Training in progress, epoch 8, checkpoint
Browse files- checkpoint-73/config.json +27 -0
- checkpoint-73/generation_config.json +6 -0
- checkpoint-73/model.safetensors +3 -0
- checkpoint-73/optimizer.pt +3 -0
- checkpoint-73/rng_state.pth +3 -0
- checkpoint-73/scheduler.pt +3 -0
- checkpoint-73/special_tokens_map.json +24 -0
- checkpoint-73/tokenizer.json +0 -0
- checkpoint-73/tokenizer_config.json +78 -0
- checkpoint-73/trainer_state.json +457 -0
- checkpoint-73/training_args.bin +3 -0
checkpoint-73/config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "lectura/TinyLlama-120M-news",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 768,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 2048,
|
13 |
+
"max_position_embeddings": 1024,
|
14 |
+
"model_type": "llama",
|
15 |
+
"num_attention_heads": 12,
|
16 |
+
"num_hidden_layers": 12,
|
17 |
+
"num_key_value_heads": 12,
|
18 |
+
"pretraining_tp": 1,
|
19 |
+
"rms_norm_eps": 1e-05,
|
20 |
+
"rope_scaling": null,
|
21 |
+
"rope_theta": 10000.0,
|
22 |
+
"tie_word_embeddings": true,
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.35.0",
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 46336
|
27 |
+
}
|
checkpoint-73/generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.35.0"
|
6 |
+
}
|
checkpoint-73/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9aa18d16a36e39ec6357bb3364bac57de56ba336cb634b1494cc8765a9c432fd
|
3 |
+
size 482171848
|
checkpoint-73/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fab2da5815e5b6e4e70c0e035a763e0c0b3acbf90820e563ef54953b7f83e4e4
|
3 |
+
size 964412154
|
checkpoint-73/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:adbac4581908b419c3039e502a4aacf8ebe77d7c5097a659c9e661f2ab321b78
|
3 |
+
size 14244
|
checkpoint-73/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:862cee2490235b1fb9ba612ca8e05a64e59447f883998526674bf1ee56bad2ad
|
3 |
+
size 1064
|
checkpoint-73/special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<unk>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
checkpoint-73/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-73/tokenizer_config.json
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<unk>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"46331": {
|
28 |
+
"content": "<|sep|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"46332": {
|
36 |
+
"content": "<|endoftext|>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"46333": {
|
44 |
+
"content": "<|acc|>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"46334": {
|
52 |
+
"content": "<|rrn|>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"46335": {
|
60 |
+
"content": "<|tel|>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
}
|
67 |
+
},
|
68 |
+
"bos_token": "<s>",
|
69 |
+
"clean_up_tokenization_spaces": false,
|
70 |
+
"eos_token": "</s>",
|
71 |
+
"legacy": false,
|
72 |
+
"model_max_length": 1000000000000000019884624838656,
|
73 |
+
"pad_token": "<unk>",
|
74 |
+
"sp_model_kwargs": {},
|
75 |
+
"tokenizer_class": "LlamaTokenizer",
|
76 |
+
"unk_token": "<unk>",
|
77 |
+
"use_default_system_prompt": false
|
78 |
+
}
|
checkpoint-73/trainer_state.json
ADDED
@@ -0,0 +1,457 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 8.984615384615385,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 73,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.12,
|
13 |
+
"learning_rate": 9.975000000000002e-06,
|
14 |
+
"loss": 12.7837,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.25,
|
19 |
+
"learning_rate": 9.950000000000001e-06,
|
20 |
+
"loss": 12.4595,
|
21 |
+
"step": 2
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.37,
