Initial commit
Browse files- all_results.json +14 -0
- config.json +32 -0
- generation_config.json +10 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +6 -0
- test_results.json +9 -0
- tokenizer.json +177 -0
- tokenizer_config.json +10 -0
- train_results.json +8 -0
- trainer_state.json +1042 -0
- training_args.bin +3 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 43.0,
|
| 3 |
+
"perplexity": 1.1020061050262677,
|
| 4 |
+
"test_accuracy": 0.5884773413073098,
|
| 5 |
+
"test_loss": 0.09713225066661835,
|
| 6 |
+
"test_runtime": 9.4021,
|
| 7 |
+
"test_samples_per_second": 248.562,
|
| 8 |
+
"test_steps_per_second": 15.635,
|
| 9 |
+
"train_loss": 0.2331255912600619,
|
| 10 |
+
"train_runtime": 2746.0841,
|
| 11 |
+
"train_samples": 7878,
|
| 12 |
+
"train_samples_per_second": 143.441,
|
| 13 |
+
"train_steps_per_second": 4.479
|
| 14 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 1,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"layer_norm_epsilon": 1e-05,
|
| 12 |
+
"model_type": "gpt2",
|
| 13 |
+
"n_embd": 144,
|
| 14 |
+
"n_head": 12,
|
| 15 |
+
"n_inner": null,
|
| 16 |
+
"n_layer": 12,
|
| 17 |
+
"n_positions": 896,
|
| 18 |
+
"pad_token": " ",
|
| 19 |
+
"reorder_and_upcast_attn": false,
|
| 20 |
+
"resid_pdrop": 0.1,
|
| 21 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 22 |
+
"scale_attn_weights": true,
|
| 23 |
+
"summary_activation": null,
|
| 24 |
+
"summary_first_dropout": 0.1,
|
| 25 |
+
"summary_proj_to_labels": true,
|
| 26 |
+
"summary_type": "cls_index",
|
| 27 |
+
"summary_use_proj": true,
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.27.1",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 52
|
| 32 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_sample": true,
|
| 3 |
+
"eos_token_id": 1,
|
| 4 |
+
"length_penalty": 0.0,
|
| 5 |
+
"max_new_tokens": 896,
|
| 6 |
+
"min_new_tokens": 1,
|
| 7 |
+
"num_return_sequences": 100,
|
| 8 |
+
"pad_token_id": 2,
|
| 9 |
+
"transformers_version": "4.27.1"
|
| 10 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:731f207586a9dda4728f79a89e66fbbe0cc2b23b3921ec47fe995fc5aeb2c63b
|
| 3 |
+
size 22270333
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "^",
|
| 3 |
+
"eos_token": "_",
|
| 4 |
+
"pad_token": " ",
|
| 5 |
+
"unk_token": "§"
|
| 6 |
+
}
|
test_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 43.0,
|
| 3 |
+
"perplexity": 1.1020061050262677,
|
| 4 |
+
"test_accuracy": 0.5884773413073098,
|
| 5 |
+
"test_loss": 0.09713225066661835,
|
| 6 |
+
"test_runtime": 9.4021,
|
| 7 |
+
"test_samples_per_second": 248.562,
|
| 8 |
+
"test_steps_per_second": 15.635
|
| 9 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,177 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 0,
|
| 8 |
+
"content": "^",
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"special": true
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"id": 1,
|
| 17 |
+
"content": "_",
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"special": true
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"id": 2,
|
| 26 |
+
"content": " ",
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"special": true
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"id": 3,
|
| 35 |
+
"content": "§",
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"special": true
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"id": 4,
|
| 44 |
+
"content": "°",
|
| 45 |
+
"single_word": false,
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"special": true
|
| 50 |
+
}
|
| 51 |
+
],
|
| 52 |
+
"normalizer": null,
|
| 53 |
+
"pre_tokenizer": {
|
| 54 |
+
"type": "Split",
|
| 55 |
+
"pattern": {
|
| 56 |
+
"Regex": ""
|
| 57 |
+
},
|
| 58 |
+
"behavior": "Isolated",
|
| 59 |
+
"invert": false
|
| 60 |
+
},
|
| 61 |
+
"post_processor": {
|
| 62 |
+
"type": "TemplateProcessing",
|
| 63 |
+
"single": [
|
| 64 |
+
{
|
| 65 |
+
"SpecialToken": {
|
| 66 |
+
"id": "^",
|
| 67 |
+
"type_id": 0
|
| 68 |
+
}
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"Sequence": {
|
| 72 |
+
"id": "A",
|
| 73 |
+
"type_id": 0
|
| 74 |
+
}
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"SpecialToken": {
|
| 78 |
+
"id": "_",
|
| 79 |
+
"type_id": 0
|
| 80 |
+
}
|
| 81 |
+
}
|
| 82 |
+
],
|
| 83 |
+
"pair": [
|
| 84 |
+
{
|
| 85 |
+
"Sequence": {
|
| 86 |
+
"id": "A",
|
| 87 |
+
"type_id": 0
|
| 88 |
+
}
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"Sequence": {
|
| 92 |
+
"id": "B",
|
| 93 |
+
"type_id": 1
|
| 94 |
+
}
|
| 95 |
+
}
|
| 96 |
+
],
|
| 97 |
+
"special_tokens": {
|
| 98 |
+
"^": {
|
| 99 |
+
"id": "^",
|
| 100 |
+
"ids": [
|
| 101 |
+
0
|
| 102 |
+
],
|
| 103 |
+
"tokens": [
|
| 104 |
+
"^"
|
| 105 |
+
]
|
| 106 |
+
},
|
| 107 |
+
"_": {
|
| 108 |
+
"id": "_",
|
| 109 |
+
"ids": [
|
| 110 |
+
1
|
| 111 |
+
],
|
