 |
+
"step": 1800
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.07599696012159514,
|
| 146 |
+
"grad_norm": 0.545949399471283,
|
| 147 |
+
"learning_rate": 0.001,
|
| 148 |
+
"loss": 4.6219,
|
| 149 |
+
"step": 1900
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.07999680012799489,
|
| 153 |
+
"grad_norm": 0.5206509232521057,
|
| 154 |
+
"learning_rate": 0.001,
|
| 155 |
+
"loss": 4.5969,
|
| 156 |
+
"step": 2000
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.08399664013439462,
|
| 160 |
+
"grad_norm": 0.44842126965522766,
|
| 161 |
+
"learning_rate": 0.001,
|
| 162 |
+
"loss": 4.5708,
|
| 163 |
+
"step": 2100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.08799648014079436,
|
| 167 |
+
"grad_norm": 0.6365007162094116,
|
| 168 |
+
"learning_rate": 0.001,
|
| 169 |
+
"loss": 4.5523,
|
| 170 |
+
"step": 2200
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.09199632014719411,
|
| 174 |
+
"grad_norm": 0.5729643702507019,
|
| 175 |
+
"learning_rate": 0.001,
|
| 176 |
+
"loss": 4.5305,
|
| 177 |
+
"step": 2300
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.09599616015359386,
|
| 181 |
+
"grad_norm": 0.5888395309448242,
|
| 182 |
+
"learning_rate": 0.001,
|
| 183 |
+
"loss": 4.5189,
|
| 184 |
+
"step": 2400
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.0999960001599936,
|
| 188 |
+
"grad_norm": 0.6099081039428711,
|
| 189 |
+
"learning_rate": 0.001,
|
| 190 |
+
"loss": 4.5038,
|
| 191 |
+
"step": 2500
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.10399584016639335,
|
| 195 |
+
"grad_norm": 0.5354722738265991,
|
| 196 |
+
"learning_rate": 0.001,
|
| 197 |
+
"loss": 4.487,
|
| 198 |
+
"step": 2600
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.10799568017279308,
|
| 202 |
+
"grad_norm": 0.6929482221603394,
|
| 203 |
+
"learning_rate": 0.001,
|
| 204 |
+
"loss": 4.4784,
|
| 205 |
+
"step": 2700
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.11199552017919283,
|
| 209 |
+
"grad_norm": 0.5511060357093811,
|
| 210 |
+
"learning_rate": 0.001,
|
| 211 |
+
"loss": 4.4682,
|
| 212 |
+
"step": 2800
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.11599536018559257,
|
| 216 |
+
"grad_norm": 0.5773873329162598,
|
| 217 |
+
"learning_rate": 0.001,
|
| 218 |
+
"loss": 4.4589,
|
| 219 |
+
"step": 2900
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.11999520019199232,
|
| 223 |
+
"grad_norm": 0.6061297655105591,
|
| 224 |
+
"learning_rate": 0.001,
|
| 225 |
+
"loss": 4.452,
|
| 226 |
+
"step": 3000
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.12399504019839207,
|
| 230 |
+
"grad_norm": 0.6082037687301636,
|
| 231 |
+
"learning_rate": 0.001,
|
| 232 |
+
"loss": 4.443,
|
| 233 |
+
"step": 3100
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.1279948802047918,
|
| 237 |
+
"grad_norm": 0.5562213063240051,
|
| 238 |
+
"learning_rate": 0.001,
|
| 239 |
+
"loss": 4.4342,
|
| 240 |
+
"step": 3200
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.13199472021119155,
|
| 244 |
+
"grad_norm": 0.5706282258033752,
|
| 245 |
+
"learning_rate": 0.001,
|
| 246 |
+
"loss": 4.4281,
|
| 247 |
+
"step": 3300
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.1359945602175913,
|
| 251 |
+
"grad_norm": 0.6546366810798645,
|
| 252 |
+
"learning_rate": 0.001,
|
| 253 |
+
"loss": 4.4192,
|
| 254 |
+
"step": 3400
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.13999440022399104,
|
| 258 |
+
"grad_norm": 0.5441614389419556,
