Training in progress, epoch 2, checkpoint
Browse files
checkpoint-1110/config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/bart-large-mnli",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "gelu",
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"BartForSequenceClassification"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.0,
|
11 |
+
"bos_token_id": 0,
|
12 |
+
"classif_dropout": 0.0,
|
13 |
+
"classifier_dropout": 0.0,
|
14 |
+
"d_model": 1024,
|
15 |
+
"decoder_attention_heads": 16,
|
16 |
+
"decoder_ffn_dim": 4096,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 12,
|
19 |
+
"decoder_start_token_id": 2,
|
20 |
+
"dropout": 0.1,
|
21 |
+
"encoder_attention_heads": 16,
|
22 |
+
"encoder_ffn_dim": 4096,
|
23 |
+
"encoder_layerdrop": 0.0,
|
24 |
+
"encoder_layers": 12,
|
25 |
+
"eos_token_id": 2,
|
26 |
+
"forced_eos_token_id": 2,
|
27 |
+
"gradient_checkpointing": false,
|
28 |
+
"id2label": {
|
29 |
+
"0": "LABEL_0",
|
30 |
+
"1": "LABEL_1"
|
31 |
+
},
|
32 |
+
"init_std": 0.02,
|
33 |
+
"is_encoder_decoder": true,
|
34 |
+
"label2id": {
|
35 |
+
"LABEL_0": 0,
|
36 |
+
"LABEL_1": 1
|
37 |
+
},
|
38 |
+
"max_position_embeddings": 1024,
|
39 |
+
"model_type": "bart",
|
40 |
+
"normalize_before": false,
|
41 |
+
"num_hidden_layers": 12,
|
42 |
+
"output_past": false,
|
43 |
+
"pad_token_id": 1,
|
44 |
+
"scale_embedding": false,
|
45 |
+
"torch_dtype": "float32",
|
46 |
+
"transformers_version": "4.47.0",
|
47 |
+
"use_cache": true,
|
48 |
+
"vocab_size": 50265
|
49 |
+
}
|
checkpoint-1110/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c6f4bf1aa355bc7e15ea5973efde11a86297856278437b219a2af0ccb2071ef
|
3 |
+
size 1629432864
|
checkpoint-1110/trainer_state.json
ADDED
@@ -0,0 +1,832 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1110,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.018026137899954935,
|
13 |
+
"grad_norm": 21.723926544189453,
|
14 |
+
"learning_rate": 4.981949458483755e-05,
|
15 |
+
"loss": 0.8104,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.03605227579990987,
|
20 |
+
"grad_norm": 55.4254035949707,
|
21 |
+
"learning_rate": 4.963898916967509e-05,
|
22 |
+
"loss": 0.5178,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.054078413699864804,
|
27 |
+
"grad_norm": 41.4888801574707,
|
28 |
+
"learning_rate": 4.945848375451264e-05,
|
29 |
+
"loss": 0.5092,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.07210455159981974,
|
34 |
+
"grad_norm": 25.77608299255371,
|
35 |
+
"learning_rate": 4.927797833935018e-05,
|
36 |
+
"loss": 0.5581,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.09013068949977468,
|
41 |
+
"grad_norm": 61.5268669128418,
|
42 |
+
"learning_rate": 4.909747292418773e-05,
|
43 |
+
"loss": 0.5132,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.10815682739972961,
|
48 |
+
"grad_norm": 18.218244552612305,
|
49 |
+
"learning_rate": 4.891696750902527e-05,
|
50 |
+
"loss": 0.4614,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.12618296529968454,
|
55 |
+
"grad_norm": 30.51982879638672,
|
56 |
+
"learning_rate": 4.873646209386282e-05,
|
57 |
+
"loss": 0.4648,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.14420910319963948,
|
62 |
+
"grad_norm": 20.707260131835938,
|
63 |
+
"learning_rate": 4.855595667870036e-05,
|
64 |
+
"loss": 0.4317,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.16223524109959442,
|
69 |
+
"grad_norm": 21.699357986450195,
|
70 |
+
"learning_rate": 4.837545126353791e-05,
|
71 |
+
"loss": 0.4226,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.18026137899954936,
|
76 |
+
"grad_norm": 51.80731201171875,
|
77 |
+
"learning_rate": 4.819494584837546e-05,
|
78 |
+
"loss": 0.5002,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.19828751689950427,
|
83 |
+
"grad_norm": 44.694942474365234,
|
84 |
+
"learning_rate": 4.8014440433213e-05,
|
85 |
+
"loss": 0.4933,
|
86 |
+
"step": 110
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.21631365479945922,
|
90 |
+
"grad_norm": 22.704530715942383,
|
91 |
+
"learning_rate": 4.783393501805055e-05,
|
92 |
+
"loss": 0.4399,
|
93 |
+
"step": 120
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.23433979269941416,
|
97 |
+
"grad_norm": 26.04544448852539,
|
98 |
+
"learning_rate": 4.765342960288809e-05,
|
99 |
+
"loss": 0.438,
|
100 |
+
"step": 130
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.25236593059936907,
|
104 |
+
"grad_norm": 14.642335891723633,
|
105 |
+
"learning_rate": 4.747292418772563e-05,
