Training in progress, step 400, checkpoint
Browse files- last-checkpoint/added_tokens.json +11 -3
- last-checkpoint/config.json +20 -21
- last-checkpoint/generation_config.json +3 -2
- last-checkpoint/model.safetensors +2 -2
- last-checkpoint/optimizer.pt +2 -2
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/special_tokens_map.json +2 -2
- last-checkpoint/tokenizer.json +2 -2
- last-checkpoint/tokenizer_config.json +69 -161
- last-checkpoint/trainer_state.json +95 -1575
- last-checkpoint/training_args.bin +1 -1
last-checkpoint/added_tokens.json
CHANGED
|
@@ -1,5 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"<|
|
| 3 |
-
"<|
|
| 4 |
-
"<|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"<|assistant|>": 32001,
|
| 3 |
+
"<|endoftext|>": 32000,
|
| 4 |
+
"<|end|>": 32007,
|
| 5 |
+
"<|placeholder1|>": 32002,
|
| 6 |
+
"<|placeholder2|>": 32003,
|
| 7 |
+
"<|placeholder3|>": 32004,
|
| 8 |
+
"<|placeholder4|>": 32005,
|
| 9 |
+
"<|placeholder5|>": 32008,
|
| 10 |
+
"<|placeholder6|>": 32009,
|
| 11 |
+
"<|system|>": 32006,
|
| 12 |
+
"<|user|>": 32010
|
| 13 |
}
|
last-checkpoint/config.json
CHANGED
|
@@ -1,32 +1,31 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
| 6 |
-
"attention_bias": true,
|
| 7 |
"attention_dropout": 0.0,
|
| 8 |
-
"bos_token_id":
|
| 9 |
-
"
|
| 10 |
-
"eos_token_id":
|
| 11 |
-
"hidden_act": "
|
| 12 |
-
"
|
| 13 |
-
"hidden_size": 512,
|
| 14 |
"initializer_range": 0.02,
|
| 15 |
-
"intermediate_size":
|
| 16 |
-
"
|
| 17 |
-
"
|
| 18 |
-
"
|
| 19 |
-
"
|
| 20 |
-
"
|
| 21 |
-
"
|
|
|
|
|
|
|
|
|
|
| 22 |
"rope_scaling": null,
|
| 23 |
-
"rope_theta": 10000,
|
| 24 |
-
"
|
| 25 |
-
"rotary_pct": 0.25,
|
| 26 |
"tie_word_embeddings": false,
|
| 27 |
"torch_dtype": "bfloat16",
|
| 28 |
"transformers_version": "4.48.1",
|
| 29 |
"use_cache": false,
|
| 30 |
-
"
|
| 31 |
-
"vocab_size": 50278
|
| 32 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "Xenova/tiny-random-Phi3ForCausalLM",
|
| 3 |
"architectures": [
|
| 4 |
+
"Phi3ForCausalLM"
|
| 5 |
],
|
|
|
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"embd_pdrop": 0.0,
|
| 9 |
+
"eos_token_id": 32000,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 32,
|
|
|
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 64,
|
| 14 |
+
"max_position_embeddings": 4096,
|
| 15 |
+
"model_type": "phi3",
|
| 16 |
+
"num_attention_heads": 4,
|
| 17 |
+
"num_hidden_layers": 2,
|
| 18 |
+
"num_key_value_heads": 4,
|
| 19 |
+
"original_max_position_embeddings": 4096,
|
| 20 |
+
"pad_token_id": 32000,
|
| 21 |
+
"resid_pdrop": 0.0,
|
| 22 |
+
"rms_norm_eps": 1e-05,
|
| 23 |
"rope_scaling": null,
|
| 24 |
+
"rope_theta": 10000.0,
|
| 25 |
+
"sliding_window": 2047,
|
|
|
|
| 26 |
"tie_word_embeddings": false,
|
| 27 |
"torch_dtype": "bfloat16",
|
| 28 |
"transformers_version": "4.48.1",
|
| 29 |
"use_cache": false,
|
| 30 |
+
"vocab_size": 32011
|
|
|
|
| 31 |
}
|
last-checkpoint/generation_config.json
CHANGED
|
@@ -1,7 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
-
"bos_token_id":
|
| 4 |
"do_sample": true,
|
| 5 |
-
"eos_token_id":
|
|
|
|
| 6 |
"transformers_version": "4.48.1"
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
"do_sample": true,
|
| 5 |
+
"eos_token_id": 32000,
|
| 6 |
+
"pad_token_id": 32000,
|
| 7 |
"transformers_version": "4.48.1"
|
| 8 |
}
|
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9887d0a75dcfd98e56a4c42489abac39f5f9adfc1e32e149aaacb6e76bd402cd
|
| 3 |
+
size 4140280
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:069af421bb650b702a640dd7555d4a79b1545bb9de69c737913eb28166e68b67
|
| 3 |
+
size 4291766
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9feae33b2fec0a6229240e7adaee6ecc8f5cfdf1a8bd0e827b1d8a241424e3c0
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a673aaf85c0fe6b6c29cb8f3e7dbd829eef637110e4ad9a775f3fcf001c92591
|
| 3 |
size 1064
|
last-checkpoint/special_tokens_map.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"bos_token": {
|
| 3 |
-
"content": "
|
| 4 |
"lstrip": false,
|
| 5 |
"normalized": false,
|
| 6 |
"rstrip": false,
|
|
@@ -21,7 +21,7 @@
|
|
| 21 |
"single_word": false
|
| 22 |
},
|
| 23 |
"unk_token": {
|
| 24 |
-
"content": "
|
| 25 |
"lstrip": false,
|
| 26 |
"normalized": false,
|
| 27 |
"rstrip": false,
|
|
|
|
| 1 |
{
|
| 2 |
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
"lstrip": false,
|
| 5 |
"normalized": false,
|
| 6 |
"rstrip": false,
|
|
|
|
| 21 |
"single_word": false
|
| 22 |
},
|
| 23 |
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
"lstrip": false,
|
| 26 |
"normalized": false,
|
| 27 |
"rstrip": false,
|
last-checkpoint/tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b013fe7282b7984bc14b1c64c2a70dd06b652a969810fbba6217f4ac70339f44
|
| 3 |
+
size 3621089
|
last-checkpoint/tokenizer_config.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"add_bos_token":
|
| 3 |
"add_eos_token": false,
|
| 4 |
-
"add_prefix_space":
|
| 5 |
"added_tokens_decoder": {
|
| 6 |
"0": {
|
| 7 |
-
"content": "
|
| 8 |
"lstrip": false,
|
| 9 |
"normalized": false,
|
| 10 |
"rstrip": false,
|
|
@@ -12,214 +12,122 @@
|
|
| 12 |
"special": true
|
| 13 |
},
|
| 14 |
"1": {
|
| 15 |
-
"content": "
|
| 16 |
"lstrip": false,
|
| 17 |
"normalized": false,
|
| 18 |
"rstrip": false,
|
| 19 |
"single_word": false,
|
| 20 |
"special": true
|
| 21 |
},
|
| 22 |
-
"
|
| 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":
|
| 114 |
-
"rstrip":
|
| 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 |
-
"
|
| 127 |
-
"content": "
|
| 128 |
"lstrip": false,
|
| 129 |
-
"normalized":
|
| 130 |
"rstrip": false,
|
| 131 |
"single_word": false,
|
| 132 |
-
"special":
|
| 133 |
},
|
| 134 |
-
"
|
| 135 |
-
"content": "
|
| 136 |
"lstrip": false,
|
| 137 |
-
"normalized":
|
| 138 |
-
"rstrip":
|
| 139 |
"single_word": false,
|
| 140 |
-
"special":
|
| 141 |
},
|
| 142 |
-
"
|
| 143 |
-
"content": "
|
| 144 |
"lstrip": false,
|
| 145 |
-
"normalized":
|
| 146 |
-
"rstrip":
|
| 147 |
"single_word": false,
|
| 148 |
-
"special":
|
| 149 |
},
|
| 150 |
-
"
|
| 151 |
-
"content": "
|
| 152 |
"lstrip": false,
|
| 153 |
-
"normalized":
|
| 154 |
-
"rstrip":
|
| 155 |
"single_word": false,
|
| 156 |
-
"special":
|
| 157 |
},
|
| 158 |
-
"
|
| 159 |
-
"content": "
|
| 160 |
"lstrip": false,
|
| 161 |
-
"normalized":
|
| 162 |
-
"rstrip":
|
| 163 |
"single_word": false,
|
| 164 |
-
"special":
|
| 165 |
},
|
| 166 |
-
"
|
| 167 |
-
"content": "
|
| 168 |
"lstrip": false,
|
| 169 |
-
"normalized":
|
| 170 |
-
"rstrip":
|
| 171 |
"single_word": false,
|
| 172 |
-
"special":
|
| 173 |
},
|
| 174 |
-
"
|
| 175 |
-
"content": "
|
| 176 |
"lstrip": false,
|
| 177 |
-
"normalized":
|
| 178 |
-
"rstrip":
|
| 179 |
"single_word": false,
|
| 180 |
-
"special":
|
| 181 |
},
|
| 182 |
-
"
|
| 183 |
-
"content": "
|
| 184 |
"lstrip": false,
|
| 185 |
-
"normalized":
|
| 186 |
-
"rstrip":
|
| 187 |
"single_word": false,
|
| 188 |
-
"special":
|
| 189 |
},
|
| 190 |
-
"
|
| 191 |
-
"content": "
|
| 192 |
"lstrip": false,
|
| 193 |
-
"normalized":
|
| 194 |
-
"rstrip":
|
| 195 |
"single_word": false,
|
| 196 |
-
"special":
|
| 197 |
},
|
| 198 |
-
"
|
| 199 |
-
"content": "
|
| 200 |
"lstrip": false,
|
| 201 |
-
"normalized":
|
| 202 |
-
"rstrip":
|
| 203 |
"single_word": false,
|
| 204 |
-
"special":
|
| 205 |
},
|
| 206 |
-
"
|
| 207 |
-
"content": "
|
| 208 |
"lstrip": false,
|
| 209 |
"normalized": false,
|
| 210 |
-
"rstrip":
|
| 211 |
"single_word": false,
|
| 212 |
"special": true
|
| 213 |
}
|
| 214 |
},
|
| 215 |
-
"bos_token": "
|
| 216 |
-
"chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{
|
| 217 |
"clean_up_tokenization_spaces": false,
|
| 218 |
"eos_token": "<|endoftext|>",
|
| 219 |
"extra_special_tokens": {},
|
| 220 |
-
"
|
|
|
|
| 221 |
"pad_token": "<|endoftext|>",
|
| 222 |
-
"
|
| 223 |
-
"
|
|
|
|
|
|
|
|
|
|
| 224 |
"use_fast": true
|
| 225 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
"added_tokens_decoder": {
|
| 6 |
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
"lstrip": false,
|
| 9 |
"normalized": false,
|
| 10 |
"rstrip": false,
|
|
|
|
| 12 |
"special": true
|
| 13 |
},
|
| 14 |
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
"lstrip": false,
|
| 17 |
"normalized": false,
|
| 18 |
"rstrip": false,
|
| 19 |
"single_word": false,
|
| 20 |
"special": true
|
| 21 |
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
"single_word": false,
|
| 28 |
"special": false
|
| 29 |
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "<|endoftext|>",
|
| 32 |
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
"rstrip": false,
|
| 35 |
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
},
|
| 38 |
+
"32001": {
|
| 39 |
+
"content": "<|assistant|>",
|
| 40 |
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": true,
|
| 43 |
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
},
|
| 46 |
+
"32002": {
|
| 47 |
+
"content": "<|placeholder1|>",
|
| 48 |
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": true,
|
| 51 |
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
},
|
| 54 |
+
"32003": {
|
| 55 |
+
"content": "<|placeholder2|>",
|
| 56 |
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": true,
|
| 59 |
"single_word": false,
|
| 60 |
+
"special": true
|
| 61 |
},
|
| 62 |
+
"32004": {
|
| 63 |
+
"content": "<|placeholder3|>",
|
| 64 |
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": true,
|
| 67 |
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
},
|
| 70 |
+
"32005": {
|
| 71 |
+
"content": "<|placeholder4|>",
|
| 72 |
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": true,
|
| 75 |
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
},
|
| 78 |
+
"32006": {
|
| 79 |
+
"content": "<|system|>",
|
| 80 |
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": true,
|
| 83 |
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
},
|
| 86 |
+
"32007": {
|
| 87 |
+
"content": "<|end|>",
|
| 88 |
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": true,
|
| 91 |
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
},
|
| 94 |
+
"32008": {
|
| 95 |
+
"content": "<|placeholder5|>",
|
| 96 |
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": true,
|
| 99 |
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
},
|
| 102 |
+
"32009": {
|
| 103 |
+
"content": "<|placeholder6|>",
|
| 104 |
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": true,
|
| 107 |
"single_word": false,
|
| 108 |
+
"special": true
|
| 109 |
},
|
| 110 |
+
"32010": {
|
| 111 |
+
"content": "<|user|>",
|
| 112 |
"lstrip": false,
|
| 113 |
"normalized": false,
|
| 114 |
+
"rstrip": true,
|
| 115 |
"single_word": false,
|
| 116 |
"special": true
|
| 117 |
}
|
| 118 |
},
|
| 119 |
+
"bos_token": "<s>",
|
| 120 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
|
| 121 |
"clean_up_tokenization_spaces": false,
|
| 122 |
"eos_token": "<|endoftext|>",
|
| 123 |
"extra_special_tokens": {},
|
| 124 |
+
"legacy": true,
|
| 125 |
+
"model_max_length": 4096,
|
| 126 |
"pad_token": "<|endoftext|>",
|
| 127 |
+
"padding_side": "left",
|
| 128 |
+
"sp_model_kwargs": {},
|
| 129 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 130 |
+
"unk_token": "<unk>",
|
| 131 |
+
"use_default_system_prompt": false,
|
| 132 |
"use_fast": true
|
| 133 |
}
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,1796 +1,316 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 200,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.0002959455460195324,
|
| 13 |
-
"eval_loss":
|
| 14 |
-
"eval_runtime":
|
| 15 |
-
"eval_samples_per_second":
|
| 16 |
-
"eval_steps_per_second":
|
| 17 |
"step": 1
|
| 18 |
},
|
| 19 |
{
|
| 20 |
"epoch": 0.002959455460195324,
|
| 21 |
-
"grad_norm":
|
| 22 |
"learning_rate": 1.6000000000000003e-05,
|
| 23 |
-
"loss":
|
| 24 |
"step": 10
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 0.005918910920390648,
|
| 28 |
-
"grad_norm":
|
| 29 |
"learning_rate": 3.2000000000000005e-05,
|
| 30 |
-
"loss":
|
| 31 |
"step": 20
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"epoch": 0.008878366380585973,
|
| 35 |
-
"grad_norm":
|
| 36 |
"learning_rate": 4.8e-05,
|
| 37 |
-
"loss":
|
| 38 |
"step": 30
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.011837821840781295,
|
| 42 |
-
"grad_norm":
|
| 43 |
"learning_rate": 6.400000000000001e-05,
|
| 44 |
-
"loss":
|
| 45 |
"step": 40
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.01479727730097662,
|
| 49 |
-
"grad_norm":
|
| 50 |
"learning_rate": 8e-05,
|
| 51 |
-
"loss":
|
| 52 |
"step": 50
|
| 53 |
},
|
| 54 |
{
|
| 55 |
"epoch": 0.017756732761171946,
|
| 56 |
-
"grad_norm":
|
| 57 |
"learning_rate": 9.6e-05,
|
| 58 |
-
"loss":
|
| 59 |
"step": 60
|
| 60 |
},
|
| 61 |
{
|
| 62 |
"epoch": 0.020716188221367268,
|
| 63 |
-
"grad_norm":
|
| 64 |
"learning_rate": 0.00011200000000000001,
|
| 65 |
-
"loss":
|
| 66 |
"step": 70
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 0.02367564368156259,
|
| 70 |
-
"grad_norm":
|
| 71 |
"learning_rate": 0.00012800000000000002,
|
| 72 |
-
"loss":
|
| 73 |
"step": 80
|
| 74 |
},
|
| 75 |
{
|
| 76 |
"epoch": 0.026635099141757917,
|
| 77 |
-
"grad_norm":
|
| 78 |
"learning_rate": 0.000144,
|
| 79 |
-
"loss":
|
| 80 |
"step": 90
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.02959455460195324,
|
| 84 |
-
"grad_norm":
|
| 85 |
"learning_rate": 0.00016,
|
| 86 |
-
"loss":
|
| 87 |
"step": 100
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 0.032554010062148565,
|
| 91 |
-
"grad_norm":
|
| 92 |
"learning_rate": 0.00017600000000000002,
|
| 93 |
-
"loss":
|
| 94 |
"step": 110
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"epoch": 0.03551346552234389,
|
| 98 |
-
"grad_norm":
|
| 99 |
"learning_rate": 0.000192,
|
| 100 |
-
"loss":
|
| 101 |
"step": 120
|
| 102 |
},
|
| 103 |
{
|
| 104 |
"epoch": 0.03847292098253921,
|
| 105 |
-
"grad_norm":
|
| 106 |
"learning_rate": 0.0001999978128380225,
|
| 107 |
-
"loss":
|
| 108 |
"step": 130
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 0.041432376442734536,
|
| 112 |
-
"grad_norm":
|
| 113 |
"learning_rate": 0.0001999803161162393,
|
| 114 |
-
"loss":
|
| 115 |
"step": 140
|
| 116 |
},
|
| 117 |
{
|
| 118 |
"epoch": 0.04439183190292986,
|
| 119 |
-
"grad_norm":
|
| 120 |
"learning_rate": 0.00019994532573409262,
|
| 121 |
-
"loss":
|
| 122 |
"step": 150
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 0.04735128736312518,
|
| 126 |
-
"grad_norm":
|
| 127 |
"learning_rate": 0.00019989284781388617,
|
| 128 |
-
"loss":
|
| 129 |
"step": 160
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 0.05031074282332051,
|
| 133 |
-
"grad_norm":
|
| 134 |
"learning_rate": 0.00019982289153773646,
|
| 135 |
-
"loss":
|
| 136 |
"step": 170
|
| 137 |
},
|
| 138 |
{
|
| 139 |
"epoch": 0.053270198283515834,
|
| 140 |
-
"grad_norm":
|
| 141 |
"learning_rate": 0.00019973546914596623,
|
| 142 |
-
"loss": 9.