| 112 |
+
"tokens": [
|
| 113 |
+
"_"
|
| 114 |
+
]
|
| 115 |
+
}
|
| 116 |
+
}
|
| 117 |
+
},
|
| 118 |
+
"decoder": null,
|
| 119 |
+
"model": {
|
| 120 |
+
"type": "WordLevel",
|
| 121 |
+
"vocab": {
|
| 122 |
+
"^": 0,
|
| 123 |
+
"_": 1,
|
| 124 |
+
" ": 2,
|
| 125 |
+
"§": 3,
|
| 126 |
+
"°": 4,
|
| 127 |
+
":": 5,
|
| 128 |
+
";": 6,
|
| 129 |
+
"[": 7,
|
| 130 |
+
"]": 8,
|
| 131 |
+
"0": 9,
|
| 132 |
+
"-": 10,
|
| 133 |
+
"1": 11,
|
| 134 |
+
"H": 12,
|
| 135 |
+
"D": 13,
|
| 136 |
+
"C": 14,
|
| 137 |
+
"2": 15,
|
| 138 |
+
"c": 16,
|
| 139 |
+
"3": 17,
|
| 140 |
+
"+": 18,
|
| 141 |
+
"7": 19,
|
| 142 |
+
"(": 20,
|
| 143 |
+
")": 21,
|
| 144 |
+
"#": 22,
|
| 145 |
+
"O": 23,
|
| 146 |
+
"4": 24,
|
| 147 |
+
"a": 25,
|
| 148 |
+
">": 26,
|
| 149 |
+
"=": 27,
|
| 150 |
+
"6": 28,
|
| 151 |
+
"5": 29,
|
| 152 |
+
"8": 30,
|
| 153 |
+
"N": 31,
|
| 154 |
+
".": 32,
|
| 155 |
+
"9": 33,
|
| 156 |
+
"B": 34,
|
| 157 |
+
"l": 35,
|
| 158 |
+
"n": 36,
|
| 159 |
+
"r": 37,
|
| 160 |
+
"S": 38,
|
| 161 |
+
"F": 39,
|
| 162 |
+
"/": 40,
|
| 163 |
+
"@": 41,
|
| 164 |
+
"I": 42,
|
| 165 |
+
"\\": 43,
|
| 166 |
+
"P": 44,
|
| 167 |
+
"M": 45,
|
| 168 |
+
"g": 46,
|
| 169 |
+
"s": 47,
|
| 170 |
+
"Z": 48,
|
| 171 |
+
"i": 49,
|
| 172 |
+
"o": 50,
|
| 173 |
+
"u": 51
|
| 174 |
+
},
|
| 175 |
+
"unk_token": "§"
|
| 176 |
+
}
|
| 177 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "^",
|
| 3 |
+
"eos_token": "_",
|
| 4 |
+
"model_max_length": 896,
|
| 5 |
+
"pad_token": " ",
|
| 6 |
+
"padding_side": "right",
|
| 7 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 8 |
+
"truncation_side": "left",
|
| 9 |
+
"unk_token": "§"
|
| 10 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 43.0,
|
| 3 |
+
"train_loss": 0.2331255912600619,
|
| 4 |
+
"train_runtime": 2746.0841,
|
| 5 |
+
"train_samples": 7878,
|
| 6 |
+
"train_samples_per_second": 143.441,
|
| 7 |
+
"train_steps_per_second": 4.479
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1042 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.0970187559723854,
|
| 3 |
+
"best_model_checkpoint": "/home/stephan/code/molreactgen/checkpoints/2023-05-12_13-06-58_experiment/checkpoint-9850",
|
| 4 |
+
"epoch": 42.99695431472081,
|
| 5 |
+
"global_step": 10588,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.41,
|
| 12 |
+
"learning_rate": 4.065040650406504e-05,
|
| 13 |
+
"loss": 3.0981,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.81,
|
| 18 |
+
"learning_rate": 8.130081300813008e-05,
|
| 19 |
+
"loss": 2.1418,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.0,
|
| 24 |
+
"eval_accuracy": 0.2829720403871191,
|
| 25 |
+
"eval_loss": 1.5341426134109497,
|
| 26 |
+
"eval_runtime": 6.1779,
|
| 27 |
+
"eval_samples_per_second": 390.745,
|
| 28 |
+
"eval_steps_per_second": 24.442,
|
| 29 |
+
"step": 246
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 1.22,
|
| 33 |
+
"learning_rate": 0.00012195121951219512,
|
| 34 |
+
"loss": 1.588,
|
| 35 |
+
"step": 300
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 1.62,
|
| 39 |
+
"learning_rate": 0.00016260162601626016,
|
| 40 |
+
"loss": 1.1354,
|
| 41 |
+
"step": 400
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 2.0,
|
| 45 |
+
"eval_accuracy": 0.32898021613845974,
|
| 46 |
+
"eval_loss": 0.7312331795692444,
|
| 47 |
+
"eval_runtime": 6.0715,
|
| 48 |
+
"eval_samples_per_second": 397.598,
|
| 49 |
+
"eval_steps_per_second": 24.87,
|
| 50 |
+
"step": 492
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 2.03,
|
| 54 |
+
"learning_rate": 0.0002032520325203252,
|
| 55 |
+
"loss": 0.8911,
|
| 56 |
+
"step": 500
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 2.44,
|
| 60 |
+
"learning_rate": 0.00024390243902439024,
|
| 61 |
+
"loss": 0.743,
|
| 62 |
+
"step": 600
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 2.84,
|
| 66 |
+
"learning_rate": 0.0002845528455284553,
|
| 67 |
+
"loss": 0.664,
|
| 68 |
+
"step": 700
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 3.0,
|
| 72 |
+
"eval_accuracy": 0.3475759534583064,
|
| 73 |
+
"eval_loss": 0.5133360028266907,
|
| 74 |
+
"eval_runtime": 6.1012,
|
| 75 |
+
"eval_samples_per_second": 395.662,
|
| 76 |
+
"eval_steps_per_second": 24.749,
|
| 77 |
+
"step": 738
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 3.25,
|
| 81 |
+
"learning_rate": 0.0003252032520325203,
|
| 82 |
+
"loss": 0.6077,
|
| 83 |
+
"step": 800
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 3.65,
|
| 87 |
+
"learning_rate": 0.00036585365853658537,
|
| 88 |
+
"loss": 0.5517,
|
| 89 |
+
"step": 900
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 4.0,
|
| 93 |
+
"eval_accuracy": 0.35866693372907127,
|
| 94 |
+
"eval_loss": 0.40151524543762207,
|
| 95 |
+
"eval_runtime": 6.0531,
|
| 96 |
+
"eval_samples_per_second": 398.803,
|
| 97 |