|
25 |
+
"learning_rate": 9.925e-06,
|
26 |
+
"loss": 11.9117,
|
27 |
+
"step": 3
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.49,
|
31 |
+
"learning_rate": 9.9e-06,
|
32 |
+
"loss": 11.662,
|
33 |
+
"step": 4
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.62,
|
37 |
+
"learning_rate": 9.875000000000001e-06,
|
38 |
+
"loss": 11.4278,
|
39 |
+
"step": 5
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.74,
|
43 |
+
"learning_rate": 9.85e-06,
|
44 |
+
"loss": 11.1398,
|
45 |
+
"step": 6
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.86,
|
49 |
+
"learning_rate": 9.825000000000002e-06,
|
50 |
+
"loss": 10.9135,
|
51 |
+
"step": 7
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.98,
|
55 |
+
"learning_rate": 9.800000000000001e-06,
|
56 |
+
"loss": 10.8274,
|
57 |
+
"step": 8
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 1.11,
|
61 |
+
"learning_rate": 9.775e-06,
|
62 |
+
"loss": 10.5068,
|
63 |
+
"step": 9
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 1.23,
|
67 |
+
"learning_rate": 9.75e-06,
|
68 |
+
"loss": 10.3551,
|
69 |
+
"step": 10
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 1.35,
|
73 |
+
"learning_rate": 9.725000000000001e-06,
|
74 |
+
"loss": 10.1776,
|
75 |
+
"step": 11
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 1.48,
|
79 |
+
"learning_rate": 9.7e-06,
|
80 |
+
"loss": 10.0708,
|
81 |
+
"step": 12
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 1.6,
|
85 |
+
"learning_rate": 9.675000000000001e-06,
|
86 |
+
"loss": 9.8703,
|
87 |
+
"step": 13
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 1.72,
|
91 |
+
"learning_rate": 9.65e-06,
|
92 |
+
"loss": 9.7534,
|
93 |
+
"step": 14
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 1.85,
|
97 |
+
"learning_rate": 9.625e-06,
|
98 |
+
"loss": 9.6094,
|
99 |
+
"step": 15
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 1.97,
|
103 |
+
"learning_rate": 9.600000000000001e-06,
|
104 |
+
"loss": 9.3989,
|
105 |
+
"step": 16
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 2.09,
|
109 |
+
"learning_rate": 9.575e-06,
|
110 |
+
"loss": 9.2753,
|
111 |
+
"step": 17
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 2.22,
|
115 |
+
"learning_rate": 9.55e-06,
|
116 |
+
"loss": 9.138,
|
117 |
+
"step": 18
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 2.34,
|
121 |
+
"learning_rate": 9.525000000000001e-06,
|
122 |
+
"loss": 9.0598,
|
123 |
+
"step": 19
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 2.46,
|
127 |
+
"learning_rate": 9.5e-06,
|
128 |
+
"loss": 8.8535,
|
129 |
+
"step": 20
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 2.58,
|
133 |
+
"learning_rate": 9.475000000000002e-06,
|
134 |
+
"loss": 8.7378,
|
135 |
+
"step": 21
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 2.71,
|
139 |
+
"learning_rate": 9.450000000000001e-06,
|
140 |
+
"loss": 8.6082,
|
141 |
+
"step": 22
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 2.83,
|
145 |
+
"learning_rate": 9.425e-06,
|
146 |
+
"loss": 8.4904,
|
147 |
+
"step": 23
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 2.95,
|
151 |
+
"learning_rate": 9.4e-06,
|
152 |
+
"loss": 8.2918,
|
153 |
+
"step": 24
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 3.08,
|
157 |
+
"learning_rate": 9.375000000000001e-06,
|
158 |
+
"loss": 8.2553,
|
159 |
+
"step": 25
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 3.2,
|
163 |
+
"learning_rate": 9.350000000000002e-06,
|
164 |
+
"loss": 8.0724,
|
165 |
+
"step": 26
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 3.32,
|
169 |
+
"learning_rate": 9.325000000000001e-06,
|
170 |
+
"loss": 8.0029,
|
171 |
+