|
| 143 |
"step": 180
|
| 144 |
},
|
| 145 |
{
|
| 146 |
"epoch": 0.05622965374371116,
|
| 147 |
-
"grad_norm":
|
| 148 |
"learning_rate": 0.00019963059593496268,
|
| 149 |
-
"loss": 9.
|
| 150 |
"step": 190
|
| 151 |
},
|
| 152 |
{
|
| 153 |
"epoch": 0.05918910920390648,
|
| 154 |
-
"grad_norm":
|
| 155 |
"learning_rate": 0.00019950829025450114,
|
| 156 |
-
"loss":
|
| 157 |
"step": 200
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"epoch": 0.05918910920390648,
|
| 161 |
-
"eval_loss": 9.
|
| 162 |
-
"eval_runtime": 11.
|
| 163 |
-
"eval_samples_per_second":
|
| 164 |
-
"eval_steps_per_second":
|
| 165 |
"step": 200
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 0.062148564664101805,
|
| 169 |
-
"grad_norm":
|
| 170 |
"learning_rate": 0.0001993685735045343,
|
| 171 |
-
"loss":
|
| 172 |
"step": 210
|
| 173 |
},
|
| 174 |
{
|
| 175 |
"epoch": 0.06510802012429713,
|
| 176 |
-
"grad_norm":
|
| 177 |
"learning_rate": 0.0001992114701314478,
|
| 178 |
-
"loss":
|
| 179 |
"step": 220
|
| 180 |
},
|
| 181 |
{
|
| 182 |
"epoch": 0.06806747558449246,
|
| 183 |
-
"grad_norm":
|
| 184 |
"learning_rate": 0.000199037007623783,
|
| 185 |
-
"loss":
|
| 186 |
"step": 230
|
| 187 |
},
|
| 188 |
{
|
| 189 |
"epoch": 0.07102693104468778,
|
| 190 |
-
"grad_norm":
|
| 191 |
"learning_rate": 0.00019884521650742715,
|
| 192 |
-
"loss":
|
| 193 |
"step": 240
|
| 194 |
},
|
| 195 |
{
|
| 196 |
"epoch": 0.0739863865048831,
|
| 197 |
-
"grad_norm":
|
| 198 |
"learning_rate": 0.00019863613034027224,
|
| 199 |
-
"loss": 9.
|
| 200 |
"step": 250
|
| 201 |
},
|
| 202 |
{
|
| 203 |
"epoch": 0.07694584196507842,
|
| 204 |
-
"grad_norm":
|
| 205 |
"learning_rate": 0.0001984097857063434,
|
| 206 |
-
"loss": 8.
|
| 207 |
"step": 260
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 0.07990529742527375,
|
| 211 |
-
"grad_norm":
|
| 212 |
"learning_rate": 0.0001981662222093976,
|
| 213 |
-
"loss": 8.
|
| 214 |
"step": 270
|
| 215 |
},
|
| 216 |
{
|
| 217 |
"epoch": 0.08286475288546907,
|
| 218 |
-
"grad_norm":
|
| 219 |
"learning_rate": 0.00019790548246599447,
|
| 220 |
-
"loss": 8.
|
| 221 |
"step": 280
|
| 222 |
},
|
| 223 |
{
|
| 224 |
"epoch": 0.0858242083456644,
|
| 225 |
-
"grad_norm":
|
| 226 |
"learning_rate": 0.00019762761209803927,
|
| 227 |
-
"loss": 8.
|
| 228 |
"step": 290
|
| 229 |
},
|
| 230 |
{
|
| 231 |
"epoch": 0.08878366380585972,
|
| 232 |
-
"grad_norm":
|
| 233 |
"learning_rate": 0.0001973326597248006,
|
| 234 |
-
"loss": 8.
|
| 235 |
"step": 300
|
| 236 |
},
|
| 237 |
{
|
| 238 |
"epoch": 0.09174311926605505,
|
| 239 |
-
"grad_norm":
|
| 240 |
"learning_rate": 0.00019702067695440332,
|
| 241 |
-
"loss":
|
| 242 |
"step": 310
|
| 243 |
},
|
| 244 |
{
|
| 245 |
"epoch": 0.09470257472625036,
|
| 246 |
-
"grad_norm":
|
| 247 |
"learning_rate": 0.00019669171837479873,
|
| 248 |
-
"loss": 8.
|
| 249 |
"step": 320
|
| 250 |
},
|
| 251 |
{
|
| 252 |
"epoch": 0.09766203018644569,
|
| 253 |
-
"grad_norm":
|
| 254 |
"learning_rate": 0.00019634584154421317,
|
| 255 |
-
"loss": 8.
|
| 256 |
"step": 330
|
| 257 |
},
|
| 258 |
{
|
| 259 |
"epoch": 0.10062148564664102,
|
| 260 |
-
"grad_norm":
|
| 261 |
"learning_rate": 0.00019598310698107702,
|
| 262 |
-
"loss": 8.
|
| 263 |
"step": 340
|
| 264 |
},
|
| 265 |
{
|
| 266 |
"epoch": 0.10358094110683634,
|
| 267 |
-
"grad_norm":
|
| 268 |
"learning_rate": 0.00019560357815343577,
|
| 269 |
-
"loss": 8.
|
| 270 |
"step": 350
|
| 271 |
},
|
| 272 |
{
|
| 273 |
"epoch": 0.10654039656703167,
|
| 274 |
-
"grad_norm":
|
| 275 |
"learning_rate": 0.00019520732146784491,
|
| 276 |
-
"loss":
|
| 277 |
"step": 360
|
| 278 |
},
|
| 279 |
{
|
| 280 |
"epoch": 0.109499852027227,
|
| 281 |
-
"grad_norm":
|
| 282 |
"learning_rate": 0.0001947944062577507,
|
| 283 |
-
"loss": 8.
|
| 284 |
"step": 370
|
| 285 |
},
|
| 286 |
{
|
| 287 |
"epoch": 0.11245930748742232,
|
| 288 |
-
"grad_norm":
|
| 289 |
"learning_rate": 0.00019436490477135878,
|
| 290 |
-
"loss": 8.
|
| 291 |
"step": 380
|
| 292 |
},
|
| 293 |
{
|
| 294 |
"epoch": 0.11541876294761765,
|
| 295 |
-
"grad_norm":
|
| 296 |
"learning_rate": 0.00019391889215899299,
|
| 297 |
-
"loss": 8.
|
| 298 |
"step": 390
|
| 299 |
},
|
| 300 |
{
|
| 301 |
"epoch": 0.11837821840781296,
|
| 302 |
-
"grad_norm":
|
| 303 |
"learning_rate": 0.0001934564464599461,
|
| 304 |
-
"loss":
|
| 305 |
"step": 400
|
| 306 |
},
|
| 307 |
{
|
| 308 |
"epoch": 0.11837821840781296,
|
| 309 |
-
"eval_loss": 8.