+
"eval_steps_per_second": 24.946,
|
| 98 |
+
"step": 985
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 4.06,
|
| 102 |
+
"learning_rate": 0.0004065040650406504,
|
| 103 |
+
"loss": 0.5002,
|
| 104 |
+
"step": 1000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 4.47,
|
| 108 |
+
"learning_rate": 0.00044715447154471545,
|
| 109 |
+
"loss": 0.4461,
|
| 110 |
+
"step": 1100
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 4.87,
|
| 114 |
+
"learning_rate": 0.0004878048780487805,
|
| 115 |
+
"loss": 0.3986,
|
| 116 |
+
"step": 1200
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 5.0,
|
| 120 |
+
"eval_accuracy": 0.36889936906506915,
|
| 121 |
+
"eval_loss": 0.30596020817756653,
|
| 122 |
+
"eval_runtime": 6.0649,
|
| 123 |
+
"eval_samples_per_second": 398.03,
|
| 124 |
+
"eval_steps_per_second": 24.897,
|
| 125 |
+
"step": 1231
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 5.28,
|
| 129 |
+
"learning_rate": 0.0004999506716812021,
|
| 130 |
+
"loss": 0.3583,
|
| 131 |
+
"step": 1300
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 5.69,
|
| 135 |
+
"learning_rate": 0.0004997091104496882,
|
| 136 |
+
"loss": 0.3313,
|
| 137 |
+
"step": 1400
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 6.0,
|
| 141 |
+
"eval_accuracy": 0.3759261451059297,
|
| 142 |
+
"eval_loss": 0.241128608584404,
|
| 143 |
+
"eval_runtime": 6.1261,
|
| 144 |
+
"eval_samples_per_second": 394.054,
|
| 145 |
+
"eval_steps_per_second": 24.649,
|
| 146 |
+
"step": 1477
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 6.09,
|
| 150 |
+
"learning_rate": 0.0004992664502959351,
|
| 151 |
+
"loss": 0.3005,
|
| 152 |
+
"step": 1500
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 6.5,
|
| 156 |
+
"learning_rate": 0.0004986230477086575,
|
| 157 |
+
"loss": 0.2758,
|
| 158 |
+
"step": 1600
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 6.9,
|
| 162 |
+
"learning_rate": 0.0004977794208410241,
|
| 163 |
+
"loss": 0.259,
|
| 164 |
+
"step": 1700
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 7.0,
|
| 168 |
+
"eval_accuracy": 0.3807942678696614,
|
| 169 |
+
"eval_loss": 0.19934649765491486,
|
| 170 |
+
"eval_runtime": 6.0599,
|
| 171 |
+
"eval_samples_per_second": 398.358,
|
| 172 |
+
"eval_steps_per_second": 24.918,
|
| 173 |
+
"step": 1723
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 7.31,
|
| 177 |
+
"learning_rate": 0.0004967362490933723,
|
| 178 |
+
"loss": 0.2409,
|
| 179 |
+
"step": 1800
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 7.72,
|
| 183 |
+
"learning_rate": 0.0004954943725660643,
|
| 184 |
+
"loss": 0.2288,
|
| 185 |
+
"step": 1900
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 8.0,
|
| 189 |
+
"eval_accuracy": 0.38369857151961545,
|
| 190 |
+
"eval_loss": 0.17374461889266968,
|
| 191 |
+
"eval_runtime": 6.1335,
|
| 192 |
+
"eval_samples_per_second": 393.573,
|
| 193 |
+
"eval_steps_per_second": 24.619,
|
| 194 |
+
"step": 1970
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 8.12,
|
| 198 |
+
"learning_rate": 0.0004940547913829275,
|
| 199 |
+
"loss": 0.2201,
|
| 200 |
+
"step": 2000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 8.53,
|
| 204 |
+
"learning_rate": 0.0004924186648858207,
|
| 205 |
+
"loss": 0.2064,
|
| 206 |
+
"step": 2100
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 8.93,
|
| 210 |
+
"learning_rate": 0.0004905873107009799,
|
| 211 |
+
"loss": 0.1992,
|
| 212 |
+
"step": 2200
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 9.0,
|
| 216 |
+
"eval_accuracy": 0.385633256552892,
|
| 217 |
+
"eval_loss": 0.15620127320289612,
|
| 218 |
+
"eval_runtime": 6.1272,
|
| 219 |
+
"eval_samples_per_second": 393.981,
|
| 220 |
+
"eval_steps_per_second": 24.644,
|
| 221 |
+
"step": 2216
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 9.34,
|
| 225 |
+
"learning_rate": 0.0004885622036778897,
|
| 226 |
+
"loss": 0.1894,
|
| 227 |
+
"step": 2300
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 9.75,
|
| 231 |
+
"learning_rate": 0.0004863449747015384,
|
| 232 |
+
"loss": 0.182,
|
| 233 |
+
"step": 2400
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 10.0,
|
| 237 |
+
"eval_accuracy": 0.38733486894215974,
|
| 238 |
+
"eval_loss": 0.1415354460477829,
|
| 239 |
+
"eval_runtime": 6.1286,
|
| 240 |
+
"eval_samples_per_second": 393.894,
|
| 241 |
+
"eval_steps_per_second": 24.639,
|
| 242 |
+
"step": 2462
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 10.15,
|
| 246 |
+
"learning_rate": 0.0004839374093790139,
|
| 247 |
+
"loss": 0.181,
|
| 248 |
+
"step": 2500
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 10.56,
|
| 252 |
+
"learning_rate": 0.00048134144660149535,
|
| 253 |
+
"loss": 0.1695,
|
| 254 |
+
"step": 2600
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 10.96,
|
| 258 |
+