"step": 27
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 3.45,
|
175 |
+
"learning_rate": 9.3e-06,
|
176 |
+
"loss": 7.8227,
|
177 |
+
"step": 28
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 3.57,
|
181 |
+
"learning_rate": 9.275e-06,
|
182 |
+
"loss": 7.7003,
|
183 |
+
"step": 29
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 3.69,
|
187 |
+
"learning_rate": 9.250000000000001e-06,
|
188 |
+
"loss": 7.5943,
|
189 |
+
"step": 30
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 3.82,
|
193 |
+
"learning_rate": 9.225e-06,
|
194 |
+
"loss": 7.5119,
|
195 |
+
"step": 31
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 3.94,
|
199 |
+
"learning_rate": 9.200000000000002e-06,
|
200 |
+
"loss": 7.3673,
|
201 |
+
"step": 32
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 4.06,
|
205 |
+
"learning_rate": 9.175000000000001e-06,
|
206 |
+
"loss": 7.3051,
|
207 |
+
"step": 33
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 4.18,
|
211 |
+
"learning_rate": 9.15e-06,
|
212 |
+
"loss": 7.224,
|
213 |
+
"step": 34
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 4.31,
|
217 |
+
"learning_rate": 9.125e-06,
|
218 |
+
"loss": 7.0517,
|
219 |
+
"step": 35
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 4.43,
|
223 |
+
"learning_rate": 9.100000000000001e-06,
|
224 |
+
"loss": 7.0021,
|
225 |
+
"step": 36
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 4.55,
|
229 |
+
"learning_rate": 9.075e-06,
|
230 |
+
"loss": 6.9407,
|
231 |
+
"step": 37
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 4.68,
|
235 |
+
"learning_rate": 9.050000000000001e-06,
|
236 |
+
"loss": 6.7762,
|
237 |
+
"step": 38
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 4.8,
|
241 |
+
"learning_rate": 9.025e-06,
|
242 |
+
"loss": 6.7675,
|
243 |
+
"step": 39
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 4.92,
|
247 |
+
"learning_rate": 9e-06,
|
248 |
+
"loss": 6.6573,
|
249 |
+
"step": 40
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 5.05,
|
253 |
+
"learning_rate": 8.975e-06,
|
254 |
+
"loss": 6.6093,
|
255 |
+
"step": 41
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 5.17,
|
259 |
+
"learning_rate": 8.95e-06,
|
260 |
+
"loss": 6.5268,
|
261 |
+
"step": 42
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 5.29,
|
265 |
+
"learning_rate": 8.925e-06,
|
266 |
+
"loss": 6.4456,
|
267 |
+
"step": 43
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 5.42,
|
271 |
+
"learning_rate": 8.900000000000001e-06,
|
272 |
+
"loss": 6.4134,
|
273 |
+
"step": 44
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 5.54,
|
277 |
+
"learning_rate": 8.875e-06,
|
278 |
+
"loss": 6.3414,
|
279 |
+
"step": 45
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 5.66,
|
283 |
+
"learning_rate": 8.85e-06,
|
284 |
+
"loss": 6.2924,
|
285 |
+
"step": 46
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 5.78,
|
289 |
+
"learning_rate": 8.825000000000001e-06,
|
290 |
+
"loss": 6.2176,
|
291 |
+
"step": 47
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 5.91,
|
295 |
+
"learning_rate": 8.8e-06,
|
296 |
+
"loss": 6.1821,
|
297 |
+
"step": 48
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 6.03,
|
301 |
+
"learning_rate": 8.775e-06,
|
302 |
+
"loss": 6.1344,
|
303 |
+
"step": 49
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 6.15,
|
307 |
+
"learning_rate": 8.750000000000001e-06,
|
308 |
+
"loss": 6.0681,
|
309 |
+
"step": 50
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 6.28,
|
313 |
+
"learning_rate": 8.725000000000002e-06,
|
314 |
+
"loss": 6.0286,
|
315 |
+
"step": 51
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 6.4,