|
| 310 |
-
"eval_runtime":
|
| 311 |
-
"eval_samples_per_second":
|
| 312 |
-
"eval_steps_per_second":
|
| 313 |
"step": 400
|
| 314 |
-
},
|
| 315 |
-
{
|
| 316 |
-
"epoch": 0.12133767386800828,
|
| 317 |
-
"grad_norm": 61.0,
|
| 318 |
-
"learning_rate": 0.00019297764858882514,
|
| 319 |
-
"loss": 8.6452,
|
| 320 |
-
"step": 410
|
| 321 |
-
},
|
| 322 |
-
{
|
| 323 |
-
"epoch": 0.12429712932820361,
|
| 324 |
-
"grad_norm": 50.0,
|
| 325 |
-
"learning_rate": 0.00019248258232139388,
|
| 326 |
-
"loss": 8.4218,
|
| 327 |
-
"step": 420
|
| 328 |
-
},
|
| 329 |
-
{
|
| 330 |
-
"epoch": 0.12725658478839894,
|
| 331 |
-
"grad_norm": 58.0,
|
| 332 |
-
"learning_rate": 0.00019197133427991436,
|
| 333 |
-
"loss": 8.4002,
|
| 334 |
-
"step": 430
|
| 335 |
-
},
|
| 336 |
-
{
|
| 337 |
-
"epoch": 0.13021604024859426,
|
| 338 |
-
"grad_norm": 588.0,
|
| 339 |
-
"learning_rate": 0.00019144399391799043,
|
| 340 |
-
"loss": 8.0756,
|
| 341 |
-
"step": 440
|
| 342 |
-
},
|
| 343 |
-
{
|
| 344 |
-
"epoch": 0.1331754957087896,
|
| 345 |
-
"grad_norm": 358.0,
|
| 346 |
-
"learning_rate": 0.00019090065350491626,
|
| 347 |
-
"loss": 8.0585,
|
| 348 |
-
"step": 450
|
| 349 |
-
},
|
| 350 |
-
{
|
| 351 |
-
"epoch": 0.1361349511689849,
|
| 352 |
-
"grad_norm": 63.5,
|
| 353 |
-
"learning_rate": 0.0001903414081095315,
|
| 354 |
-
"loss": 8.504,
|
| 355 |
-
"step": 460
|
| 356 |
-
},
|
| 357 |
-
{
|
| 358 |
-
"epoch": 0.13909440662918024,
|
| 359 |
-
"grad_norm": 83.5,
|
| 360 |
-
"learning_rate": 0.00018976635558358722,
|
| 361 |
-
"loss": 8.4537,
|
| 362 |
-
"step": 470
|
| 363 |
-
},
|
| 364 |
-
{
|
| 365 |
-
"epoch": 0.14205386208937557,
|
| 366 |
-
"grad_norm": 154.0,
|
| 367 |
-
"learning_rate": 0.00018917559654462474,
|
| 368 |
-
"loss": 8.2744,
|
| 369 |
-
"step": 480
|
| 370 |
-
},
|
| 371 |
-
{
|
| 372 |
-
"epoch": 0.1450133175495709,
|
| 373 |
-
"grad_norm": 139.0,
|
| 374 |
-
"learning_rate": 0.00018856923435837022,
|
| 375 |
-
"loss": 7.9953,
|
| 376 |
-
"step": 490
|
| 377 |
-
},
|
| 378 |
-
{
|
| 379 |
-
"epoch": 0.1479727730097662,
|
| 380 |
-
"grad_norm": 300.0,
|
| 381 |
-
"learning_rate": 0.0001879473751206489,
|
| 382 |
-
"loss": 8.2303,
|
| 383 |
-
"step": 500
|
| 384 |
-
},
|
| 385 |
-
{
|
| 386 |
-
"epoch": 0.15093222846996152,
|
| 387 |
-
"grad_norm": 157.0,
|
| 388 |
-
"learning_rate": 0.00018731012763882133,
|
| 389 |
-
"loss": 8.2334,
|
| 390 |
-
"step": 510
|
| 391 |
-
},
|
| 392 |
-
{
|
| 393 |
-
"epoch": 0.15389168393015684,
|
| 394 |
-
"grad_norm": 145.0,
|
| 395 |
-
"learning_rate": 0.00018665760341274505,
|
| 396 |
-
"loss": 8.0997,
|
| 397 |
-
"step": 520
|
| 398 |
-
},
|
| 399 |
-
{
|
| 400 |
-
"epoch": 0.15685113939035217,
|
| 401 |
-
"grad_norm": 43.5,
|
| 402 |
-
"learning_rate": 0.00018598991661526572,
|
| 403 |
-
"loss": 8.0979,
|
| 404 |
-
"step": 530
|
| 405 |
-
},
|
| 406 |
-
{
|
| 407 |
-
"epoch": 0.1598105948505475,
|
| 408 |
-
"grad_norm": 53.5,
|
| 409 |
-
"learning_rate": 0.00018530718407223974,
|
| 410 |
-
"loss": 8.3276,
|
| 411 |
-
"step": 540
|
| 412 |
-
},
|
| 413 |
-
{
|
| 414 |
-
"epoch": 0.16277005031074282,
|
| 415 |
-
"grad_norm": 145.0,
|
| 416 |
-
"learning_rate": 0.00018460952524209355,
|
| 417 |
-
"loss": 7.9545,
|
| 418 |
-
"step": 550
|
| 419 |
-
},
|
| 420 |
-
{
|
| 421 |
-
"epoch": 0.16572950577093815,
|
| 422 |
-
"grad_norm": 49.75,
|
| 423 |
-
"learning_rate": 0.00018389706219492147,
|
| 424 |
-
"loss": 8.3634,
|
| 425 |
-
"step": 560
|
| 426 |
-
},
|
| 427 |
-
{
|
| 428 |
-
"epoch": 0.16868896123113347,
|
| 429 |
-
"grad_norm": 90.5,
|
| 430 |
-
"learning_rate": 0.00018316991959112716,
|
| 431 |
-
"loss": 7.8803,
|
| 432 |
-
"step": 570
|
| 433 |
-
},
|
| 434 |
-
{
|
| 435 |
-
"epoch": 0.1716484166913288,
|
| 436 |
-
"grad_norm": 61.75,
|
| 437 |
-
"learning_rate": 0.00018242822465961176,
|
| 438 |
-
"loss": 8.0672,
|
| 439 |
-
"step": 580
|
| 440 |
-
},
|
| 441 |
-
{
|
| 442 |
-
"epoch": 0.17460787215152412,
|
| 443 |
-
"grad_norm": 113.0,
|
| 444 |
-
"learning_rate": 0.00018167210717551224,
|
| 445 |
-
"loss": 7.9656,
|
| 446 |
-
"step": 590
|
| 447 |
-
},
|
| 448 |
-
{
|
| 449 |
-
"epoch": 0.17756732761171945,
|
| 450 |
-
"grad_norm": 194.0,
|
| 451 |
-
"learning_rate": 0.00018090169943749476,
|
| 452 |
-
"loss": 7.7851,
|
| 453 |
-
"step": 600
|
| 454 |
-
},
|
| 455 |
-
{
|
| 456 |
-
"epoch": 0.17756732761171945,
|
| 457 |
-
"eval_loss": 9.452142715454102,
|
| 458 |
-
"eval_runtime": 9.0209,
|
| 459 |
-
"eval_samples_per_second": 166.503,
|
| 460 |
-
"eval_steps_per_second": 41.681,
|
| 461 |
-
"step": 600
|
| 462 |
-
},
|
| 463 |
-
{
|
| 464 |
-
"epoch": 0.18052678307191478,
|
| 465 |
-
"grad_norm": 336.0,
|
| 466 |
-
"learning_rate": 0.00018011713624460608,
|
| 467 |
-
"loss": 9.1377,
|
| 468 |
-
"step": 610
|
| 469 |
-
},
|
| 470 |
-
{
|
| 471 |
-
"epoch": 0.1834862385321101,
|
| 472 |
-
"grad_norm": 133.0,
|
| 473 |
-
"learning_rate": 0.00017931855487268782,
|
| 474 |
-
"loss": 7.9937,
|
| 475 |
-
"step": 620
|
| 476 |
-
},
|
| 477 |
-
{
|
| 478 |
-
"epoch": 0.18644569399230543,
|
| 479 |
-
"grad_norm": 456.0,
|
| 480 |
-
"learning_rate": 0.0001785060950503568,
|
| 481 |
-
"loss": 8.1474,
|
| 482 |
-
"step": 630
|
| 483 |
-
},
|
| 484 |
-
{
|
| 485 |
-
"epoch": 0.18940514945250073,
|
| 486 |
-
"grad_norm": 92.0,
|
| 487 |
-
"learning_rate": 0.00017767989893455698,
|
| 488 |
-
"loss": 8.0396,
|
| 489 |
-
"step": 640
|
| 490 |
-
},
|
| 491 |
-
{
|
| 492 |
-
"epoch": 0.19236460491269605,
|
| 493 |
-
"grad_norm": 1096.0,
|
| 494 |
-
"learning_rate": 0.00017684011108568592,
|
| 495 |
-
"loss": 8.8535,
|
| 496 |
-
"step": 650
|
| 497 |
-
},
|
| 498 |
-
{
|
| 499 |
-
"epoch": 0.19532406037289138,
|
| 500 |
-
"grad_norm": 41.5,
|
| 501 |
-
"learning_rate": 0.00017598687844230088,
|
| 502 |
-
"loss": 8.2106,
|
| 503 |
-
"step": 660
|
| 504 |
-
},
|
| 505 |
-
{
|
| 506 |
-
"epoch": 0.1982835158330867,
|
| 507 |
-
"grad_norm": 284.0,
|
| 508 |
-
"learning_rate": 0.00017512035029540885,
|
| 509 |
-
"loss": 8.3013,
|
| 510 |
-
"step": 670
|
| 511 |
-
},
|
| 512 |
-
{
|
| 513 |
-
"epoch": 0.20124297129328203,
|
| 514 |
-
"grad_norm": 39.0,
|
| 515 |
-
"learning_rate": 0.000174240678262345,
|
| 516 |
-
"loss": 8.1738,
|
| 517 |
-
"step": 680
|
| 518 |
-
},
|
| 519 |
-
{
|
| 520 |
-
"epoch": 0.20420242675347736,
|
| 521 |
-
"grad_norm": 107.5,
|
| 522 |
-
"learning_rate": 0.000173348016260244,
|
| 523 |
-
"loss": 8.4127,
|
| 524 |
-
"step": 690
|
| 525 |
-
},
|
| 526 |
-
{
|
| 527 |
-
"epoch": 0.20716188221367268,
|
| 528 |
-
"grad_norm": 288.0,
|
| 529 |
-
"learning_rate": 0.00017244252047910892,
|
| 530 |
-
"loss": 8.4413,
|
| 531 |
-
"step": 700
|
| 532 |
-
},
|
| 533 |
-
{
|
| 534 |
-
"epoch": 0.210121337673868,
|
| 535 |
-
"grad_norm": 55.5,
|
| 536 |
-
"learning_rate": 0.00017152434935448256,
|
| 537 |
-
"loss": 8.0362,
|
| 538 |
-
"step": 710
|
| 539 |
-
},
|
| 540 |
-
{
|
| 541 |
-
"epoch": 0.21308079313406333,
|
| 542 |
-
"grad_norm": 78.5,
|
| 543 |
-
"learning_rate": 0.0001705936635397259,
|
| 544 |
-
"loss": 7.9471,
|
| 545 |
-
"step": 720
|
| 546 |
-
},
|
| 547 |
-
{
|
| 548 |
-
"epoch": 0.21604024859425866,
|
| 549 |
-
"grad_norm": 62.75,
|
| 550 |
-
"learning_rate": 0.00016965062587790823,
|
| 551 |
-
"loss": 8.1659,
|
| 552 |
-
"step": 730
|
| 553 |
-
},
|
| 554 |
-
{
|
| 555 |
-
"epoch": 0.218999704054454,
|
| 556 |
-
"grad_norm": 56.5,
|
| 557 |
-
"learning_rate": 0.00016869540137331445,
|
| 558 |
-
"loss": 7.9207,
|
| 559 |
-
"step": 740
|
| 560 |
-
},
|
| 561 |
-
{
|
| 562 |
-
"epoch": 0.2219591595146493,
|
| 563 |
-
"grad_norm": 362.0,
|
| 564 |
-
"learning_rate": 0.00016772815716257412,
|
| 565 |
-
"loss": 8.1589,
|
| 566 |
-
"step": 750
|
| 567 |
-
},
|
| 568 |
-
{
|
| 569 |
-
"epoch": 0.22491861497484464,
|
| 570 |
-
"grad_norm": 22.875,
|
| 571 |
-
"learning_rate": 0.00016674906248541726,
|
| 572 |
-
"loss": 8.1283,
|
| 573 |
-
"step": 760
|
| 574 |
-
},
|
| 575 |
-
{
|
| 576 |
-
"epoch": 0.22787807043503996,
|
| 577 |
-
"grad_norm": 482.0,
|
| 578 |
-
"learning_rate": 0.00016575828865506245,
|
| 579 |
-
"loss": 7.7056,
|
| 580 |
-
"step": 770
|
| 581 |
-
},
|
| 582 |
-
{
|
| 583 |
-
"epoch": 0.2308375258952353,
|
| 584 |
-
"grad_norm": 72.5,
|
| 585 |
-
"learning_rate": 0.0001647560090282419,
|
| 586 |
-
"loss": 8.1033,
|
| 587 |
-
"step": 780
|
| 588 |
-
},
|
| 589 |
-
{
|
| 590 |
-
"epoch": 0.2337969813554306,
|
| 591 |
-
"grad_norm": 116.5,
|
| 592 |
-
"learning_rate": 0.000163742398974869,
|
| 593 |
-
"loss": 7.6061,
|
| 594 |
-
"step": 790
|
| 595 |
-
},
|
| 596 |
-
{
|
| 597 |
-
"epoch": 0.23675643681562591,
|
| 598 |
-
"grad_norm": 1448.0,
|
| 599 |
-
"learning_rate": 0.0001627176358473537,
|
| 600 |
-
"loss": 8.1142,
|
| 601 |
-
"step": 800
|
| 602 |
-
},
|
| 603 |
-
{
|
| 604 |
-
"epoch": 0.23675643681562591,
|
| 605 |
-
"eval_loss": 9.41397762298584,
|
| 606 |
-
"eval_runtime": 8.9895,
|
| 607 |
-
"eval_samples_per_second": 167.083,
|
| 608 |
-
"eval_steps_per_second": 41.826,
|
| 609 |
-
"step": 800
|
| 610 |
-
},
|
| 611 |
-
{
|
| 612 |
-
"epoch": 0.23971589227582124,
|
| 613 |
-
"grad_norm": 35.0,
|
| 614 |
-
"learning_rate": 0.0001616818989495711,
|
| 615 |
-
"loss": 8.3766,