|
| 259 |
+
"learning_rate": 0.001,
|
| 260 |
+
"loss": 4.4157,
|
| 261 |
+
"step": 3500
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.14399424023039079,
|
| 265 |
+
"grad_norm": 0.547122061252594,
|
| 266 |
+
"learning_rate": 0.001,
|
| 267 |
+
"loss": 4.4079,
|
| 268 |
+
"step": 3600
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.14799408023679053,
|
| 272 |
+
"grad_norm": 0.520165741443634,
|
| 273 |
+
"learning_rate": 0.001,
|
| 274 |
+
"loss": 4.4047,
|
| 275 |
+
"step": 3700
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.15199392024319028,
|
| 279 |
+
"grad_norm": 0.529140293598175,
|
| 280 |
+
"learning_rate": 0.001,
|
| 281 |
+
"loss": 4.3997,
|
| 282 |
+
"step": 3800
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.15599376024959002,
|
| 286 |
+
"grad_norm": 0.5902653336524963,
|
| 287 |
+
"learning_rate": 0.001,
|
| 288 |
+
"loss": 4.3921,
|
| 289 |
+
"step": 3900
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.15999360025598977,
|
| 293 |
+
"grad_norm": 0.6136724948883057,
|
| 294 |
+
"learning_rate": 0.001,
|
| 295 |
+
"loss": 4.3877,
|
| 296 |
+
"step": 4000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.16399344026238952,
|
| 300 |
+
"grad_norm": 0.5538173913955688,
|
| 301 |
+
"learning_rate": 0.001,
|
| 302 |
+
"loss": 4.383,
|
| 303 |
+
"step": 4100
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.16799328026878924,
|
| 307 |
+
"grad_norm": 0.5516422986984253,
|
| 308 |
+
"learning_rate": 0.001,
|
| 309 |
+
"loss": 4.3815,
|
| 310 |
+
"step": 4200
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.17199312027518898,
|
| 314 |
+
"grad_norm": 0.535236656665802,
|
| 315 |
+
"learning_rate": 0.001,
|
| 316 |
+
"loss": 4.375,
|
| 317 |
+
"step": 4300
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.17599296028158873,
|
| 321 |
+
"grad_norm": 0.5214977860450745,
|
| 322 |
+
"learning_rate": 0.001,
|
| 323 |
+
"loss": 4.3716,
|
| 324 |
+
"step": 4400
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.17999280028798847,
|
| 328 |
+
"grad_norm": 0.473036527633667,
|
| 329 |
+
"learning_rate": 0.001,
|
| 330 |
+
"loss": 4.3679,
|
| 331 |
+
"step": 4500
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.18399264029438822,
|
| 335 |
+
"grad_norm": 0.5115819573402405,
|
| 336 |
+
"learning_rate": 0.001,
|
| 337 |
+
"loss": 4.3661,
|
| 338 |
+
"step": 4600
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.18799248030078797,
|
| 342 |
+
"grad_norm": 0.5074037313461304,
|
| 343 |
+
"learning_rate": 0.001,
|
| 344 |
+
"loss": 4.3606,
|
| 345 |
+
"step": 4700
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.1919923203071877,
|
| 349 |
+
"grad_norm": 0.4992203116416931,
|
| 350 |
+
"learning_rate": 0.001,
|
| 351 |
+
"loss": 4.3579,
|
| 352 |
+
"step": 4800
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.19599216031358746,
|
| 356 |
+
"grad_norm": 0.5755491256713867,
|
| 357 |
+
"learning_rate": 0.001,
|
| 358 |
+
"loss": 4.3501,
|
| 359 |
+
"step": 4900
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.1999920003199872,
|
| 363 |
+
"grad_norm": 0.5061823725700378,
|
| 364 |
+
"learning_rate": 0.001,
|
| 365 |
+
"loss": 4.3486,
|
| 366 |
+
"step": 5000
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.20399184032638695,
|
| 370 |
+
"grad_norm": 0.5323928594589233,
|
| 371 |
+
"learning_rate": 0.001,
|
| 372 |
+
"loss": 4.3477,
|
| 373 |
+
"step": 5100