"learning_rate": 0.0004785591769828005,
|
| 259 |
+
"loss": 0.1687,
|
| 260 |
+
"step": 2700
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 11.0,
|
| 264 |
+
"eval_accuracy": 0.3880878028351102,
|
| 265 |
+
"eval_loss": 0.13479964435100555,
|
| 266 |
+
"eval_runtime": 6.1178,
|
| 267 |
+
"eval_samples_per_second": 394.588,
|
| 268 |
+
"eval_steps_per_second": 24.682,
|
| 269 |
+
"step": 2708
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 11.37,
|
| 273 |
+
"learning_rate": 0.00047559284117574613,
|
| 274 |
+
"loss": 0.1629,
|
| 275 |
+
"step": 2800
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 11.78,
|
| 279 |
+
"learning_rate": 0.0004724448280676768,
|
| 280 |
+
"loss": 0.1592,
|
| 281 |
+
"step": 2900
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 12.0,
|
| 285 |
+
"eval_accuracy": 0.38904467529156844,
|
| 286 |
+
"eval_loss": 0.12684421241283417,
|
| 287 |
+
"eval_runtime": 6.118,
|
| 288 |
+
"eval_samples_per_second": 394.571,
|
| 289 |
+
"eval_steps_per_second": 24.681,
|
| 290 |
+
"step": 2955
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 12.18,
|
| 294 |
+
"learning_rate": 0.00046911767285661587,
|
| 295 |
+
"loss": 0.1527,
|
| 296 |
+
"step": 3000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 12.59,
|
| 300 |
+
"learning_rate": 0.0004656140550095876,
|
| 301 |
+
"loss": 0.1516,
|
| 302 |
+
"step": 3100
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 12.99,
|
| 306 |
+
"learning_rate": 0.00046193679610475414,
|
| 307 |
+
"loss": 0.1476,
|
| 308 |
+
"step": 3200
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 13.0,
|
| 312 |
+
"eval_accuracy": 0.3893742545772372,
|
| 313 |
+
"eval_loss": 0.12305640429258347,
|
| 314 |
+
"eval_runtime": 6.1457,
|
| 315 |
+
"eval_samples_per_second": 392.794,
|
| 316 |
+
"eval_steps_per_second": 24.57,
|
| 317 |
+
"step": 3201
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 13.4,
|
| 321 |
+
"learning_rate": 0.0004580888575591068,
|
| 322 |
+
"loss": 0.1447,
|
| 323 |
+
"step": 3300
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 13.81,
|
| 327 |
+
"learning_rate": 0.00045407333824353966,
|
| 328 |
+
"loss": 0.1417,
|
| 329 |
+
"step": 3400
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 14.0,
|
| 333 |
+
"eval_accuracy": 0.3899678614674472,
|
| 334 |
+
"eval_loss": 0.11744081974029541,
|
| 335 |
+
"eval_runtime": 6.1575,
|
| 336 |
+
"eval_samples_per_second": 392.044,
|
| 337 |
+
"eval_steps_per_second": 24.523,
|
| 338 |
+
"step": 3447
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 14.21,
|
| 342 |
+
"learning_rate": 0.00044989347198722777,
|
| 343 |
+
"loss": 0.1412,
|
| 344 |
+
"step": 3500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 14.62,
|
| 348 |
+
"learning_rate": 0.00044555262497331783,
|
| 349 |
+
"loss": 0.1403,
|
| 350 |
+
"step": 3600
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 15.0,
|
| 354 |
+
"eval_accuracy": 0.3901754417910176,
|
| 355 |
+
"eval_loss": 0.11636122316122055,
|
| 356 |
+
"eval_runtime": 6.1213,
|
| 357 |
+
"eval_samples_per_second": 394.36,
|
| 358 |
+
"eval_steps_per_second": 24.668,
|
| 359 |
+
"step": 3693
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 15.03,
|
| 363 |
+
"learning_rate": 0.0004410542930280316,
|
| 364 |
+
"loss": 0.1354,
|
| 365 |
+
"step": 3700
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 15.43,
|
| 369 |
+
"learning_rate": 0.0004364020988053623,
|
| 370 |
+
"loss": 0.1314,
|
| 371 |
+
"step": 3800
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 15.84,
|
| 375 |
+
"learning_rate": 0.00043159978886963223,
|
| 376 |
+
"loss": 0.1342,
|
| 377 |
+
"step": 3900
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 16.0,
|
| 381 |
+
"eval_accuracy": 0.3905068419567177,
|
| 382 |
+
"eval_loss": 0.11423930525779724,
|
| 383 |
+
"eval_runtime": 6.1098,
|
| 384 |
+
"eval_samples_per_second": 395.1,
|
| 385 |
+
"eval_steps_per_second": 24.714,
|
| 386 |
+
"step": 3940
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 16.24,
|
| 390 |
+
"learning_rate": 0.0004266512306782628,
|
| 391 |
+
"loss": 0.1307,
|
| 392 |
+
"step": 4000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 16.65,
|
| 396 |
+
"learning_rate": 0.00042156040946718344,
|
| 397 |
+
"loss": 0.1273,
|
| 398 |
+
"step": 4100
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 17.0,
|
| 402 |
+
"eval_accuracy": 0.39085189872265264,
|
| 403 |
+
"eval_loss": 0.1110914945602417,
|
| 404 |
+
"eval_runtime": 6.0921,
|
| 405 |
+
"eval_samples_per_second": 396.254,
|
| 406 |
+
"eval_steps_per_second": 24.786,
|
| 407 |
+
"step": 4186
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 17.06,
|
| 411 |
+
"learning_rate": 0.00041633142504139133,
|
| 412 |
+
"loss": 0.128,
|
| 413 |
+
"step": 4200
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 17.46,