|
| 616 |
-
"step": 810
|
| 617 |
-
},
|
| 618 |
-
{
|
| 619 |
-
"epoch": 0.24267534773601657,
|
| 620 |
-
"grad_norm": 27.375,
|
| 621 |
-
"learning_rate": 0.00016063536950548826,
|
| 622 |
-
"loss": 8.2034,
|
| 623 |
-
"step": 820
|
| 624 |
-
},
|
| 625 |
-
{
|
| 626 |
-
"epoch": 0.2456348031962119,
|
| 627 |
-
"grad_norm": 40.0,
|
| 628 |
-
"learning_rate": 0.0001595782306274553,
|
| 629 |
-
"loss": 8.05,
|
| 630 |
-
"step": 830
|
| 631 |
-
},
|
| 632 |
-
{
|
| 633 |
-
"epoch": 0.24859425865640722,
|
| 634 |
-
"grad_norm": 25.25,
|
| 635 |
-
"learning_rate": 0.00015851066728416618,
|
| 636 |
-
"loss": 7.7749,
|
| 637 |
-
"step": 840
|
| 638 |
-
},
|
| 639 |
-
{
|
| 640 |
-
"epoch": 0.25155371411660254,
|
| 641 |
-
"grad_norm": 1848.0,
|
| 642 |
-
"learning_rate": 0.00015743286626829437,
|
| 643 |
-
"loss": 7.915,
|
| 644 |
-
"step": 850
|
| 645 |
-
},
|
| 646 |
-
{
|
| 647 |
-
"epoch": 0.25451316957679787,
|
| 648 |
-
"grad_norm": 34.0,
|
| 649 |
-
"learning_rate": 0.00015634501616380967,
|
| 650 |
-
"loss": 7.951,
|
| 651 |
-
"step": 860
|
| 652 |
-
},
|
| 653 |
-
{
|
| 654 |
-
"epoch": 0.2574726250369932,
|
| 655 |
-
"grad_norm": 53.25,
|
| 656 |
-
"learning_rate": 0.00015524730731298134,
|
| 657 |
-
"loss": 7.691,
|
| 658 |
-
"step": 870
|
| 659 |
-
},
|
| 660 |
-
{
|
| 661 |
-
"epoch": 0.2604320804971885,
|
| 662 |
-
"grad_norm": 148.0,
|
| 663 |
-
"learning_rate": 0.0001541399317830738,
|
| 664 |
-
"loss": 7.915,
|
| 665 |
-
"step": 880
|
| 666 |
-
},
|
| 667 |
-
{
|
| 668 |
-
"epoch": 0.26339153595738385,
|
| 669 |
-
"grad_norm": 78.0,
|
| 670 |
-
"learning_rate": 0.0001530230833327405,
|
| 671 |
-
"loss": 7.844,
|
| 672 |
-
"step": 890
|
| 673 |
-
},
|
| 674 |
-
{
|
| 675 |
-
"epoch": 0.2663509914175792,
|
| 676 |
-
"grad_norm": 86.0,
|
| 677 |
-
"learning_rate": 0.00015189695737812152,
|
| 678 |
-
"loss": 7.5695,
|
| 679 |
-
"step": 900
|
| 680 |
-
},
|
| 681 |
-
{
|
| 682 |
-
"epoch": 0.2693104468777745,
|
| 683 |
-
"grad_norm": 65.0,
|
| 684 |
-
"learning_rate": 0.0001507617509586517,
|
| 685 |
-
"loss": 7.9703,
|
| 686 |
-
"step": 910
|
| 687 |
-
},
|
| 688 |
-
{
|
| 689 |
-
"epoch": 0.2722699023379698,
|
| 690 |
-
"grad_norm": 23.375,
|
| 691 |
-
"learning_rate": 0.00014961766270258422,
|
| 692 |
-
"loss": 7.4996,
|
| 693 |
-
"step": 920
|
| 694 |
-
},
|
| 695 |
-
{
|
| 696 |
-
"epoch": 0.27522935779816515,
|
| 697 |
-
"grad_norm": 40.5,
|
| 698 |
-
"learning_rate": 0.00014846489279223652,
|
| 699 |
-
"loss": 7.7973,
|
| 700 |
-
"step": 930
|
| 701 |
-
},
|
| 702 |
-
{
|
| 703 |
-
"epoch": 0.2781888132583605,
|
| 704 |
-
"grad_norm": 512.0,
|
| 705 |
-
"learning_rate": 0.0001473036429289641,
|
| 706 |
-
"loss": 7.9165,
|
| 707 |
-
"step": 940
|
| 708 |
-
},
|
| 709 |
-
{
|
| 710 |
-
"epoch": 0.2811482687185558,
|
| 711 |
-
"grad_norm": 4320.0,
|
| 712 |
-
"learning_rate": 0.0001461341162978688,
|
| 713 |
-
"loss": 7.8394,
|
| 714 |
-
"step": 950
|
| 715 |
-
},
|
| 716 |
-
{
|
| 717 |
-
"epoch": 0.28410772417875113,
|
| 718 |
-
"grad_norm": 146.0,
|
| 719 |
-
"learning_rate": 0.00014495651753224705,
|
| 720 |
-
"loss": 8.26,
|
| 721 |
-
"step": 960
|
| 722 |
-
},
|
| 723 |
-
{
|
| 724 |
-
"epoch": 0.28706717963894646,
|
| 725 |
-
"grad_norm": 132.0,
|
| 726 |
-
"learning_rate": 0.00014377105267778518,
|
| 727 |
-
"loss": 8.2372,
|
| 728 |
-
"step": 970
|
| 729 |
-
},
|
| 730 |
-
{
|
| 731 |
-
"epoch": 0.2900266350991418,
|
| 732 |
-
"grad_norm": 117.5,
|
| 733 |
-
"learning_rate": 0.00014257792915650728,
|
| 734 |
-
"loss": 8.0396,
|
| 735 |
-
"step": 980
|
| 736 |
-
},
|
| 737 |
-
{
|
| 738 |
-
"epoch": 0.2929860905593371,
|
| 739 |
-
"grad_norm": 424.0,
|
| 740 |
-
"learning_rate": 0.00014137735573048233,
|
| 741 |
-
"loss": 8.1126,
|
| 742 |
-
"step": 990
|
| 743 |
-
},
|
| 744 |
-
{
|
| 745 |
-
"epoch": 0.2959455460195324,
|
| 746 |
-
"grad_norm": 2224.0,
|
| 747 |
-
"learning_rate": 0.00014016954246529696,
|
| 748 |
-
"loss": 8.3142,
|
| 749 |
-
"step": 1000
|
| 750 |
-
},
|
| 751 |
-
{
|
| 752 |
-
"epoch": 0.2959455460195324,
|
| 753 |
-
"eval_loss": 8.17757797241211,
|
| 754 |
-
"eval_runtime": 9.0278,
|
| 755 |
-
"eval_samples_per_second": 166.375,
|
| 756 |
-
"eval_steps_per_second": 41.649,
|
| 757 |
-
"step": 1000
|
| 758 |
-
},
|
| 759 |
-
{
|
| 760 |
-
"epoch": 0.2989050014797277,
|
| 761 |
-
"grad_norm": 100.5,
|
| 762 |
-
"learning_rate": 0.00013895470069330004,
|
| 763 |
-
"loss": 7.9549,
|
| 764 |
-
"step": 1010
|
| 765 |
-
},
|
| 766 |
-
{
|
| 767 |
-
"epoch": 0.30186445693992303,
|
| 768 |
-
"grad_norm": 79.0,
|
| 769 |
-
"learning_rate": 0.00013773304297662559,
|
| 770 |
-
"loss": 7.8468,
|
| 771 |
-
"step": 1020
|
| 772 |
-
},
|
| 773 |
-
{
|
| 774 |
-
"epoch": 0.30482391240011836,
|
| 775 |
-
"grad_norm": 308.0,
|
| 776 |
-
"learning_rate": 0.00013650478307000057,
|
| 777 |
-
"loss": 7.7471,
|
| 778 |
-
"step": 1030
|
| 779 |
-
},
|
| 780 |
-
{
|
| 781 |
-
"epoch": 0.3077833678603137,
|
| 782 |
-
"grad_norm": 165.0,
|
| 783 |
-
"learning_rate": 0.00013527013588334415,
|
| 784 |
-
"loss": 7.8435,
|
| 785 |
-
"step": 1040
|
| 786 |
-
},
|
| 787 |
-
{
|
| 788 |
-
"epoch": 0.310742823320509,
|
| 789 |
-
"grad_norm": 229.0,
|
| 790 |
-
"learning_rate": 0.00013402931744416433,
|
| 791 |
-
"loss": 7.9423,
|
| 792 |
-
"step": 1050
|
| 793 |
-
},
|
| 794 |
-
{
|
| 795 |
-
"epoch": 0.31370227878070434,
|
| 796 |
-
"grad_norm": 584.0,
|
| 797 |
-
"learning_rate": 0.00013278254485975976,
|
| 798 |
-
"loss": 9.4635,
|
| 799 |
-
"step": 1060
|
| 800 |
-
},
|
| 801 |
-
{
|
| 802 |
-
"epoch": 0.31666173424089966,
|
| 803 |
-
"grad_norm": 1128.0,
|
| 804 |
-
"learning_rate": 0.00013153003627923218,
|
| 805 |
-
"loss": 8.107,
|
| 806 |
-
"step": 1070
|
| 807 |
-
},
|
| 808 |
-
{
|
| 809 |
-
"epoch": 0.319621189701095,
|
| 810 |
-
"grad_norm": 123.5,
|
| 811 |
-
"learning_rate": 0.00013027201085531634,
|
| 812 |
-
"loss": 8.1185,
|
| 813 |
-
"step": 1080
|
| 814 |
-
},
|
| 815 |
-
{
|
| 816 |
-
"epoch": 0.3225806451612903,
|
| 817 |
-
"grad_norm": 95.5,
|
| 818 |
-
"learning_rate": 0.00012900868870603503,
|
| 819 |
-
"loss": 7.9646,
|
| 820 |
-
"step": 1090
|
| 821 |
-
},
|
| 822 |
-
{
|
| 823 |
-
"epoch": 0.32554010062148564,
|
| 824 |
-
"grad_norm": 350.0,
|
| 825 |
-
"learning_rate": 0.00012774029087618446,
|
| 826 |
-
"loss": 8.2899,
|
| 827 |
-
"step": 1100
|
| 828 |
-
},
|
| 829 |
-
{
|
| 830 |
-
"epoch": 0.32849955608168097,
|
| 831 |
-
"grad_norm": 70.0,
|
| 832 |
-
"learning_rate": 0.00012646703929865817,
|
| 833 |
-
"loss": 7.8757,
|
| 834 |
-
"step": 1110
|
| 835 |
-
},
|
| 836 |
-
{
|
| 837 |
-
"epoch": 0.3314590115418763,
|
| 838 |
-
"grad_norm": 117.0,
|
| 839 |
-
"learning_rate": 0.00012518915675561483,
|
| 840 |
-
"loss": 7.6223,
|
| 841 |
-
"step": 1120
|
| 842 |
-
},
|
| 843 |
-
{
|
| 844 |
-
"epoch": 0.3344184670020716,
|
| 845 |
-
"grad_norm": 294.0,
|
| 846 |
-
"learning_rate": 0.00012390686683949798,
|
| 847 |
-
"loss": 7.7403,
|
| 848 |
-
"step": 1130
|
| 849 |
-
},
|
| 850 |
-
{
|
| 851 |
-
"epoch": 0.33737792246226694,
|
| 852 |
-
"grad_norm": 205.0,
|
| 853 |
-
"learning_rate": 0.00012262039391391404,
|
| 854 |
-
"loss": 7.7307,
|
| 855 |
-
"step": 1140
|
| 856 |
-
},
|
| 857 |
-
{
|
| 858 |
-
"epoch": 0.34033737792246227,
|
| 859 |
-
"grad_norm": 588.0,
|
| 860 |
-
"learning_rate": 0.0001213299630743747,
|
| 861 |
-
"loss": 7.8997,
|
| 862 |
-
"step": 1150
|
| 863 |
-
},
|
| 864 |
-
{
|
| 865 |
-
"epoch": 0.3432968333826576,
|
| 866 |
-
"grad_norm": 29.75,
|
| 867 |
-
"learning_rate": 0.00012003580010891213,
|
| 868 |
-
"loss": 7.8493,
|
| 869 |
-
"step": 1160
|
| 870 |
-
},
|
| 871 |
-
{
|
| 872 |
-
"epoch": 0.3462562888428529,
|
| 873 |
-
"grad_norm": 50.75,
|
| 874 |
-
"learning_rate": 0.00011873813145857249,
|
| 875 |
-
"loss": 7.5136,
|
| 876 |
-
"step": 1170
|
| 877 |
-
},
|
| 878 |
-
{
|
| 879 |
-
"epoch": 0.34921574430304825,
|
| 880 |
-
"grad_norm": 59.25,
|
| 881 |
-
"learning_rate": 0.00011743718417779517,
|
| 882 |
-
"loss": 8.0157,
|
| 883 |
-
"step": 1180
|
| 884 |
-
},
|
| 885 |
-
{
|
| 886 |
-
"epoch": 0.3521751997632436,
|
| 887 |
-
"grad_norm": 108.5,
|
| 888 |
-
"learning_rate": 0.00011613318589468511,
|
| 889 |
-
"loss": 7.5891,
|
| 890 |
-
"step": 1190
|
| 891 |
-
},
|
| 892 |
-
{
|
| 893 |
-
"epoch": 0.3551346552234389,
|
| 894 |
-
"grad_norm": 280.0,
|
| 895 |
-
"learning_rate": 0.0001148263647711842,
|
| 896 |
-
"loss": 7.7884,
|
| 897 |
-
"step": 1200
|
| 898 |
-
},
|
| 899 |
-
{
|
| 900 |
-
"epoch": 0.3551346552234389,
|
| 901 |
-
"eval_loss": 8.000994682312012,
|
| 902 |
-
"eval_runtime": 9.0516,
|
| 903 |
-
"eval_samples_per_second": 165.937,
|
| 904 |
-
"eval_steps_per_second": 41.539,
|
| 905 |
-
"step": 1200
|
| 906 |
-
},
|
| 907 |
-
{
|
| 908 |
-
"epoch": 0.3580941106836342,
|
| 909 |
-
"grad_norm": 30.125,
|
| 910 |
-
"learning_rate": 0.0001135169494631497,
|
| 911 |
-
"loss": 8.0308,
|
| 912 |
-
"step": 1210
|
| 913 |
-
},
|
| 914 |
-
{
|
| 915 |
-
"epoch": 0.36105356614382955,
|
| 916 |
-
"grad_norm": 37.75,
|
| 917 |
-
"learning_rate": 0.00011220516908034601,
|
| 918 |
-
"loss": 7.7083,
|
| 919 |
-
"step": 1220
|
| 920 |
-
},
|
| 921 |
-
{
|
| 922 |
-
"epoch": 0.3640130216040249,