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.2079916803327867,
|
| 377 |
+
"grad_norm": 0.5301046967506409,
|
| 378 |
+
"learning_rate": 0.001,
|
| 379 |
+
"loss": 4.3411,
|
| 380 |
+
"step": 5200
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.21199152033918645,
|
| 384 |
+
"grad_norm": 0.563123345375061,
|
| 385 |
+
"learning_rate": 0.001,
|
| 386 |
+
"loss": 4.3405,
|
| 387 |
+
"step": 5300
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.21599136034558616,
|
| 391 |
+
"grad_norm": 0.4736695885658264,
|
| 392 |
+
"learning_rate": 0.001,
|
| 393 |
+
"loss": 4.3391,
|
| 394 |
+
"step": 5400
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.2199912003519859,
|
| 398 |
+
"grad_norm": 0.46568775177001953,
|
| 399 |
+
"learning_rate": 0.001,
|
| 400 |
+
"loss": 4.3372,
|
| 401 |
+
"step": 5500
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.22399104035838566,
|
| 405 |
+
"grad_norm": 0.591935396194458,
|
| 406 |
+
"learning_rate": 0.001,
|
| 407 |
+
"loss": 4.3318,
|
| 408 |
+
"step": 5600
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.2279908803647854,
|
| 412 |
+
"grad_norm": 0.4887066185474396,
|
| 413 |
+
"learning_rate": 0.001,
|
| 414 |
+
"loss": 4.3318,
|
| 415 |
+
"step": 5700
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.23199072037118515,
|
| 419 |
+
"grad_norm": 0.4820877015590668,
|
| 420 |
+
"learning_rate": 0.001,
|
| 421 |
+
"loss": 4.3253,
|
| 422 |
+
"step": 5800
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.2359905603775849,
|
| 426 |
+
"grad_norm": 0.48746803402900696,
|
| 427 |
+
"learning_rate": 0.001,
|
| 428 |
+
"loss": 4.3242,
|
| 429 |
+
"step": 5900
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.23999040038398464,
|
| 433 |
+
"grad_norm": 0.5339901447296143,
|
| 434 |
+
"learning_rate": 0.001,
|
| 435 |
+
"loss": 4.3226,
|
| 436 |
+
"step": 6000
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.2439902403903844,
|
| 440 |
+
"grad_norm": 0.5406463146209717,
|
| 441 |
+
"learning_rate": 0.001,
|
| 442 |
+
"loss": 4.3197,
|
| 443 |
+
"step": 6100
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.24799008039678413,
|
| 447 |
+
"grad_norm": 0.5854783654212952,
|
| 448 |
+
"learning_rate": 0.001,
|
| 449 |
+
"loss": 4.318,
|
| 450 |
+
"step": 6200
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.25198992040318385,
|
| 454 |
+
"grad_norm": 0.47678840160369873,
|
| 455 |
+
"learning_rate": 0.001,
|
| 456 |
+
"loss": 4.3187,
|
| 457 |
+
"step": 6300
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.2559897604095836,
|
| 461 |
+
"grad_norm": 0.5523233413696289,
|
| 462 |
+
"learning_rate": 0.001,
|
| 463 |
+
"loss": 4.3117,
|
| 464 |
+
"step": 6400
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.25998960041598335,
|
| 468 |
+
"grad_norm": 0.46079719066619873,
|
| 469 |
+
"learning_rate": 0.001,
|
| 470 |
+
"loss": 4.3165,
|
| 471 |
+
"step": 6500
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.2639894404223831,
|
| 475 |
+
"grad_norm": 0.4956238269805908,
|
| 476 |
+
"learning_rate": 0.001,
|
| 477 |
+
"loss": 4.3116,
|
| 478 |
+
"step": 6600
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.26798928042878284,
|
| 482 |
+
"grad_norm": 0.532508373260498,
|
| 483 |
+
"learning_rate": 0.001,
|
| 484 |
+
"loss": 4.307,
|
| 485 |
+
"step": 6700
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.2719891204351826,
|
| 489 |
+
"grad_norm": 0.5244960188865662,
|
| 490 |
+
"learning_rate": 0.001,