|
319 |
+
"learning_rate": 8.700000000000001e-06,
|
320 |
+
"loss": 5.9494,
|
321 |
+
"step": 52
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 6.52,
|
325 |
+
"learning_rate": 8.675e-06,
|
326 |
+
"loss": 5.9192,
|
327 |
+
"step": 53
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 6.65,
|
331 |
+
"learning_rate": 8.65e-06,
|
332 |
+
"loss": 5.8799,
|
333 |
+
"step": 54
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 6.77,
|
337 |
+
"learning_rate": 8.625000000000001e-06,
|
338 |
+
"loss": 5.8367,
|
339 |
+
"step": 55
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 6.89,
|
343 |
+
"learning_rate": 8.6e-06,
|
344 |
+
"loss": 5.7919,
|
345 |
+
"step": 56
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 7.02,
|
349 |
+
"learning_rate": 8.575000000000002e-06,
|
350 |
+
"loss": 5.7692,
|
351 |
+
"step": 57
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 7.14,
|
355 |
+
"learning_rate": 8.550000000000001e-06,
|
356 |
+
"loss": 5.7151,
|
357 |
+
"step": 58
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 7.26,
|
361 |
+
"learning_rate": 8.525e-06,
|
362 |
+
"loss": 5.6839,
|
363 |
+
"step": 59
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 7.38,
|
367 |
+
"learning_rate": 8.5e-06,
|
368 |
+
"loss": 5.6504,
|
369 |
+
"step": 60
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 7.51,
|
373 |
+
"learning_rate": 8.475000000000001e-06,
|
374 |
+
"loss": 5.6222,
|
375 |
+
"step": 61
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 7.63,
|
379 |
+
"learning_rate": 8.45e-06,
|
380 |
+
"loss": 5.5806,
|
381 |
+
"step": 62
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 7.75,
|
385 |
+
"learning_rate": 8.425000000000001e-06,
|
386 |
+
"loss": 5.5354,
|
387 |
+
"step": 63
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 7.88,
|
391 |
+
"learning_rate": 8.400000000000001e-06,
|
392 |
+
"loss": 5.4984,
|
393 |
+
"step": 64
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 8.0,
|
397 |
+
"learning_rate": 8.375e-06,
|
398 |
+
"loss": 5.4788,
|
399 |
+
"step": 65
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 8.12,
|
403 |
+
"learning_rate": 8.35e-06,
|
404 |
+
"loss": 5.4293,
|
405 |
+
"step": 66
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 8.25,
|
409 |
+
"learning_rate": 8.325e-06,
|
410 |
+
"loss": 5.4256,
|
411 |
+
"step": 67
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 8.37,
|
415 |
+
"learning_rate": 8.3e-06,
|
416 |
+
"loss": 5.3499,
|
417 |
+
"step": 68
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 8.49,
|
421 |
+
"learning_rate": 8.275000000000001e-06,
|
422 |
+
"loss": 5.3758,
|
423 |
+
"step": 69
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 8.62,
|
427 |
+
"learning_rate": 8.25e-06,
|
428 |
+
"loss": 5.3384,
|
429 |
+
"step": 70
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 8.74,
|
433 |
+
"learning_rate": 8.225e-06,
|
434 |
+
"loss": 5.3189,
|
435 |
+
"step": 71
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 8.86,
|
439 |
+
"learning_rate": 8.2e-06,
|
440 |
+
"loss": 5.2841,
|
441 |
+
"step": 72
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 8.98,
|
445 |
+
"learning_rate": 8.175e-06,
|
446 |
+
"loss": 5.2387,
|
447 |
+
"step": 73
|
448 |
+
}
|
449 |
+
],
|
450 |
+
"logging_steps": 1,
|
451 |
+
"max_steps": 400,
|
452 |
+
"num_train_epochs": 50,
|
453 |
+
"save_steps": 500,
|
454 |
+
"total_flos": 4857327107702784.0,
|
455 |
+
"trial_name": null,
|
456 |
+
"trial_params": null
|
457 |
+
}
|
checkpoint-73/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60568d4dd0f6572abe8a02d69c2d1f0c25627e4687509d3e2f27d2eb514e2587
|
3 |
+
size 4600
|