|
| 923 |
-
"grad_norm": 48.75,
|
| 924 |
-
"learning_rate": 0.00011089125314635726,
|
| 925 |
-
"loss": 7.7182,
|
| 926 |
-
"step": 1230
|
| 927 |
-
},
|
| 928 |
-
{
|
| 929 |
-
"epoch": 0.3669724770642202,
|
| 930 |
-
"grad_norm": 39.5,
|
| 931 |
-
"learning_rate": 0.00010957543155842702,
|
| 932 |
-
"loss": 7.6788,
|
| 933 |
-
"step": 1240
|
| 934 |
-
},
|
| 935 |
-
{
|
| 936 |
-
"epoch": 0.36993193252441553,
|
| 937 |
-
"grad_norm": 46.75,
|
| 938 |
-
"learning_rate": 0.00010825793454723325,
|
| 939 |
-
"loss": 7.9517,
|
| 940 |
-
"step": 1250
|
| 941 |
-
},
|
| 942 |
-
{
|
| 943 |
-
"epoch": 0.37289138798461086,
|
| 944 |
-
"grad_norm": 33.5,
|
| 945 |
-
"learning_rate": 0.00010693899263660441,
|
| 946 |
-
"loss": 7.821,
|
| 947 |
-
"step": 1260
|
| 948 |
-
},
|
| 949 |
-
{
|
| 950 |
-
"epoch": 0.3758508434448062,
|
| 951 |
-
"grad_norm": 51.25,
|
| 952 |
-
"learning_rate": 0.00010561883660318455,
|
| 953 |
-
"loss": 7.7532,
|
| 954 |
-
"step": 1270
|
| 955 |
-
},
|
| 956 |
-
{
|
| 957 |
-
"epoch": 0.37881029890500145,
|
| 958 |
-
"grad_norm": 82.0,
|
| 959 |
-
"learning_rate": 0.00010429769743605407,
|
| 960 |
-
"loss": 7.6321,
|
| 961 |
-
"step": 1280
|
| 962 |
-
},
|
| 963 |
-
{
|
| 964 |
-
"epoch": 0.3817697543651968,
|
| 965 |
-
"grad_norm": 38.5,
|
| 966 |
-
"learning_rate": 0.00010297580629631325,
|
| 967 |
-
"loss": 7.5741,
|
| 968 |
-
"step": 1290
|
| 969 |
-
},
|
| 970 |
-
{
|
| 971 |
-
"epoch": 0.3847292098253921,
|
| 972 |
-
"grad_norm": 292.0,
|
| 973 |
-
"learning_rate": 0.00010165339447663587,
|
| 974 |
-
"loss": 7.2796,
|
| 975 |
-
"step": 1300
|
| 976 |
-
},
|
| 977 |
-
{
|
| 978 |
-
"epoch": 0.38768866528558743,
|
| 979 |
-
"grad_norm": 76.5,
|
| 980 |
-
"learning_rate": 0.00010033069336079952,
|
| 981 |
-
"loss": 7.926,
|
| 982 |
-
"step": 1310
|
| 983 |
-
},
|
| 984 |
-
{
|
| 985 |
-
"epoch": 0.39064812074578276,
|
| 986 |
-
"grad_norm": 64.0,
|
| 987 |
-
"learning_rate": 9.900793438320037e-05,
|
| 988 |
-
"loss": 7.5464,
|
| 989 |
-
"step": 1320
|
| 990 |
-
},
|
| 991 |
-
{
|
| 992 |
-
"epoch": 0.3936075762059781,
|
| 993 |
-
"grad_norm": 120.5,
|
| 994 |
-
"learning_rate": 9.768534898835862e-05,
|
| 995 |
-
"loss": 7.5249,
|
| 996 |
-
"step": 1330
|
| 997 |
-
},
|
| 998 |
-
{
|
| 999 |
-
"epoch": 0.3965670316661734,
|
| 1000 |
-
"grad_norm": 108.5,
|
| 1001 |
-
"learning_rate": 9.636316859042259e-05,
|
| 1002 |
-
"loss": 7.4919,
|
| 1003 |
-
"step": 1340
|
| 1004 |
-
},
|
| 1005 |
-
{
|
| 1006 |
-
"epoch": 0.39952648712636873,
|
| 1007 |
-
"grad_norm": 972.0,
|
| 1008 |
-
"learning_rate": 9.504162453267777e-05,
|
| 1009 |
-
"loss": 7.332,
|
| 1010 |
-
"step": 1350
|
| 1011 |
-
},
|
| 1012 |
-
{
|
| 1013 |
-
"epoch": 0.40248594258656406,
|
| 1014 |
-
"grad_norm": 328.0,
|
| 1015 |
-
"learning_rate": 9.372094804706867e-05,
|
| 1016 |
-
"loss": 7.6553,
|
| 1017 |
-
"step": 1360
|
| 1018 |
-
},
|
| 1019 |
-
{
|
| 1020 |
-
"epoch": 0.4054453980467594,
|
| 1021 |
-
"grad_norm": 154.0,
|
| 1022 |
-
"learning_rate": 9.24013702137397e-05,
|
| 1023 |
-
"loss": 7.5773,
|
| 1024 |
-
"step": 1370
|
| 1025 |
-
},
|
| 1026 |
-
{
|
| 1027 |
-
"epoch": 0.4084048535069547,
|
| 1028 |
-
"grad_norm": 43.75,
|
| 1029 |
-
"learning_rate": 9.108312192060298e-05,
|
| 1030 |
-
"loss": 7.5746,
|
| 1031 |
-
"step": 1380
|
| 1032 |
-
},
|
| 1033 |
-
{
|
| 1034 |
-
"epoch": 0.41136430896715004,
|
| 1035 |
-
"grad_norm": 310.0,
|
| 1036 |
-
"learning_rate": 8.97664338229395e-05,
|
| 1037 |
-
"loss": 7.6845,
|
| 1038 |
-
"step": 1390
|
| 1039 |
-
},
|
| 1040 |
-
{
|
| 1041 |
-
"epoch": 0.41432376442734536,
|
| 1042 |
-
"grad_norm": 336.0,
|
| 1043 |
-
"learning_rate": 8.845153630304139e-05,
|
| 1044 |
-
"loss": 7.449,
|
| 1045 |
-
"step": 1400
|
| 1046 |
-
},
|
| 1047 |
-
{
|
| 1048 |
-
"epoch": 0.41432376442734536,
|
| 1049 |
-
"eval_loss": 7.618994235992432,
|
| 1050 |
-
"eval_runtime": 9.0496,
|
| 1051 |
-
"eval_samples_per_second": 165.975,
|
| 1052 |
-
"eval_steps_per_second": 41.549,
|
| 1053 |
-
"step": 1400
|
| 1054 |
-
},
|
| 1055 |
-
{
|
| 1056 |
-
"epoch": 0.4172832198875407,
|
| 1057 |
-
"grad_norm": 39.5,
|
| 1058 |
-
"learning_rate": 8.713865942990141e-05,
|
| 1059 |
-
"loss": 7.6821,
|
| 1060 |
-
"step": 1410
|
| 1061 |
-
},
|
| 1062 |
-
{
|
| 1063 |
-
"epoch": 0.420242675347736,
|
| 1064 |
-
"grad_norm": 76.5,
|
| 1065 |
-
"learning_rate": 8.582803291895758e-05,
|
| 1066 |
-
"loss": 7.5631,
|
| 1067 |
-
"step": 1420
|
| 1068 |
-
},
|
| 1069 |
-
{
|
| 1070 |
-
"epoch": 0.42320213080793134,
|
| 1071 |
-
"grad_norm": 167.0,
|
| 1072 |
-
"learning_rate": 8.451988609189987e-05,
|
| 1073 |
-
"loss": 7.7359,
|
| 1074 |
-
"step": 1430
|
| 1075 |
-
},
|
| 1076 |
-
{
|
| 1077 |
-
"epoch": 0.42616158626812667,
|
| 1078 |
-
"grad_norm": 268.0,
|
| 1079 |
-
"learning_rate": 8.321444783654524e-05,
|
| 1080 |
-
"loss": 7.4941,
|
| 1081 |
-
"step": 1440
|
| 1082 |
-
},
|
| 1083 |
-
{
|
| 1084 |
-
"epoch": 0.429121041728322,
|
| 1085 |
-
"grad_norm": 103.5,
|
| 1086 |
-
"learning_rate": 8.191194656678904e-05,
|
| 1087 |
-
"loss": 7.4398,
|
| 1088 |
-
"step": 1450
|
| 1089 |
-
},
|
| 1090 |
-
{
|
| 1091 |
-
"epoch": 0.4320804971885173,
|
| 1092 |
-
"grad_norm": 66.0,
|
| 1093 |
-
"learning_rate": 8.061261018263919e-05,
|
| 1094 |
-
"loss": 7.5629,
|
| 1095 |
-
"step": 1460
|
| 1096 |
-
},
|
| 1097 |
-
{
|
| 1098 |
-
"epoch": 0.43503995264871265,
|
| 1099 |
-
"grad_norm": 24.0,
|
| 1100 |
-
"learning_rate": 7.931666603034033e-05,
|
| 1101 |
-
"loss": 7.5025,
|
| 1102 |
-
"step": 1470
|
| 1103 |
-
},
|
| 1104 |
-
{
|
| 1105 |
-
"epoch": 0.437999408108908,
|
| 1106 |
-
"grad_norm": 142.0,
|
| 1107 |
-
"learning_rate": 7.80243408625947e-05,
|
| 1108 |
-
"loss": 7.4416,
|
| 1109 |
-
"step": 1480
|
| 1110 |
-
},
|
| 1111 |
-
{
|
| 1112 |
-
"epoch": 0.4409588635691033,
|
| 1113 |
-
"grad_norm": 1488.0,
|
| 1114 |
-
"learning_rate": 7.673586079888698e-05,
|
| 1115 |
-
"loss": 7.4872,
|
| 1116 |
-
"step": 1490
|
| 1117 |
-
},
|
| 1118 |
-
{
|
| 1119 |
-
"epoch": 0.4439183190292986,
|
| 1120 |
-
"grad_norm": 892.0,
|
| 1121 |
-
"learning_rate": 7.54514512859201e-05,
|
| 1122 |
-
"loss": 7.4681,
|
| 1123 |
-
"step": 1500
|
| 1124 |
-
},
|
| 1125 |
-
{
|
| 1126 |
-
"epoch": 0.44687777448949395,
|
| 1127 |
-
"grad_norm": 92.5,
|
| 1128 |
-
"learning_rate": 7.417133705816837e-05,
|
| 1129 |
-
"loss": 7.4869,
|
| 1130 |
-
"step": 1510
|
| 1131 |
-
},
|
| 1132 |
-
{
|
| 1133 |
-
"epoch": 0.4498372299496893,
|
| 1134 |
-
"grad_norm": 160.0,
|
| 1135 |
-
"learning_rate": 7.289574209855559e-05,
|
| 1136 |
-
"loss": 7.7108,
|
| 1137 |
-
"step": 1520
|
| 1138 |
-
},
|
| 1139 |
-
{
|
| 1140 |
-
"epoch": 0.4527966854098846,
|
| 1141 |
-
"grad_norm": 211.0,
|
| 1142 |
-
"learning_rate": 7.16248895992645e-05,
|
| 1143 |
-
"loss": 7.5492,
|
| 1144 |
-
"step": 1530
|
| 1145 |
-
},
|
| 1146 |
-
{
|
| 1147 |
-
"epoch": 0.45575614087007993,
|
| 1148 |
-
"grad_norm": 135.0,
|
| 1149 |
-
"learning_rate": 7.035900192268464e-05,
|
| 1150 |
-
"loss": 7.409,
|
| 1151 |
-
"step": 1540
|
| 1152 |
-
},
|
| 1153 |
-
{
|
| 1154 |
-
"epoch": 0.45871559633027525,
|
| 1155 |
-
"grad_norm": 124.5,
|
| 1156 |
-
"learning_rate": 6.909830056250527e-05,
|
| 1157 |
-
"loss": 7.3087,
|
| 1158 |
-
"step": 1550
|
| 1159 |
-
},
|
| 1160 |
-
{
|
| 1161 |
-
"epoch": 0.4616750517904706,
|
| 1162 |
-
"grad_norm": 133.0,
|
| 1163 |
-
"learning_rate": 6.784300610496048e-05,
|
| 1164 |
-
"loss": 7.9377,
|
| 1165 |
-
"step": 1560
|
| 1166 |
-
},
|
| 1167 |
-
{
|
| 1168 |
-
"epoch": 0.46463450725066585,
|
| 1169 |
-
"grad_norm": 225.0,
|
| 1170 |
-
"learning_rate": 6.65933381902329e-05,
|
| 1171 |
-
"loss": 7.5162,
|
| 1172 |
-
"step": 1570
|
| 1173 |
-
},
|
| 1174 |
-
{
|
| 1175 |
-
"epoch": 0.4675939627108612,
|
| 1176 |
-
"grad_norm": 186.0,
|
| 1177 |
-
"learning_rate": 6.534951547402322e-05,
|
| 1178 |
-
"loss": 7.7924,
|
| 1179 |
-
"step": 1580
|
| 1180 |
-
},
|
| 1181 |
-
{
|
| 1182 |
-
"epoch": 0.4705534181710565,
|
| 1183 |
-
"grad_norm": 404.0,
|
| 1184 |
-
"learning_rate": 6.411175558929152e-05,
|
| 1185 |
-
"loss": 7.579,
|
| 1186 |
-
"step": 1590
|
| 1187 |
-
},
|
| 1188 |
-
{
|
| 1189 |
-
"epoch": 0.47351287363125183,
|
| 1190 |
-
"grad_norm": 600.0,
|
| 1191 |
-
"learning_rate": 6.28802751081779e-05,
|
| 1192 |
-
"loss": 7.3673,
|
| 1193 |
-
"step": 1600
|
| 1194 |
-
},
|
| 1195 |
-
{
|
| 1196 |
-
"epoch": 0.47351287363125183,
|
| 1197 |
-
"eval_loss": 7.5222601890563965,
|
| 1198 |
-
"eval_runtime": 10.7021,
|
| 1199 |
-
"eval_samples_per_second": 140.346,
|
| 1200 |
-
"eval_steps_per_second": 35.133,
|
| 1201 |
-
"step": 1600
|
| 1202 |
-
},
|
| 1203 |
-
{
|
| 1204 |
-
"epoch": 0.47647232909144716,
|
| 1205 |
-
"grad_norm": 306.0,
|
| 1206 |
-
"learning_rate": 6.165528950410884e-05,
|
| 1207 |
-
"loss": 7.6311,
|
| 1208 |
-
"step": 1610
|
| 1209 |
-
},
|
| 1210 |
-
{
|
| 1211 |
-
"epoch": 0.4794317845516425,
|
| 1212 |
-
"grad_norm": 1808.0,
|
| 1213 |
-
"learning_rate": 6.0437013114095195e-05,
|
| 1214 |
-
"loss": 7.5535,
|
| 1215 |
-
"step": 1620
|
| 1216 |
-
},
|
| 1217 |
-
{
|
| 1218 |
-
"epoch": 0.4823912400118378,
|
| 1219 |
-
"grad_norm": 151.0,
|
| 1220 |
-
"learning_rate": 5.922565910122967e-05,