|
| 417 |
+
"learning_rate": 0.00041096848847324417,
|
| 418 |
+
"loss": 0.1247,
|
| 419 |
+
"step": 4300
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 17.87,
|
| 423 |
+
"learning_rate": 0.0004054759187111451,
|
| 424 |
+
"loss": 0.1243,
|
| 425 |
+
"step": 4400
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 18.0,
|
| 429 |
+
"eval_accuracy": 0.39107313564645796,
|
| 430 |
+
"eval_loss": 0.10974010080099106,
|
| 431 |
+
"eval_runtime": 6.1271,
|
| 432 |
+
"eval_samples_per_second": 393.988,
|
| 433 |
+
"eval_steps_per_second": 24.645,
|
| 434 |
+
"step": 4432
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 18.27,
|
| 438 |
+
"learning_rate": 0.00039985813910135305,
|
| 439 |
+
"loss": 0.1231,
|
| 440 |
+
"step": 4500
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 18.68,
|
| 444 |
+
"learning_rate": 0.00039411967382571643,
|
| 445 |
+
"loss": 0.1205,
|
| 446 |
+
"step": 4600
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 19.0,
|
| 450 |
+
"eval_accuracy": 0.39124429836940194,
|
| 451 |
+
"eval_loss": 0.10775511711835861,
|
| 452 |
+
"eval_runtime": 6.146,
|
| 453 |
+
"eval_samples_per_second": 392.775,
|
| 454 |
+
"eval_steps_per_second": 24.569,
|
| 455 |
+
"step": 4678
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 19.09,
|
| 459 |
+
"learning_rate": 0.0003882651442582019,
|
| 460 |
+
"loss": 0.1193,
|
| 461 |
+
"step": 4700
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 19.49,
|
| 465 |
+
"learning_rate": 0.00038229926524315015,
|
| 466 |
+
"loss": 0.1175,
|
| 467 |
+
"step": 4800
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 19.9,
|
| 471 |
+
"learning_rate": 0.0003762268412982577,
|
| 472 |
+
"loss": 0.1202,
|
| 473 |
+
"step": 4900
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 20.0,
|
| 477 |
+
"eval_accuracy": 0.3915374600544443,
|
| 478 |
+
"eval_loss": 0.10535065084695816,
|
| 479 |
+
"eval_runtime": 6.1087,
|
| 480 |
+
"eval_samples_per_second": 395.174,
|
| 481 |
+
"eval_steps_per_second": 24.719,
|
| 482 |
+
"step": 4925
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 20.3,
|
| 486 |
+
"learning_rate": 0.00037005276274534144,
|
| 487 |
+
"loss": 0.1151,
|
| 488 |
+
"step": 5000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 20.71,
|
| 492 |
+
"learning_rate": 0.0003637820017720022,
|
| 493 |
+
"loss": 0.1146,
|
| 494 |
+
"step": 5100
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 21.0,
|
| 498 |
+
"eval_accuracy": 0.39146917705326983,
|
| 499 |
+
"eval_loss": 0.10494475811719894,
|
| 500 |
+
"eval_runtime": 6.135,
|
| 501 |
+
"eval_samples_per_second": 393.48,
|
| 502 |
+
"eval_steps_per_second": 24.613,
|
| 503 |
+
"step": 5171
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 21.12,
|
| 507 |
+
"learning_rate": 0.00035741960842735953,
|
| 508 |
+
"loss": 0.1152,
|
| 509 |
+
"step": 5200
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 21.52,
|
| 513 |
+
"learning_rate": 0.0003509707065550817,
|
| 514 |
+
"loss": 0.1133,
|
| 515 |
+
"step": 5300
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 21.93,
|
| 519 |
+
"learning_rate": 0.00034444048966698643,
|
| 520 |
+
"loss": 0.1119,
|
| 521 |
+
"step": 5400
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 22.0,
|
| 525 |
+
"eval_accuracy": 0.39147099793330115,
|
| 526 |
+
"eval_loss": 0.10487605631351471,
|
| 527 |
+
"eval_runtime": 6.1054,
|
| 528 |
+
"eval_samples_per_second": 395.389,
|
| 529 |
+
"eval_steps_per_second": 24.732,
|
| 530 |
+
"step": 5417
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 22.34,
|
| 534 |
+
"learning_rate": 0.0003378342167605362,
|
| 535 |
+
"loss": 0.11,
|
| 536 |
+
"step": 5500
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 22.74,
|
| 540 |
+
"learning_rate": 0.00033115720808359495,
|
| 541 |
+
"loss": 0.1107,
|
| 542 |
+
"step": 5600
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 23.0,
|
| 546 |
+
"eval_accuracy": 0.39174139861795204,
|
| 547 |
+
"eval_loss": 0.10271785408258438,
|
| 548 |
+
"eval_runtime": 6.1004,
|
| 549 |
+
"eval_samples_per_second": 395.715,
|
| 550 |
+
"eval_steps_per_second": 24.753,
|
| 551 |
+
"step": 5663
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 23.15,
|
| 555 |
+
"learning_rate": 0.0003244148408498587,
|
| 556 |
+
"loss": 0.1095,
|
| 557 |
+
"step": 5700
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 23.55,
|
| 561 |
+
"learning_rate": 0.000317612544908409,
|
| 562 |
+
"loss": 0.1067,
|
| 563 |
+
"step": 5800
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 23.96,
|
| 567 |
+
"learning_rate": 0.000310755798370878,
|
| 568 |
+
"loss": 0.1085,
|
| 569 |
+
"step": 5900
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 24.0,
|
| 573 |
+
"eval_accuracy": 0.391701339257263,
|
| 574 |
+
"eval_loss": 0.10227391123771667,
|
| 575 |