|
| 491 |
+
"loss": 4.309,
|
| 492 |
+
"step": 6800
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.27598896044158233,
|
| 496 |
+
"grad_norm": 0.48627936840057373,
|
| 497 |
+
"learning_rate": 0.001,
|
| 498 |
+
"loss": 4.3025,
|
| 499 |
+
"step": 6900
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.2799888004479821,
|
| 503 |
+
"grad_norm": 0.5393197536468506,
|
| 504 |
+
"learning_rate": 0.001,
|
| 505 |
+
"loss": 4.3062,
|
| 506 |
+
"step": 7000
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.2839886404543818,
|
| 510 |
+
"grad_norm": 0.5384635925292969,
|
| 511 |
+
"learning_rate": 0.001,
|
| 512 |
+
"loss": 4.2993,
|
| 513 |
+
"step": 7100
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.28798848046078157,
|
| 517 |
+
"grad_norm": 0.5455852150917053,
|
| 518 |
+
"learning_rate": 0.001,
|
| 519 |
+
"loss": 4.299,
|
| 520 |
+
"step": 7200
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.2919883204671813,
|
| 524 |
+
"grad_norm": 0.45626768469810486,
|
| 525 |
+
"learning_rate": 0.001,
|
| 526 |
+
"loss": 4.2983,
|
| 527 |
+
"step": 7300
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.29598816047358106,
|
| 531 |
+
"grad_norm": 0.5111705660820007,
|
| 532 |
+
"learning_rate": 0.001,
|
| 533 |
+
"loss": 4.2992,
|
| 534 |
+
"step": 7400
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.2999880004799808,
|
| 538 |
+
"grad_norm": 0.5607153177261353,
|
| 539 |
+
"learning_rate": 0.001,
|
| 540 |
+
"loss": 4.291,
|
| 541 |
+
"step": 7500
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.30398784048638056,
|
| 545 |
+
"grad_norm": 0.5863308906555176,
|
| 546 |
+
"learning_rate": 0.001,
|
| 547 |
+
"loss": 4.2928,
|
| 548 |
+
"step": 7600
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.3079876804927803,
|
| 552 |
+
"grad_norm": 0.48837366700172424,
|
| 553 |
+
"learning_rate": 0.001,
|
| 554 |
+
"loss": 4.2951,
|
| 555 |
+
"step": 7700
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.31198752049918005,
|
| 559 |
+
"grad_norm": 0.5300312042236328,
|
| 560 |
+
"learning_rate": 0.001,
|
| 561 |
+
"loss": 4.2891,
|
| 562 |
+
"step": 7800
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.3159873605055798,
|
| 566 |
+
"grad_norm": 0.4869995415210724,
|
| 567 |
+
"learning_rate": 0.001,
|
| 568 |
+
"loss": 4.2868,
|
| 569 |
+
"step": 7900
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.31998720051197954,
|
| 573 |
+
"grad_norm": 0.5378390550613403,
|
| 574 |
+
"learning_rate": 0.001,
|
| 575 |
+
"loss": 4.2863,
|
| 576 |
+
"step": 8000
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.3239870405183793,
|
| 580 |
+
"grad_norm": 0.49154022336006165,
|
| 581 |
+
"learning_rate": 0.001,
|
| 582 |
+
"loss": 4.2902,
|
| 583 |
+
"step": 8100
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.32798688052477903,
|
| 587 |
+
"grad_norm": 0.5984882712364197,
|
| 588 |
+
"learning_rate": 0.001,
|
| 589 |
+
"loss": 4.2851,
|
| 590 |
+
"step": 8200
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.3319867205311788,
|
| 594 |
+
"grad_norm": 0.5132819414138794,
|
| 595 |
+
"learning_rate": 0.001,
|
| 596 |
+
"loss": 4.2854,
|
| 597 |
+
"step": 8300
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.33598656053757847,
|
| 601 |
+
"grad_norm": 0.5187487006187439,
|
| 602 |
+
"learning_rate": 0.001,
|
| 603 |
+
"loss": 4.2853,
|
| 604 |
+
"step": 8400
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.3399864005439782,