|
| 1221 |
-
"loss": 7.4998,
|
| 1222 |
-
"step": 1630
|
| 1223 |
-
},
|
| 1224 |
-
{
|
| 1225 |
-
"epoch": 0.48535069547203313,
|
| 1226 |
-
"grad_norm": 792.0,
|
| 1227 |
-
"learning_rate": 5.8021439417389444e-05,
|
| 1228 |
-
"loss": 7.2634,
|
| 1229 |
-
"step": 1640
|
| 1230 |
-
},
|
| 1231 |
-
{
|
| 1232 |
-
"epoch": 0.48831015093222846,
|
| 1233 |
-
"grad_norm": 80.5,
|
| 1234 |
-
"learning_rate": 5.6824564766150726e-05,
|
| 1235 |
-
"loss": 7.0989,
|
| 1236 |
-
"step": 1650
|
| 1237 |
-
},
|
| 1238 |
-
{
|
| 1239 |
-
"epoch": 0.4912696063924238,
|
| 1240 |
-
"grad_norm": 172.0,
|
| 1241 |
-
"learning_rate": 5.563524456592163e-05,
|
| 1242 |
-
"loss": 7.6032,
|
| 1243 |
-
"step": 1660
|
| 1244 |
-
},
|
| 1245 |
-
{
|
| 1246 |
-
"epoch": 0.4942290618526191,
|
| 1247 |
-
"grad_norm": 348.0,
|
| 1248 |
-
"learning_rate": 5.4453686913300074e-05,
|
| 1249 |
-
"loss": 7.2613,
|
| 1250 |
-
"step": 1670
|
| 1251 |
-
},
|
| 1252 |
-
{
|
| 1253 |
-
"epoch": 0.49718851731281444,
|
| 1254 |
-
"grad_norm": 54.75,
|
| 1255 |
-
"learning_rate": 5.328009854666303e-05,
|
| 1256 |
-
"loss": 7.434,
|
| 1257 |
-
"step": 1680
|
| 1258 |
-
},
|
| 1259 |
-
{
|
| 1260 |
-
"epoch": 0.5001479727730098,
|
| 1261 |
-
"grad_norm": 122.0,
|
| 1262 |
-
"learning_rate": 5.2114684809993044e-05,
|
| 1263 |
-
"loss": 7.3746,
|
| 1264 |
-
"step": 1690
|
| 1265 |
-
},
|
| 1266 |
-
{
|
| 1267 |
-
"epoch": 0.5031074282332051,
|
| 1268 |
-
"grad_norm": 72.0,
|
| 1269 |
-
"learning_rate": 5.095764961694922e-05,
|
| 1270 |
-
"loss": 7.5639,
|
| 1271 |
-
"step": 1700
|
| 1272 |
-
},
|
| 1273 |
-
{
|
| 1274 |
-
"epoch": 0.5060668836934004,
|
| 1275 |
-
"grad_norm": 59.5,
|
| 1276 |
-
"learning_rate": 4.980919541518796e-05,
|
| 1277 |
-
"loss": 7.8365,
|
| 1278 |
-
"step": 1710
|
| 1279 |
-
},
|
| 1280 |
-
{
|
| 1281 |
-
"epoch": 0.5090263391535957,
|
| 1282 |
-
"grad_norm": 113.5,
|
| 1283 |
-
"learning_rate": 4.866952315094088e-05,
|
| 1284 |
-
"loss": 7.4722,
|
| 1285 |
-
"step": 1720
|
| 1286 |
-
},
|
| 1287 |
-
{
|
| 1288 |
-
"epoch": 0.511985794613791,
|
| 1289 |
-
"grad_norm": 92.0,
|
| 1290 |
-
"learning_rate": 4.753883223385467e-05,
|
| 1291 |
-
"loss": 7.6937,
|
| 1292 |
-
"step": 1730
|
| 1293 |
-
},
|
| 1294 |
-
{
|
| 1295 |
-
"epoch": 0.5149452500739864,
|
| 1296 |
-
"grad_norm": 178.0,
|
| 1297 |
-
"learning_rate": 4.6417320502100316e-05,
|
| 1298 |
-
"loss": 7.4405,
|
| 1299 |
-
"step": 1740
|
| 1300 |
-
},
|
| 1301 |
-
{
|
| 1302 |
-
"epoch": 0.5179047055341817,
|
| 1303 |
-
"grad_norm": 72.5,
|
| 1304 |
-
"learning_rate": 4.530518418775733e-05,
|
| 1305 |
-
"loss": 7.4937,
|
| 1306 |
-
"step": 1750
|
| 1307 |
-
},
|
| 1308 |
-
{
|
| 1309 |
-
"epoch": 0.520864160994377,
|
| 1310 |
-
"grad_norm": 25.625,
|
| 1311 |
-
"learning_rate": 4.4202617882478405e-05,
|
| 1312 |
-
"loss": 7.9844,
|
| 1313 |
-
"step": 1760
|
| 1314 |
-
},
|
| 1315 |
-
{
|
| 1316 |
-
"epoch": 0.5238236164545723,
|
| 1317 |
-
"grad_norm": 86.5,
|
| 1318 |
-
"learning_rate": 4.310981450344189e-05,
|
| 1319 |
-
"loss": 7.3943,
|
| 1320 |
-
"step": 1770
|
| 1321 |
-
},
|
| 1322 |
-
{
|
| 1323 |
-
"epoch": 0.5267830719147677,
|
| 1324 |
-
"grad_norm": 229.0,
|
| 1325 |
-
"learning_rate": 4.2026965259596666e-05,
|
| 1326 |
-
"loss": 7.6026,
|
| 1327 |
-
"step": 1780
|
| 1328 |
-
},
|
| 1329 |
-
{
|
| 1330 |
-
"epoch": 0.529742527374963,
|
| 1331 |
-
"grad_norm": 35.0,
|
| 1332 |
-
"learning_rate": 4.0954259618206295e-05,
|
| 1333 |
-
"loss": 7.4426,
|
| 1334 |
-
"step": 1790
|
| 1335 |
-
},
|
| 1336 |
-
{
|
| 1337 |
-
"epoch": 0.5327019828351583,
|
| 1338 |
-
"grad_norm": 110.5,
|
| 1339 |
-
"learning_rate": 3.9891885271697496e-05,
|
| 1340 |
-
"loss": 7.7448,
|
| 1341 |
-
"step": 1800
|
| 1342 |
-
},
|
| 1343 |
-
{
|
| 1344 |
-
"epoch": 0.5327019828351583,
|
| 1345 |
-
"eval_loss": 7.529196739196777,
|
| 1346 |
-
"eval_runtime": 9.1371,
|
| 1347 |
-
"eval_samples_per_second": 164.385,
|
| 1348 |
-
"eval_steps_per_second": 41.151,
|
| 1349 |
-
"step": 1800
|
| 1350 |
-
},
|
| 1351 |
-
{
|
| 1352 |
-
"epoch": 0.5356614382953536,
|
| 1353 |
-
"grad_norm": 63.25,
|
| 1354 |
-
"learning_rate": 3.884002810481958e-05,
|
| 1355 |
-
"loss": 7.6213,
|
| 1356 |
-
"step": 1810
|
| 1357 |
-
},
|
| 1358 |
-
{
|
| 1359 |
-
"epoch": 0.538620893755549,
|
| 1360 |
-
"grad_norm": 308.0,
|
| 1361 |
-
"learning_rate": 3.779887216211995e-05,
|
| 1362 |
-
"loss": 7.3711,
|
| 1363 |
-
"step": 1820
|
| 1364 |
-
},
|
| 1365 |
-
{
|
| 1366 |
-
"epoch": 0.5415803492157443,
|
| 1367 |
-
"grad_norm": 75.5,
|
| 1368 |
-
"learning_rate": 3.676859961574162e-05,
|
| 1369 |
-
"loss": 7.2565,
|
| 1370 |
-
"step": 1830
|
| 1371 |
-
},
|
| 1372 |
-
{
|
| 1373 |
-
"epoch": 0.5445398046759397,
|
| 1374 |
-
"grad_norm": 85.5,
|
| 1375 |
-
"learning_rate": 3.574939073354838e-05,
|
| 1376 |
-
"loss": 7.5128,
|
| 1377 |
-
"step": 1840
|
| 1378 |
-
},
|
| 1379 |
-
{
|
| 1380 |
-
"epoch": 0.5474992601361349,
|
| 1381 |
-
"grad_norm": 151.0,
|
| 1382 |
-
"learning_rate": 3.4741423847583134e-05,
|
| 1383 |
-
"loss": 7.4537,
|
| 1384 |
-
"step": 1850
|
| 1385 |
-
},
|
| 1386 |
-
{
|
| 1387 |
-
"epoch": 0.5504587155963303,
|
| 1388 |
-
"grad_norm": 206.0,
|
| 1389 |
-
"learning_rate": 3.3744875322865034e-05,
|
| 1390 |
-
"loss": 7.6777,
|
| 1391 |
-
"step": 1860
|
| 1392 |
-
},
|
| 1393 |
-
{
|
| 1394 |
-
"epoch": 0.5534181710565256,
|
| 1395 |
-
"grad_norm": 51.0,
|
| 1396 |
-
"learning_rate": 3.275991952653054e-05,
|
| 1397 |
-
"loss": 7.3127,
|
| 1398 |
-
"step": 1870
|
| 1399 |
-
},
|
| 1400 |
-
{
|
| 1401 |
-
"epoch": 0.556377626516721,
|
| 1402 |
-
"grad_norm": 254.0,
|
| 1403 |
-
"learning_rate": 3.178672879732435e-05,
|
| 1404 |
-
"loss": 7.5413,
|
| 1405 |
-
"step": 1880
|
| 1406 |
-
},
|
| 1407 |
-
{
|
| 1408 |
-
"epoch": 0.5593370819769162,
|
| 1409 |
-
"grad_norm": 510.0,
|
| 1410 |
-
"learning_rate": 3.0825473415445074e-05,
|
| 1411 |
-
"loss": 7.3452,
|
| 1412 |
-
"step": 1890
|
| 1413 |
-
},
|
| 1414 |
-
{
|
| 1415 |
-
"epoch": 0.5622965374371116,
|
| 1416 |
-
"grad_norm": 972.0,
|
| 1417 |
-
"learning_rate": 2.9876321572751144e-05,
|
| 1418 |
-
"loss": 7.8002,
|
| 1419 |
-
"step": 1900
|
| 1420 |
-
},
|
| 1421 |
-
{
|
| 1422 |
-
"epoch": 0.5652559928973069,
|
| 1423 |
-
"grad_norm": 135.0,
|
| 1424 |
-
"learning_rate": 2.8939439343332086e-05,
|
| 1425 |
-
"loss": 7.638,
|
| 1426 |
-
"step": 1910
|
| 1427 |
-
},
|
| 1428 |
-
{
|
| 1429 |
-
"epoch": 0.5682154483575023,
|
| 1430 |
-
"grad_norm": 91.0,
|
| 1431 |
-
"learning_rate": 2.8014990654450325e-05,
|
| 1432 |
-
"loss": 7.1467,
|
| 1433 |
-
"step": 1920
|
| 1434 |
-
},
|
| 1435 |
-
{
|
| 1436 |
-
"epoch": 0.5711749038176975,
|
| 1437 |
-
"grad_norm": 189.0,
|
| 1438 |
-
"learning_rate": 2.7103137257858868e-05,
|
| 1439 |
-
"loss": 7.1859,
|
| 1440 |
-
"step": 1930
|
| 1441 |
-
},
|
| 1442 |
-
{
|
| 1443 |
-
"epoch": 0.5741343592778929,
|
| 1444 |
-
"grad_norm": 82.0,
|
| 1445 |
-
"learning_rate": 2.6204038701499056e-05,
|
| 1446 |
-
"loss": 7.5085,
|
| 1447 |
-
"step": 1940
|
| 1448 |
-
},
|
| 1449 |
-
{
|
| 1450 |
-
"epoch": 0.5770938147380882,
|
| 1451 |
-
"grad_norm": 344.0,
|
| 1452 |
-
"learning_rate": 2.5317852301584643e-05,
|
| 1453 |
-
"loss": 7.0502,
|
| 1454 |
-
"step": 1950
|
| 1455 |
-
},
|
| 1456 |
-
{
|
| 1457 |
-
"epoch": 0.5800532701982836,
|
| 1458 |
-
"grad_norm": 168.0,
|
| 1459 |
-
"learning_rate": 2.4444733115075823e-05,
|
| 1460 |
-
"loss": 7.6417,
|
| 1461 |
-
"step": 1960
|
| 1462 |
-
},
|
| 1463 |
-
{
|
| 1464 |
-
"epoch": 0.5830127256584788,
|
| 1465 |
-
"grad_norm": 77.5,
|
| 1466 |
-
"learning_rate": 2.3584833912548888e-05,
|
| 1467 |
-
"loss": 7.4358,
|
| 1468 |
-
"step": 1970
|
| 1469 |
-
},
|
| 1470 |
-
{
|
| 1471 |
-
"epoch": 0.5859721811186742,
|
| 1472 |
-
"grad_norm": 30.625,
|
| 1473 |
-
"learning_rate": 2.2738305151465645e-05,
|
| 1474 |
-
"loss": 7.329,
|
| 1475 |
-
"step": 1980
|
| 1476 |
-
},
|
| 1477 |
-
{
|
| 1478 |
-
"epoch": 0.5889316365788695,
|
| 1479 |
-
"grad_norm": 474.0,
|
| 1480 |
-
"learning_rate": 2.190529494984782e-05,
|
| 1481 |
-
"loss": 7.4855,
|
| 1482 |
-
"step": 1990
|
| 1483 |
-
},
|
| 1484 |
-
{
|
| 1485 |
-
"epoch": 0.5918910920390648,
|
| 1486 |
-
"grad_norm": 115.5,
|
| 1487 |
-
"learning_rate": 2.1085949060360654e-05,
|
| 1488 |
-
"loss": 7.6519,
|
| 1489 |
-
"step": 2000
|
| 1490 |
-
},
|
| 1491 |
-
{
|
| 1492 |
-
"epoch": 0.5918910920390648,
|
| 1493 |
-
"eval_loss": 7.52925443649292,
|
| 1494 |
-
"eval_runtime": 9.1246,
|
| 1495 |
-
"eval_samples_per_second": 164.61,
|
| 1496 |
-
"eval_steps_per_second": 41.207,
|
| 1497 |
-
"step": 2000
|
| 1498 |
-
},
|
| 1499 |
-
{
|
| 1500 |
-
"epoch": 0.5948505474992601,
|
| 1501 |
-
"grad_norm": 73.5,
|
| 1502 |
-
"learning_rate": 2.0280410844810428e-05,
|
| 1503 |
-
"loss": 7.5898,
|
| 1504 |
-
"step": 2010
|
| 1505 |
-
},
|
| 1506 |
-
{
|
| 1507 |
-
"epoch": 0.5978100029594554,
|
| 1508 |
-
"grad_norm": 29.625,
|
| 1509 |
-
"learning_rate": 1.9488821249060297e-05,
|
| 1510 |
-
"loss": 7.3119,
|
| 1511 |
-
"step": 2020
|
| 1512 |
-
},
|
| 1513 |
-
{
|
| 1514 |
-
"epoch": 0.6007694584196508,
|
| 1515 |
-
"grad_norm": 185.0,
|
| 1516 |
-
"learning_rate": 1.871131877836879e-05,