+
"eval_runtime": 6.1722,
|
| 576 |
+
"eval_samples_per_second": 391.109,
|
| 577 |
+
"eval_steps_per_second": 24.465,
|
| 578 |
+
"step": 5910
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 24.37,
|
| 582 |
+
"learning_rate": 0.00030385012319974537,
|
| 583 |
+
"loss": 0.1055,
|
| 584 |
+
"step": 6000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 24.77,
|
| 588 |
+
"learning_rate": 0.00029690108076132154,
|
| 589 |
+
"loss": 0.1068,
|
| 590 |
+
"step": 6100
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 25.0,
|
| 594 |
+
"eval_accuracy": 0.3917787266585941,
|
| 595 |
+
"eval_loss": 0.10184060782194138,
|
| 596 |
+
"eval_runtime": 6.1443,
|
| 597 |
+
"eval_samples_per_second": 392.883,
|
| 598 |
+
"eval_steps_per_second": 24.576,
|
| 599 |
+
"step": 6156
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 25.18,
|
| 603 |
+
"learning_rate": 0.0002899142673469971,
|
| 604 |
+
"loss": 0.1049,
|
| 605 |
+
"step": 6200
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 25.58,
|
| 609 |
+
"learning_rate": 0.00028289530966636625,
|
| 610 |
+
"loss": 0.1038,
|
| 611 |
+
"step": 6300
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 25.99,
|
| 615 |
+
"learning_rate": 0.000275849860315853,
|
| 616 |
+
"loss": 0.1045,
|
| 617 |
+
"step": 6400
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 26.0,
|
| 621 |
+
"eval_accuracy": 0.3920181723827126,
|
| 622 |
+
"eval_loss": 0.1005973368883133,
|
| 623 |
+
"eval_runtime": 6.0791,
|
| 624 |
+
"eval_samples_per_second": 397.098,
|
| 625 |
+
"eval_steps_per_second": 24.839,
|
| 626 |
+
"step": 6402
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 26.4,
|
| 630 |
+
"learning_rate": 0.0002687835932264908,
|
| 631 |
+
"loss": 0.1008,
|
| 632 |
+
"step": 6500
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 26.8,
|
| 636 |
+
"learning_rate": 0.0002617021990945197,
|
| 637 |
+
"loss": 0.1022,
|
| 638 |
+
"step": 6600
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 27.0,
|
| 642 |
+
"eval_accuracy": 0.39193259102124056,
|
| 643 |
+
"eval_loss": 0.10028840601444244,
|
| 644 |
+
"eval_runtime": 6.0776,
|
| 645 |
+
"eval_samples_per_second": 397.197,
|
| 646 |
+
"eval_steps_per_second": 24.845,
|
| 647 |
+
"step": 6648
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 27.21,
|
| 651 |
+
"learning_rate": 0.0002546113807984821,
|
| 652 |
+
"loss": 0.1011,
|
| 653 |
+
"step": 6700
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 27.61,
|
| 657 |
+
"learning_rate": 0.00024751684880650884,
|
| 658 |
+
"loss": 0.0995,
|
| 659 |
+
"step": 6800
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 28.0,
|
| 663 |
+
"eval_accuracy": 0.39223394666642386,
|
| 664 |
+
"eval_loss": 0.09900100529193878,
|
| 665 |
+
"eval_runtime": 6.1395,
|
| 666 |
+
"eval_samples_per_second": 393.191,
|
| 667 |
+
"eval_steps_per_second": 24.595,
|
| 668 |
+
"step": 6895
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 28.02,
|
| 672 |
+
"learning_rate": 0.00024042431657749118,
|
| 673 |
+
"loss": 0.1009,
|
| 674 |
+
"step": 6900
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 28.43,
|
| 678 |
+
"learning_rate": 0.0002333394959598461,
|
| 679 |
+
"loss": 0.0977,
|
| 680 |
+
"step": 7000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 28.83,
|
| 684 |
+
"learning_rate": 0.00022626809259157726,
|
| 685 |
+
"loss": 0.0989,
|
| 686 |
+
"step": 7100
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 29.0,
|
| 690 |
+
"eval_accuracy": 0.39221664830612635,
|
| 691 |
+
"eval_loss": 0.09937664866447449,
|
| 692 |
+
"eval_runtime": 6.1179,
|
| 693 |
+
"eval_samples_per_second": 394.581,
|
| 694 |
+
"eval_steps_per_second": 24.682,
|
| 695 |
+
"step": 7141
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 29.24,
|
| 699 |
+
"learning_rate": 0.00021921580130533828,
|
| 700 |
+
"loss": 0.0977,
|
| 701 |
+
"step": 7200
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 29.64,
|
| 705 |
+
"learning_rate": 0.0002121883015421973,
|
| 706 |
+
"loss": 0.0975,
|
| 707 |
+
"step": 7300
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 30.0,
|
| 711 |
+
"eval_accuracy": 0.3923249906679898,
|
| 712 |
+
"eval_loss": 0.09780476242303848,
|
| 713 |
+
"eval_runtime": 6.0619,
|
| 714 |
+
"eval_samples_per_second": 398.224,
|
| 715 |
+
"eval_steps_per_second": 24.91,
|
| 716 |
+
"step": 7387
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 30.05,
|
| 720 |
+
"learning_rate": 0.00020519125277779733,
|
| 721 |
+
"loss": 0.0964,
|
| 722 |
+
"step": 7400
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 30.46,
|
| 726 |
+
"learning_rate": 0.00019823028996459485,
|
| 727 |
+
"loss": 0.0941,
|
| 728 |
+
"step": 7500
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 30.86,
|
| 732 |
+
"learning_rate": 0.00019131101899384867,
|
| 733 |
+