|
| 608 |
+
"grad_norm": 0.5310469269752502,
|
| 609 |
+
"learning_rate": 0.001,
|
| 610 |
+
"loss": 4.2785,
|
| 611 |
+
"step": 8500
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.34398624055037796,
|
| 615 |
+
"grad_norm": 0.5427576899528503,
|
| 616 |
+
"learning_rate": 0.001,
|
| 617 |
+
"loss": 4.2799,
|
| 618 |
+
"step": 8600
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.3479860805567777,
|
| 622 |
+
"grad_norm": 0.566967248916626,
|
| 623 |
+
"learning_rate": 0.001,
|
| 624 |
+
"loss": 4.2822,
|
| 625 |
+
"step": 8700
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.35198592056317746,
|
| 629 |
+
"grad_norm": 0.48460662364959717,
|
| 630 |
+
"learning_rate": 0.001,
|
| 631 |
+
"loss": 4.2772,
|
| 632 |
+
"step": 8800
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.3559857605695772,
|
| 636 |
+
"grad_norm": 0.5119643807411194,
|
| 637 |
+
"learning_rate": 0.001,
|
| 638 |
+
"loss": 4.2782,
|
| 639 |
+
"step": 8900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.35998560057597695,
|
| 643 |
+
"grad_norm": 0.5386670827865601,
|
| 644 |
+
"learning_rate": 0.001,
|
| 645 |
+
"loss": 4.2749,
|
| 646 |
+
"step": 9000
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.3639854405823767,
|
| 650 |
+
"grad_norm": 0.5337742567062378,
|
| 651 |
+
"learning_rate": 0.001,
|
| 652 |
+
"loss": 4.2745,
|
| 653 |
+
"step": 9100
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.36798528058877644,
|
| 657 |
+
"grad_norm": 0.522514283657074,
|
| 658 |
+
"learning_rate": 0.001,
|
| 659 |
+
"loss": 4.2717,
|
| 660 |
+
"step": 9200
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.3719851205951762,
|
| 664 |
+
"grad_norm": 0.549670934677124,
|
| 665 |
+
"learning_rate": 0.001,
|
| 666 |
+
"loss": 4.272,
|
| 667 |
+
"step": 9300
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.37598496060157593,
|
| 671 |
+
"grad_norm": 0.6063629388809204,
|
| 672 |
+
"learning_rate": 0.001,
|
| 673 |
+
"loss": 4.2684,
|
| 674 |
+
"step": 9400
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.3799848006079757,
|
| 678 |
+
"grad_norm": 0.5420516133308411,
|
| 679 |
+
"learning_rate": 0.001,
|
| 680 |
+
"loss": 4.2674,
|
| 681 |
+
"step": 9500
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.3839846406143754,
|
| 685 |
+
"grad_norm": 0.48435646295547485,
|
| 686 |
+
"learning_rate": 0.001,
|
| 687 |
+
"loss": 4.2675,
|
| 688 |
+
"step": 9600
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.3879844806207752,
|
| 692 |
+
"grad_norm": 0.5914377570152283,
|
| 693 |
+
"learning_rate": 0.001,
|
| 694 |
+
"loss": 4.2737,
|
| 695 |
+
"step": 9700
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.3919843206271749,
|
| 699 |
+
"grad_norm": 0.4351874589920044,
|
| 700 |
+
"learning_rate": 0.001,
|
| 701 |
+
"loss": 4.2684,
|
| 702 |
+
"step": 9800
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.39598416063357467,
|
| 706 |
+
"grad_norm": 0.5514108538627625,
|
| 707 |
+
"learning_rate": 0.001,
|
| 708 |
+
"loss": 4.2671,
|
| 709 |
+
"step": 9900
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.3999840006399744,
|
| 713 |
+
"grad_norm": 0.5687771439552307,
|
| 714 |
+
"learning_rate": 0.001,
|
| 715 |
+
"loss": 4.2626,
|
| 716 |
+
"step": 10000
|
| 717 |
+
}
|
| 718 |
+
],
|
| 719 |
+
"logging_steps": 100,
|
| 720 |
+
"max_steps": 150000,
|
| 721 |
+
"num_input_tokens_seen": 0,
|
| 722 |
+
"num_train_epochs": 6,
|
| 723 |
+