|
| 1517 |
-
"loss": 7.3793,
|
| 1518 |
-
"step": 2030
|
| 1519 |
-
},
|
| 1520 |
-
{
|
| 1521 |
-
"epoch": 0.6037289138798461,
|
| 1522 |
-
"grad_norm": 416.0,
|
| 1523 |
-
"learning_rate": 1.7948039473155554e-05,
|
| 1524 |
-
"loss": 7.2483,
|
| 1525 |
-
"step": 2040
|
| 1526 |
-
},
|
| 1527 |
-
{
|
| 1528 |
-
"epoch": 0.6066883693400414,
|
| 1529 |
-
"grad_norm": 2400.0,
|
| 1530 |
-
"learning_rate": 1.7199116885197995e-05,
|
| 1531 |
-
"loss": 7.5825,
|
| 1532 |
-
"step": 2050
|
| 1533 |
-
},
|
| 1534 |
-
{
|
| 1535 |
-
"epoch": 0.6096478248002367,
|
| 1536 |
-
"grad_norm": 138.0,
|
| 1537 |
-
"learning_rate": 1.646468205426377e-05,
|
| 1538 |
-
"loss": 7.5139,
|
| 1539 |
-
"step": 2060
|
| 1540 |
-
},
|
| 1541 |
-
{
|
| 1542 |
-
"epoch": 0.6126072802604321,
|
| 1543 |
-
"grad_norm": 1120.0,
|
| 1544 |
-
"learning_rate": 1.5744863485182537e-05,
|
| 1545 |
-
"loss": 7.4844,
|
| 1546 |
-
"step": 2070
|
| 1547 |
-
},
|
| 1548 |
-
{
|
| 1549 |
-
"epoch": 0.6155667357206274,
|
| 1550 |
-
"grad_norm": 114.0,
|
| 1551 |
-
"learning_rate": 1.5039787125361326e-05,
|
| 1552 |
-
"loss": 7.3547,
|
| 1553 |
-
"step": 2080
|
| 1554 |
-
},
|
| 1555 |
-
{
|
| 1556 |
-
"epoch": 0.6185261911808227,
|
| 1557 |
-
"grad_norm": 126.5,
|
| 1558 |
-
"learning_rate": 1.4349576342747462e-05,
|
| 1559 |
-
"loss": 7.3867,
|
| 1560 |
-
"step": 2090
|
| 1561 |
-
},
|
| 1562 |
-
{
|
| 1563 |
-
"epoch": 0.621485646641018,
|
| 1564 |
-
"grad_norm": 78.0,
|
| 1565 |
-
"learning_rate": 1.3674351904242611e-05,
|
| 1566 |
-
"loss": 7.194,
|
| 1567 |
-
"step": 2100
|
| 1568 |
-
},
|
| 1569 |
-
{
|
| 1570 |
-
"epoch": 0.6244451021012134,
|
| 1571 |
-
"grad_norm": 77.5,
|
| 1572 |
-
"learning_rate": 1.3014231954572287e-05,
|
| 1573 |
-
"loss": 7.3503,
|
| 1574 |
-
"step": 2110
|
| 1575 |
-
},
|
| 1576 |
-
{
|
| 1577 |
-
"epoch": 0.6274045575614087,
|
| 1578 |
-
"grad_norm": 230.0,
|
| 1579 |
-
"learning_rate": 1.2369331995613665e-05,
|
| 1580 |
-
"loss": 7.3932,
|
| 1581 |
-
"step": 2120
|
| 1582 |
-
},
|
| 1583 |
-
{
|
| 1584 |
-
"epoch": 0.630364013021604,
|
| 1585 |
-
"grad_norm": 61.0,
|
| 1586 |
-
"learning_rate": 1.173976486618631e-05,
|
| 1587 |
-
"loss": 7.4046,
|
| 1588 |
-
"step": 2130
|
| 1589 |
-
},
|
| 1590 |
-
{
|
| 1591 |
-
"epoch": 0.6333234684817993,
|
| 1592 |
-
"grad_norm": 113.5,
|
| 1593 |
-
"learning_rate": 1.1125640722308628e-05,
|
| 1594 |
-
"loss": 7.4239,
|
| 1595 |
-
"step": 2140
|
| 1596 |
-
},
|
| 1597 |
-
{
|
| 1598 |
-
"epoch": 0.6362829239419947,
|
| 1599 |
-
"grad_norm": 192.0,
|
| 1600 |
-
"learning_rate": 1.0527067017923654e-05,
|
| 1601 |
-
"loss": 7.8214,
|
| 1602 |
-
"step": 2150
|
| 1603 |
-
},
|
| 1604 |
-
{
|
| 1605 |
-
"epoch": 0.63924237940219,
|
| 1606 |
-
"grad_norm": 122.0,
|
| 1607 |
-
"learning_rate": 9.944148486097793e-06,
|
| 1608 |
-
"loss": 7.4993,
|
| 1609 |
-
"step": 2160
|
| 1610 |
-
},
|
| 1611 |
-
{
|
| 1612 |
-
"epoch": 0.6422018348623854,
|
| 1613 |
-
"grad_norm": 87.5,
|
| 1614 |
-
"learning_rate": 9.376987120695545e-06,
|
| 1615 |
-
"loss": 7.2951,
|
| 1616 |
-
"step": 2170
|
| 1617 |
-
},
|
| 1618 |
-
{
|
| 1619 |
-
"epoch": 0.6451612903225806,
|
| 1620 |
-
"grad_norm": 44.75,
|
| 1621 |
-
"learning_rate": 8.825682158533554e-06,
|
| 1622 |
-
"loss": 7.2342,
|
| 1623 |
-
"step": 2180
|
| 1624 |
-
},
|
| 1625 |
-
{
|
| 1626 |
-
"epoch": 0.648120745782776,
|
| 1627 |
-
"grad_norm": 298.0,
|
| 1628 |
-
"learning_rate": 8.290330062017016e-06,
|
| 1629 |
-
"loss": 7.3409,
|
| 1630 |
-
"step": 2190
|
| 1631 |
-
},
|
| 1632 |
-
{
|
| 1633 |
-
"epoch": 0.6510802012429713,
|
| 1634 |
-
"grad_norm": 133.0,
|
| 1635 |
-
"learning_rate": 7.771024502261526e-06,
|
| 1636 |
-
"loss": 7.1213,
|
| 1637 |
-
"step": 2200
|
| 1638 |
-
},
|
| 1639 |
-
{
|
| 1640 |
-
"epoch": 0.6510802012429713,
|
| 1641 |
-
"eval_loss": 7.390503406524658,
|
| 1642 |
-
"eval_runtime": 8.9829,
|
| 1643 |
-
"eval_samples_per_second": 167.207,
|
| 1644 |
-
"eval_steps_per_second": 41.857,
|
| 1645 |
-
"step": 2200
|
| 1646 |
-
},
|
| 1647 |
-
{
|
| 1648 |
-
"epoch": 0.6540396567031667,
|
| 1649 |
-
"grad_norm": 94.0,
|
| 1650 |
-
"learning_rate": 7.267856342703461e-06,
|
| 1651 |
-
"loss": 7.5047,
|
| 1652 |
-
"step": 2210
|
| 1653 |
-
},
|
| 1654 |
-
{
|
| 1655 |
-
"epoch": 0.6569991121633619,
|
| 1656 |
-
"grad_norm": 320.0,
|
| 1657 |
-
"learning_rate": 6.780913623201346e-06,
|
| 1658 |
-
"loss": 7.2716,
|
| 1659 |
-
"step": 2220
|
| 1660 |
-
},
|
| 1661 |
-
{
|
| 1662 |
-
"epoch": 0.6599585676235573,
|
| 1663 |
-
"grad_norm": 21.0,
|
| 1664 |
-
"learning_rate": 6.310281544631546e-06,
|
| 1665 |
-
"loss": 7.4708,
|
| 1666 |
-
"step": 2230
|
| 1667 |
-
},
|
| 1668 |
-
{
|
| 1669 |
-
"epoch": 0.6629180230837526,
|
| 1670 |
-
"grad_norm": 233.0,
|
| 1671 |
-
"learning_rate": 5.856042453980526e-06,
|
| 1672 |
-
"loss": 7.4026,
|
| 1673 |
-
"step": 2240
|
| 1674 |
-
},
|
| 1675 |
-
{
|
| 1676 |
-
"epoch": 0.665877478543948,
|
| 1677 |
-
"grad_norm": 170.0,
|
| 1678 |
-
"learning_rate": 5.418275829936537e-06,
|
| 1679 |
-
"loss": 7.0923,
|
| 1680 |
-
"step": 2250
|
| 1681 |
-
},
|
| 1682 |
-
{
|
| 1683 |
-
"epoch": 0.6688369340041432,
|
| 1684 |
-
"grad_norm": 57.75,
|
| 1685 |
-
"learning_rate": 4.997058268983135e-06,
|
| 1686 |
-
"loss": 7.6658,
|
| 1687 |
-
"step": 2260
|
| 1688 |
-
},
|
| 1689 |
-
{
|
| 1690 |
-
"epoch": 0.6717963894643386,
|
| 1691 |
-
"grad_norm": 264.0,
|
| 1692 |
-
"learning_rate": 4.592463471997022e-06,
|
| 1693 |
-
"loss": 7.3902,
|
| 1694 |
-
"step": 2270
|
| 1695 |
-
},
|
| 1696 |
-
{
|
| 1697 |
-
"epoch": 0.6747558449245339,
|
| 1698 |
-
"grad_norm": 101.0,
|
| 1699 |
-
"learning_rate": 4.204562231352516e-06,
|
| 1700 |
-
"loss": 7.3701,
|
| 1701 |
-
"step": 2280
|
| 1702 |
-
},
|
| 1703 |
-
{
|
| 1704 |
-
"epoch": 0.6777153003847292,
|
| 1705 |
-
"grad_norm": 38.25,
|
| 1706 |
-
"learning_rate": 3.83342241853496e-06,
|
| 1707 |
-
"loss": 7.2345,
|
| 1708 |
-
"step": 2290
|
| 1709 |
-
},
|
| 1710 |
-
{
|
| 1711 |
-
"epoch": 0.6806747558449245,
|
| 1712 |
-
"grad_norm": 84.0,
|
| 1713 |
-
"learning_rate": 3.4791089722651436e-06,
|
| 1714 |
-
"loss": 7.3887,
|
| 1715 |
-
"step": 2300
|
| 1716 |
-
},
|
| 1717 |
-
{
|
| 1718 |
-
"epoch": 0.6836342113051198,
|
| 1719 |
-
"grad_norm": 199.0,
|
| 1720 |
-
"learning_rate": 3.1416838871368924e-06,
|
| 1721 |
-
"loss": 7.2888,
|
| 1722 |
-
"step": 2310
|
| 1723 |
-
},
|
| 1724 |
-
{
|
| 1725 |
-
"epoch": 0.6865936667653152,
|
| 1726 |
-
"grad_norm": 34.75,
|
| 1727 |
-
"learning_rate": 2.821206202769899e-06,
|
| 1728 |
-
"loss": 7.4502,
|
| 1729 |
-
"step": 2320
|
| 1730 |
-
},
|
| 1731 |
-
{
|
| 1732 |
-
"epoch": 0.6895531222255105,
|
| 1733 |
-
"grad_norm": 121.5,
|
| 1734 |
-
"learning_rate": 2.5177319934794e-06,
|
| 1735 |
-
"loss": 7.3453,
|
| 1736 |
-
"step": 2330
|
| 1737 |
-
},
|
| 1738 |
-
{
|
| 1739 |
-
"epoch": 0.6925125776857058,
|
| 1740 |
-
"grad_norm": 398.0,
|
| 1741 |
-
"learning_rate": 2.2313143584648423e-06,
|
| 1742 |
-
"loss": 7.489,
|
| 1743 |
-
"step": 2340
|
| 1744 |
-
},
|
| 1745 |
-
{
|
| 1746 |
-
"epoch": 0.6954720331459011,
|
| 1747 |
-
"grad_norm": 840.0,
|
| 1748 |
-
"learning_rate": 1.9620034125190644e-06,
|
| 1749 |
-
"loss": 7.2602,
|
| 1750 |
-
"step": 2350
|
| 1751 |
-
},
|
| 1752 |
-
{
|
| 1753 |
-
"epoch": 0.6984314886060965,
|
| 1754 |
-
"grad_norm": 47.0,
|
| 1755 |
-
"learning_rate": 1.7098462772596302e-06,
|
| 1756 |
-
"loss": 7.4021,
|
| 1757 |
-
"step": 2360
|
| 1758 |
-
},
|
| 1759 |
-
{
|
| 1760 |
-
"epoch": 0.7013909440662918,
|
| 1761 |
-
"grad_norm": 32.5,
|
| 1762 |
-
"learning_rate": 1.4748870728839347e-06,
|
| 1763 |
-
"loss": 7.2297,
|
| 1764 |
-
"step": 2370
|
| 1765 |
-
},
|
| 1766 |
-
{
|
| 1767 |
-
"epoch": 0.7043503995264871,
|
| 1768 |
-
"grad_norm": 25.375,
|
| 1769 |
-
"learning_rate": 1.2571669104494256e-06,
|
| 1770 |
-
"loss": 7.3295,
|
| 1771 |
-
"step": 2380
|
| 1772 |
-
},
|
| 1773 |
-
{
|
| 1774 |
-
"epoch": 0.7073098549866824,
|
| 1775 |
-
"grad_norm": 290.0,
|
| 1776 |
-
"learning_rate": 1.0567238846803996e-06,
|
| 1777 |
-
"loss": 7.3048,
|
| 1778 |
-
"step": 2390
|
| 1779 |
-
},
|
| 1780 |
-
{
|
| 1781 |
-
"epoch": 0.7102693104468778,
|
| 1782 |
-
"grad_norm": 74.0,
|
| 1783 |
-
"learning_rate": 8.735930673024806e-07,
|
| 1784 |
-
"loss": 7.2075,
|
| 1785 |
-
"step": 2400
|
| 1786 |
-
},
|
| 1787 |
-
{
|
| 1788 |
-
"epoch": 0.7102693104468778,
|
| 1789 |
-
"eval_loss": 7.393959045410156,
|
| 1790 |
-
"eval_runtime": 9.0065,
|
| 1791 |
-
"eval_samples_per_second": 166.769,
|
| 1792 |
-
"eval_steps_per_second": 41.748,
|
| 1793 |
-
"step": 2400
|
| 1794 |
}
|
| 1795 |
],
|
| 1796 |
"logging_steps": 10,
|
|
@@ -1810,7 +330,7 @@
|
|
| 1810 |
"attributes": {}
|
| 1811 |
}
|
| 1812 |
},
|
| 1813 |
-
"total_flos":
|
| 1814 |
"train_batch_size": 4,
|
| 1815 |
"trial_name": null,
|
| 1816 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.11837821840781296,
|
| 5 |
"eval_steps": 200,
|
| 6 |
+
"global_step": 400,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.0002959455460195324,
|
| 13 |
+
"eval_loss": 10.377325057983398,
|
| 14 |
+
"eval_runtime": 11.0363,
|
| 15 |
+
"eval_samples_per_second": 136.096,
|
| 16 |
+