"loss": 0.0956,
|
| 734 |
+
"step": 7600
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 31.0,
|
| 738 |
+
"eval_accuracy": 0.39216930542531203,
|
| 739 |
+
"eval_loss": 0.0990176796913147,
|
| 740 |
+
"eval_runtime": 6.1212,
|
| 741 |
+
"eval_samples_per_second": 394.37,
|
| 742 |
+
"eval_steps_per_second": 24.669,
|
| 743 |
+
"step": 7633
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 31.27,
|
| 747 |
+
"learning_rate": 0.00018443901218101152,
|
| 748 |
+
"loss": 0.0942,
|
| 749 |
+
"step": 7700
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 31.68,
|
| 753 |
+
"learning_rate": 0.00017761980377816285,
|
| 754 |
+
"loss": 0.0931,
|
| 755 |
+
"step": 7800
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 32.0,
|
| 759 |
+
"eval_accuracy": 0.39236231870863186,
|
| 760 |
+
"eval_loss": 0.09768786281347275,
|
| 761 |
+
"eval_runtime": 6.0866,
|
| 762 |
+
"eval_samples_per_second": 396.608,
|
| 763 |
+
"eval_steps_per_second": 24.809,
|
| 764 |
+
"step": 7880
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 32.08,
|
| 768 |
+
"learning_rate": 0.00017085888551709338,
|
| 769 |
+
"loss": 0.0945,
|
| 770 |
+
"step": 7900
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 32.49,
|
| 774 |
+
"learning_rate": 0.00016416170218663446,
|
| 775 |
+
"loss": 0.0916,
|
| 776 |
+
"step": 8000
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 32.89,
|
| 780 |
+
"learning_rate": 0.0001575336472477909,
|
| 781 |
+
"loss": 0.0926,
|
| 782 |
+
"step": 8100
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 33.0,
|
| 786 |
+
"eval_accuracy": 0.3922312153463769,
|
| 787 |
+
"eval_loss": 0.09789934009313583,
|
| 788 |
+
"eval_runtime": 6.1446,
|
| 789 |
+
"eval_samples_per_second": 392.866,
|
| 790 |
+
"eval_steps_per_second": 24.574,
|
| 791 |
+
"step": 8126
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 33.3,
|
| 795 |
+
"learning_rate": 0.0001509800584902108,
|
| 796 |
+
"loss": 0.0912,
|
| 797 |
+
"step": 8200
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 33.71,
|
| 801 |
+
"learning_rate": 0.00014450621373348819,
|
| 802 |
+
"loss": 0.0908,
|
| 803 |
+
"step": 8300
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 34.0,
|
| 807 |
+
"eval_accuracy": 0.3923732439888198,
|
| 808 |
+
"eval_loss": 0.09784437716007233,
|
| 809 |
+
"eval_runtime": 6.1319,
|
| 810 |
+
"eval_samples_per_second": 393.678,
|
| 811 |
+
"eval_steps_per_second": 24.625,
|
| 812 |
+
"step": 8372
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 34.11,
|
| 816 |
+
"learning_rate": 0.0001381173265767623,
|
| 817 |
+
"loss": 0.0905,
|
| 818 |
+
"step": 8400
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 34.52,
|
| 822 |
+
"learning_rate": 0.00013181854220003567,
|
| 823 |
+
"loss": 0.0895,
|
| 824 |
+
"step": 8500
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 34.92,
|
| 828 |
+
"learning_rate": 0.00012561493322059202,
|
| 829 |
+
"loss": 0.0896,
|
| 830 |
+
"step": 8600
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 35.0,
|
| 834 |
+
"eval_accuracy": 0.3924324225898377,
|
| 835 |
+
"eval_loss": 0.09740225225687027,
|
| 836 |
+
"eval_runtime": 6.1438,
|
| 837 |
+
"eval_samples_per_second": 392.916,
|
| 838 |
+
"eval_steps_per_second": 24.578,
|
| 839 |
+
"step": 8618
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 35.33,
|
| 843 |
+
"learning_rate": 0.00011951149560785166,
|
| 844 |
+
"loss": 0.0892,
|
| 845 |
+
"step": 8700
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 35.74,
|
| 849 |
+
"learning_rate": 0.0001135131446599535,
|
| 850 |
+
"loss": 0.0883,
|
| 851 |
+
"step": 8800
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 36.0,
|
| 855 |
+
"eval_accuracy": 0.3924469896300882,
|
| 856 |
+
"eval_loss": 0.09739205241203308,
|
| 857 |
+
"eval_runtime": 6.1304,
|
| 858 |
+
"eval_samples_per_second": 393.776,
|
| 859 |
+
"eval_steps_per_second": 24.631,
|
| 860 |
+
"step": 8865
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 36.14,
|
| 864 |
+
"learning_rate": 0.00010762471104530472,
|
| 865 |
+
"loss": 0.0877,
|
| 866 |
+
"step": 8900
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 36.55,
|
| 870 |
+
"learning_rate": 0.00010185093691228534,
|
| 871 |
+
"loss": 0.0866,
|
| 872 |
+
"step": 9000
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 36.95,
|
| 876 |
+
"learning_rate": 9.619647207024071e-05,
|
| 877 |
+
"loss": 0.0878,
|
| 878 |
+
"step": 9100
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 37.0,
|
| 882 |
+
"eval_accuracy": 0.3924242286296967,
|
| 883 |
+
"eval_loss": 0.0978410392999649,
|
| 884 |
+
"eval_runtime": 6.1135,
|
| 885 |
+
"eval_samples_per_second": 394.865,
|
| 886 |
+
"eval_steps_per_second": 24.699,
|
| 887 |
+
"step": 9111
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 37.36,
|
| 891 |
+