"save_steps": 500,
|
| 724 |
+
"stateful_callbacks": {
|
| 725 |
+
"TrainerControl": {
|
| 726 |
+
"args": {
|
| 727 |
+
"should_epoch_stop": false,
|
| 728 |
+
"should_evaluate": false,
|
| 729 |
+
"should_log": false,
|
| 730 |
+
"should_save": true,
|
| 731 |
+
"should_training_stop": false
|
| 732 |
+
},
|
| 733 |
+
"attributes": {}
|
| 734 |
+
}
|
| 735 |
+
},
|
| 736 |
+
"total_flos": 2.39981297664e+17,
|
| 737 |
+
"train_batch_size": 64,
|
| 738 |
+
"trial_name": null,
|
| 739 |
+
"trial_params": null
|
| 740 |
+
}
|
checkpoint-10000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b573a96e19aa9061cdc1bcf783263829ca1386cefdf168bd82b7d605ad2594ec
|
| 3 |
+
size 5649
|
checkpoint-100000/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "EleutherAI/pythia-14m",
|
| 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": 128,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 512,
|
| 16 |
+
"layer_norm_eps": 1e-05,
|
| 17 |
+
"max_position_embeddings": 2048,
|
| 18 |
+
"model_type": "gpt_neox",
|
| 19 |
+
"num_attention_heads": 4,
|
| 20 |
+
"num_hidden_layers": 6,
|
| 21 |
+
"partial_rotary_factor": 0.25,
|
| 22 |
+
"rope_scaling": null,
|
| 23 |
+
"rope_theta": 10000,
|
| 24 |
+
"rotary_emb_base": 10000,
|
| 25 |
+
"rotary_pct": 0.25,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.45.2",
|
| 29 |
+
"use_cache": false,
|
| 30 |
+
"use_parallel_residual": true,
|
| 31 |
+
"vocab_size": 50304
|
| 32 |
+
}
|
checkpoint-100000/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"transformers_version": "4.45.2",
|
| 6 |
+
"use_cache": false
|
| 7 |
+
}
|
checkpoint-100000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:474b712d999a8985525239ef03051e255271c60e094376cf1f927ae8a0af91b3
|
| 3 |
+
size 56279344
|
checkpoint-100000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59886b2ae140cbe8da64a2239a400d34c37c1431bd61ad52842539d86f688120
|
| 3 |
+
size 112605707
|
checkpoint-100000/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:daf26c930fc778c4127c596aa27bd243fe34e1aafd70f1c2e2344fd17a0fc5ae
|
| 3 |
+
size 16325
|
checkpoint-100000/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:677c13f0cc0bb08bbb080fdfeb71469f745f9a89f482907cfcfbbd31f924ed81
|
| 3 |
+
size 16325
|
checkpoint-100000/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:111bd2f8a56e8291b195da2889303ad84ea2144dc8b5d9bd9a2554aee0c6ed4d
|
| 3 |
+
size 16325
|
checkpoint-100000/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7d4b38e6d4e20fbc05cee147d55111e549ff1b673bf6664138e2dce7b2baabf
|
| 3 |
+
size 16325
|
checkpoint-100000/rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef0a66a93651c55490a7f069ec878a68d27db46a11e2222541fe9c6ded602cf1
|
| 3 |
+
size 16325
|
checkpoint-100000/rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:705636c2daeef82bfeea12acec4d335d3b07a026ce57d3d3e0db4e9dc2b2bb17
|
| 3 |
+
size 16325
|
checkpoint-100000/rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d37c80b222aa5f5f25888cce288b804fcda67f69b6d390d167ba9e8226ed2fb
|
| 3 |
+
size 16325
|
checkpoint-100000/rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:891d0ff333b1113d2278c595ff57245737f23f5f620aad19cd2e3e3cf6d0ea7c
|
| 3 |
+
size 16325
|
checkpoint-100000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5d226e068a64fdb5946e25b7b2e0d0f2e89f6c3c2fb105ea0567d6133bf383a
|
| 3 |
+
size 1465
|
checkpoint-100000/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 |
+
}
|