"eval_steps_per_second": 34.069,
|
| 17 |
"step": 1
|
| 18 |
},
|
| 19 |
{
|
| 20 |
"epoch": 0.002959455460195324,
|
| 21 |
+
"grad_norm": 0.43359375,
|
| 22 |
"learning_rate": 1.6000000000000003e-05,
|
| 23 |
+
"loss": 10.3751,
|
| 24 |
"step": 10
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 0.005918910920390648,
|
| 28 |
+
"grad_norm": 0.51171875,
|
| 29 |
"learning_rate": 3.2000000000000005e-05,
|
| 30 |
+
"loss": 10.3738,
|
| 31 |
"step": 20
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"epoch": 0.008878366380585973,
|
| 35 |
+
"grad_norm": 0.640625,
|
| 36 |
"learning_rate": 4.8e-05,
|
| 37 |
+
"loss": 10.3766,
|
| 38 |
"step": 30
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.011837821840781295,
|
| 42 |
+
"grad_norm": 0.8359375,
|
| 43 |
"learning_rate": 6.400000000000001e-05,
|
| 44 |
+
"loss": 10.3761,
|
| 45 |
"step": 40
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.01479727730097662,
|
| 49 |
+
"grad_norm": 1.5859375,
|
| 50 |
"learning_rate": 8e-05,
|
| 51 |
+
"loss": 10.369,
|
| 52 |
"step": 50
|
| 53 |
},
|
| 54 |
{
|
| 55 |
"epoch": 0.017756732761171946,
|
| 56 |
+
"grad_norm": 0.462890625,
|
| 57 |
"learning_rate": 9.6e-05,
|
| 58 |
+
"loss": 10.3704,
|
| 59 |
"step": 60
|
| 60 |
},
|
| 61 |
{
|
| 62 |
"epoch": 0.020716188221367268,
|
| 63 |
+
"grad_norm": 0.6015625,
|
| 64 |
"learning_rate": 0.00011200000000000001,
|
| 65 |
+
"loss": 10.362,
|
| 66 |
"step": 70
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 0.02367564368156259,
|
| 70 |
+
"grad_norm": 0.76171875,
|
| 71 |
"learning_rate": 0.00012800000000000002,
|
| 72 |
+
"loss": 10.3539,
|
| 73 |
"step": 80
|
| 74 |
},
|
| 75 |
{
|
| 76 |
"epoch": 0.026635099141757917,
|
| 77 |
+
"grad_norm": 1.1484375,
|
| 78 |
"learning_rate": 0.000144,
|
| 79 |
+
"loss": 10.3111,
|
| 80 |
"step": 90
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.02959455460195324,
|
| 84 |
+
"grad_norm": 2.53125,
|
| 85 |
"learning_rate": 0.00016,
|
| 86 |
+
"loss": 10.2556,
|
| 87 |
"step": 100
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 0.032554010062148565,
|
| 91 |
+
"grad_norm": 0.7578125,
|
| 92 |
"learning_rate": 0.00017600000000000002,
|
| 93 |
+
"loss": 10.1628,
|
| 94 |
"step": 110
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"epoch": 0.03551346552234389,
|
| 98 |
+
"grad_norm": 0.66796875,
|
| 99 |
"learning_rate": 0.000192,
|
| 100 |
+
"loss": 10.0397,
|
| 101 |
"step": 120
|
| 102 |
},
|
| 103 |
{
|
| 104 |
"epoch": 0.03847292098253921,
|
| 105 |
+
"grad_norm": 0.7421875,
|
| 106 |
"learning_rate": 0.0001999978128380225,
|
| 107 |
+
"loss": 9.9248,
|
| 108 |
"step": 130
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 0.041432376442734536,
|
| 112 |
+
"grad_norm": 0.88671875,
|
| 113 |
"learning_rate": 0.0001999803161162393,
|
| 114 |
+
"loss": 9.8201,
|
| 115 |
"step": 140
|
| 116 |
},
|
| 117 |
{
|
| 118 |
"epoch": 0.04439183190292986,
|
| 119 |
+
"grad_norm": 1.78125,
|
| 120 |
"learning_rate": 0.00019994532573409262,
|
| 121 |
+
"loss": 9.7523,
|
| 122 |
"step": 150
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 0.04735128736312518,
|
| 126 |
+
"grad_norm": 0.609375,
|
| 127 |
"learning_rate": 0.00019989284781388617,
|
| 128 |
+
"loss": 9.6134,
|
| 129 |
"step": 160
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 0.05031074282332051,
|
| 133 |
+
"grad_norm": 0.57421875,
|
| 134 |
"learning_rate": 0.00019982289153773646,
|
| 135 |
+
"loss": 9.5326,
|
| 136 |
"step": 170
|
| 137 |
},
|
| 138 |
{
|
| 139 |
"epoch": 0.053270198283515834,
|
| 140 |
+
"grad_norm": 0.6640625,
|
| 141 |
"learning_rate": 0.00019973546914596623,
|
| 142 |
+
"loss": 9.4273,
|
| 143 |
"step": 180
|
| 144 |
},
|
| 145 |
{
|
| 146 |
"epoch": 0.05622965374371116,
|
| 147 |
+
"grad_norm": 0.90234375,
|
| 148 |
"learning_rate": 0.00019963059593496268,
|
| 149 |
+
"loss": 9.3176,
|
| 150 |
"step": 190
|
| 151 |
},
|
| 152 |
{
|
| 153 |
"epoch": 0.05918910920390648,
|
| 154 |
+
"grad_norm": 1.6015625,
|
| 155 |
"learning_rate": 0.00019950829025450114,
|
| 156 |
+
"loss": 9.2412,
|
| 157 |
"step": 200
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"epoch": 0.05918910920390648,
|
| 161 |
+
"eval_loss": 9.224679946899414,
|
| 162 |
+
"eval_runtime": 11.174,
|
| 163 |
+
"eval_samples_per_second": 134.419,
|
| 164 |
+
"eval_steps_per_second": 33.649,
|
| 165 |
"step": 200
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 0.062148564664101805,
|
| 169 |
+
"grad_norm": 0.640625,
|
| 170 |
"learning_rate": 0.0001993685735045343,
|
| 171 |
+
"loss": 9.1904,
|
| 172 |
"step": 210
|
| 173 |
},
|
| 174 |
{
|
| 175 |
"epoch": 0.06510802012429713,
|
| 176 |
+
"grad_norm": 0.71484375,
|
| 177 |
"learning_rate": 0.0001992114701314478,
|
| 178 |
+
"loss": 9.1332,
|
| 179 |
"step": 220
|
| 180 |
},
|
| 181 |
{
|
| 182 |
"epoch": 0.06806747558449246,
|
| 183 |
+
"grad_norm": 0.703125,
|
| 184 |
"learning_rate": 0.000199037007623783,
|
| 185 |
+
"loss": 9.0845,
|
| 186 |
"step": 230
|
| 187 |
},
|
| 188 |
{
|
| 189 |
"epoch": 0.07102693104468778,
|
| 190 |
+
"grad_norm": 0.83984375,
|
| 191 |
"learning_rate": 0.00019884521650742715,
|
| 192 |
+
"loss": 8.992,
|
| 193 |
"step": 240
|
| 194 |
},
|
| 195 |
{
|
| 196 |
"epoch": 0.0739863865048831,
|
| 197 |
+
"grad_norm": 2.59375,
|
| 198 |
"learning_rate": 0.00019863613034027224,
|
| 199 |
+
"loss": 9.0056,
|
| 200 |
"step": 250
|
| 201 |
},
|
| 202 |
{
|
| 203 |
"epoch": 0.07694584196507842,
|
| 204 |
+
"grad_norm": 0.6953125,
|
| 205 |
"learning_rate": 0.0001984097857063434,
|
| 206 |
+
"loss": 8.8204,
|
| 207 |
"step": 260
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 0.07990529742527375,
|
| 211 |
+
"grad_norm": 0.77734375,
|
| 212 |
"learning_rate": 0.0001981662222093976,
|
| 213 |
+
"loss": 8.8472,
|
| 214 |
"step": 270
|
| 215 |
},
|
| 216 |
{
|
| 217 |
"epoch": 0.08286475288546907,
|
| 218 |
+
"grad_norm": 0.70703125,
|
| 219 |
"learning_rate": 0.00019790548246599447,
|
| 220 |
+
"loss": 8.785,
|
| 221 |
"step": 280
|
| 222 |
},
|
| 223 |
{
|
| 224 |
"epoch": 0.0858242083456644,
|
| 225 |
+
"grad_norm": 0.8515625,
|
| 226 |
"learning_rate": 0.00019762761209803927,
|
| 227 |
+
"loss": 8.7212,
|
| 228 |
"step": 290
|
| 229 |
},
|
| 230 |
{
|
| 231 |
"epoch": 0.08878366380585972,
|
| 232 |
+
"grad_norm": 1.6484375,
|
| 233 |
"learning_rate": 0.0001973326597248006,
|
| 234 |
+
"loss": 8.748,
|
| 235 |
"step": 300
|
| 236 |
},
|
| 237 |
{
|
| 238 |
"epoch": 0.09174311926605505,
|
| 239 |
+
"grad_norm": 0.609375,
|
| 240 |
"learning_rate": 0.00019702067695440332,
|
| 241 |
+
"loss": 8.6333,
|
| 242 |
"step": 310
|
| 243 |
},
|
| 244 |
{
|
| 245 |
"epoch": 0.09470257472625036,
|
| 246 |
+
"grad_norm": 0.6171875,
|
| 247 |
"learning_rate": 0.00019669171837479873,
|
| 248 |
+
"loss": 8.6464,
|
| 249 |
"step": 320
|
| 250 |
},
|
| 251 |
{
|
| 252 |
"epoch": 0.09766203018644569,
|
| 253 |
+
"grad_norm": 0.640625,
|
| 254 |
"learning_rate": 0.00019634584154421317,
|
| 255 |
+
"loss": 8.6169,
|
| 256 |
"step": 330
|
| 257 |
},
|
| 258 |
{
|
| 259 |
"epoch": 0.10062148564664102,
|
| 260 |
+
"grad_norm": 0.79296875,
|
| 261 |
"learning_rate": 0.00019598310698107702,
|
| 262 |
+
"loss": 8.541,
|
| 263 |
"step": 340
|
| 264 |
},
|
| 265 |
{
|
| 266 |
"epoch": 0.10358094110683634,
|
| 267 |
+
"grad_norm": 1.8203125,
|
| 268 |
"learning_rate": 0.00019560357815343577,
|
| 269 |
+
"loss": 8.4839,
|
| 270 |
"step": 350
|
| 271 |
},
|
| 272 |
{
|
| 273 |
"epoch": 0.10654039656703167,
|
| 274 |
+
"grad_norm": 0.77734375,
|
| 275 |
"learning_rate": 0.00019520732146784491,
|
| 276 |
+
"loss": 8.5185,
|
| 277 |
"step": 360
|
| 278 |
},
|
| 279 |
{
|
| 280 |
"epoch": 0.109499852027227,
|
| 281 |
+
"grad_norm": 1.0703125,
|
| 282 |
"learning_rate": 0.0001947944062577507,
|
| 283 |
+
"loss": 8.4832,
|
| 284 |
"step": 370
|
| 285 |
},
|
| 286 |
{
|
| 287 |
"epoch": 0.11245930748742232,
|
| 288 |
+
"grad_norm": 0.734375,
|
| 289 |
"learning_rate": 0.00019436490477135878,
|
| 290 |
+
"loss": 8.4174,
|
| 291 |
"step": 380
|
| 292 |
},
|
| 293 |
{
|
| 294 |
"epoch": 0.11541876294761765,
|
| 295 |
+
"grad_norm": 0.84375,
|
| 296 |
"learning_rate": 0.00019391889215899299,
|
| 297 |
+
"loss": 8.477,
|
| 298 |
"step": 390
|
| 299 |
},
|
| 300 |
{
|
| 301 |
"epoch": 0.11837821840781296,
|
| 302 |
+
"grad_norm": 1.9921875,
|
| 303 |
"learning_rate": 0.0001934564464599461,
|
| 304 |
+
"loss": 8.2947,
|
| 305 |
"step": 400
|
| 306 |
},
|
| 307 |
{
|
| 308 |
"epoch": 0.11837821840781296,
|
| 309 |
+
"eval_loss": 8.401090621948242,
|
| 310 |
+
"eval_runtime": 12.2623,
|
| 311 |
+
"eval_samples_per_second": 122.489,
|
| 312 |
+
"eval_steps_per_second": 30.663,
|
| 313 |
"step": 400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 314 |
}
|
| 315 |
],
|
| 316 |
"logging_steps": 10,
|
|
|
|
| 330 |
"attributes": {}
|
| 331 |
}
|
| 332 |
},
|
| 333 |
+
"total_flos": 20596742160384.0,
|
| 334 |
"train_batch_size": 4,
|
| 335 |
"trial_name": null,
|
| 336 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6840
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ffd459aa83253f73e371e129574dd0434ee79c2c18eb103b0e4428a34062eb2
|
| 3 |
size 6840
|