"learning_rate": 9.0665870244838e-05,
|
| 892 |
+
"loss": 0.0859,
|
| 893 |
+
"step": 9200
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 37.77,
|
| 897 |
+
"learning_rate": 8.526358541080173e-05,
|
| 898 |
+
"loss": 0.0865,
|
| 899 |
+
"step": 9300
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 38.0,
|
| 903 |
+
"eval_accuracy": 0.3925216457113723,
|
| 904 |
+
"eval_loss": 0.09711020439863205,
|
| 905 |
+
"eval_runtime": 6.1232,
|
| 906 |
+
"eval_samples_per_second": 394.237,
|
| 907 |
+
"eval_steps_per_second": 24.66,
|
| 908 |
+
"step": 9357
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 38.17,
|
| 912 |
+
"learning_rate": 7.999396820498208e-05,
|
| 913 |
+
"loss": 0.0857,
|
| 914 |
+
"step": 9400
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 38.58,
|
| 918 |
+
"learning_rate": 7.486126242264468e-05,
|
| 919 |
+
"loss": 0.085,
|
| 920 |
+
"step": 9500
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 38.98,
|
| 924 |
+
"learning_rate": 6.986960159980326e-05,
|
| 925 |
+
"loss": 0.0855,
|
| 926 |
+
"step": 9600
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 39.0,
|
| 930 |
+
"eval_accuracy": 0.3925689885921866,
|
| 931 |
+
"eval_loss": 0.09748318791389465,
|
| 932 |
+
"eval_runtime": 6.1096,
|
| 933 |
+
"eval_samples_per_second": 395.116,
|
| 934 |
+
"eval_steps_per_second": 24.715,
|
| 935 |
+
"step": 9603
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 39.39,
|
| 939 |
+
"learning_rate": 6.502300568434777e-05,
|
| 940 |
+
"loss": 0.0838,
|
| 941 |
+
"step": 9700
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 39.8,
|
| 945 |
+
"learning_rate": 6.0325377798648745e-05,
|
| 946 |
+
"loss": 0.0847,
|
| 947 |
+
"step": 9800
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 40.0,
|
| 951 |
+
"eval_accuracy": 0.3925434962717481,
|
| 952 |
+
"eval_loss": 0.0970187559723854,
|
| 953 |
+
"eval_runtime": 6.2108,
|
| 954 |
+
"eval_samples_per_second": 388.675,
|
| 955 |
+
"eval_steps_per_second": 24.312,
|
| 956 |
+
"step": 9850
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 40.2,
|
| 960 |
+
"learning_rate": 5.578050109624511e-05,
|
| 961 |
+
"loss": 0.0827,
|
| 962 |
+
"step": 9900
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 40.61,
|
| 966 |
+
"learning_rate": 5.139203571514672e-05,
|
| 967 |
+
"loss": 0.0835,
|
| 968 |
+
"step": 10000
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 41.0,
|
| 972 |
+
"eval_accuracy": 0.3925671677121553,
|
| 973 |
+
"eval_loss": 0.09726004302501678,
|
| 974 |
+
"eval_runtime": 6.0996,
|
| 975 |
+
"eval_samples_per_second": 395.763,
|
| 976 |
+
"eval_steps_per_second": 24.756,
|
| 977 |
+
"step": 10096
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 41.02,
|
| 981 |
+
"learning_rate": 4.716351583020542e-05,
|
| 982 |
+
"loss": 0.0831,
|
| 983 |
+
"step": 10100
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 41.42,
|
| 987 |
+
"learning_rate": 4.3098346806928315e-05,
|
| 988 |
+
"loss": 0.0821,
|
| 989 |
+
"step": 10200
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 41.83,
|
| 993 |
+
"learning_rate": 3.919980245902524e-05,
|
| 994 |
+
"loss": 0.0825,
|
| 995 |
+
"step": 10300
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 42.0,
|
| 999 |
+
"eval_accuracy": 0.392557152871983,
|
| 1000 |
+
"eval_loss": 0.09756684303283691,
|
| 1001 |
+
"eval_runtime": 6.1355,
|
| 1002 |
+
"eval_samples_per_second": 393.449,
|
| 1003 |
+
"eval_steps_per_second": 24.611,
|
| 1004 |
+
"step": 10342
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 42.23,
|
| 1008 |
+
"learning_rate": 3.5471022411899925e-05,
|
| 1009 |
+
"loss": 0.0825,
|
| 1010 |
+
"step": 10400
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 42.64,
|
| 1014 |
+
"learning_rate": 3.1915009574206264e-05,
|
| 1015 |
+
"loss": 0.0814,
|
| 1016 |
+
"step": 10500
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 43.0,
|
| 1020 |
+
"eval_accuracy": 0.3925817347524058,
|
| 1021 |
+
"eval_loss": 0.09748771786689758,
|
| 1022 |
+
"eval_runtime": 6.1103,
|
| 1023 |
+
"eval_samples_per_second": 395.068,
|
| 1024 |
+
"eval_steps_per_second": 24.712,
|
| 1025 |
+
"step": 10588
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 43.0,
|
| 1029 |
+
"step": 10588,
|
| 1030 |
+
"total_flos": 3084220612961280.0,
|
| 1031 |
+
"train_loss": 0.2331255912600619,
|
| 1032 |
+
"train_runtime": 2746.0841,
|
| 1033 |
+
"train_samples_per_second": 143.441,
|
| 1034 |
+
"train_steps_per_second": 4.479
|
| 1035 |
+
}
|
| 1036 |
+
],
|
| 1037 |
+
"max_steps": 12300,
|
| 1038 |
+
"num_train_epochs": 50,
|
| 1039 |
+
"total_flos": 3084220612961280.0,
|
| 1040 |
+
"trial_name": null,
|
| 1041 |
+
"trial_params": null
|
| 1042 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0db7b0d2599b04668617c424a3337e9f602ee02316377c982902ccf0e0c3346
|
| 3 |
+
size 3643
|