|
106 |
+
"loss": 0.4591,
|
107 |
+
"step": 140
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.270392068499324,
|
111 |
+
"grad_norm": 16.13884162902832,
|
112 |
+
"learning_rate": 4.7292418772563177e-05,
|
113 |
+
"loss": 0.4546,
|
114 |
+
"step": 150
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.28841820639927895,
|
118 |
+
"grad_norm": 29.33772087097168,
|
119 |
+
"learning_rate": 4.711191335740072e-05,
|
120 |
+
"loss": 0.4665,
|
121 |
+
"step": 160
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.3064443442992339,
|
125 |
+
"grad_norm": 15.900433540344238,
|
126 |
+
"learning_rate": 4.693140794223827e-05,
|
127 |
+
"loss": 0.4703,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.32447048219918884,
|
132 |
+
"grad_norm": 17.246356964111328,
|
133 |
+
"learning_rate": 4.675090252707581e-05,
|
134 |
+
"loss": 0.426,
|
135 |
+
"step": 180
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.3424966200991438,
|
139 |
+
"grad_norm": 25.457477569580078,
|
140 |
+
"learning_rate": 4.657039711191336e-05,
|
141 |
+
"loss": 0.4711,
|
142 |
+
"step": 190
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.3605227579990987,
|
146 |
+
"grad_norm": 25.43963050842285,
|
147 |
+
"learning_rate": 4.63898916967509e-05,
|
148 |
+
"loss": 0.4547,
|
149 |
+
"step": 200
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.3785488958990536,
|
153 |
+
"grad_norm": 32.49702072143555,
|
154 |
+
"learning_rate": 4.620938628158845e-05,
|
155 |
+
"loss": 0.4603,
|
156 |
+
"step": 210
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.39657503379900855,
|
160 |
+
"grad_norm": 52.78520965576172,
|
161 |
+
"learning_rate": 4.602888086642599e-05,
|
162 |
+
"loss": 0.4471,
|
163 |
+
"step": 220
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.4146011716989635,
|
167 |
+
"grad_norm": 16.70362663269043,
|
168 |
+
"learning_rate": 4.584837545126354e-05,
|
169 |
+
"loss": 0.4393,
|
170 |
+
"step": 230
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.43262730959891843,
|
174 |
+
"grad_norm": 23.55246353149414,
|
175 |
+
"learning_rate": 4.566787003610109e-05,
|
176 |
+
"loss": 0.4256,
|
177 |
+
"step": 240
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.45065344749887337,
|
181 |
+
"grad_norm": 18.868804931640625,
|
182 |
+
"learning_rate": 4.548736462093863e-05,
|
183 |
+
"loss": 0.4324,
|
184 |
+
"step": 250
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.4686795853988283,
|
188 |
+
"grad_norm": 19.074827194213867,
|
189 |
+
"learning_rate": 4.530685920577618e-05,
|
190 |
+
"loss": 0.4419,
|
191 |
+
"step": 260
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.48670572329878325,
|
195 |
+
"grad_norm": 29.232803344726562,
|
196 |
+
"learning_rate": 4.5126353790613716e-05,
|
197 |
+
"loss": 0.4179,
|
198 |
+
"step": 270
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.5047318611987381,
|
202 |
+
"grad_norm": 17.780059814453125,
|
203 |
+
"learning_rate": 4.494584837545127e-05,
|
204 |
+
"loss": 0.3917,
|
205 |
+
"step": 280
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.5227579990986931,
|
209 |
+
"grad_norm": 13.99399471282959,
|
210 |
+
"learning_rate": 4.4765342960288806e-05,
|
211 |
+
"loss": 0.4321,
|
212 |
+
"step": 290
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.540784136998648,
|
216 |
+
"grad_norm": 14.700942039489746,
|
217 |
+
"learning_rate": 4.458483754512636e-05,
|
218 |
+
"loss": 0.4163,
|
219 |
+
"step": 300
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.558810274898603,
|
223 |
+
"grad_norm": 17.43704605102539,
|
224 |
+
"learning_rate": 4.44043321299639e-05,
|
225 |
+
"loss": 0.4268,
|
226 |
+
"step": 310
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.5768364127985579,
|
230 |
+
"grad_norm": 28.500301361083984,
|
231 |
+
"learning_rate": 4.422382671480145e-05,
|
232 |
+
"loss": 0.4229,
|
233 |
+
"step": 320
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.5948625506985128,
|
237 |
+
"grad_norm": 36.14088439941406,
|
238 |
+
"learning_rate": 4.404332129963899e-05,
|
239 |
+
"loss": 0.4559,
|
240 |
+
"step": 330
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.6128886885984678,
|
244 |
+
"grad_norm": 15.279230117797852,
|
245 |
+
"learning_rate": 4.386281588447654e-05,
|
246 |
+
"loss": 0.4067,
|
247 |
+
"step": 340
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.6309148264984227,
|
251 |
+
"grad_norm": 21.569740295410156,
|
252 |
+
"learning_rate": 4.368231046931408e-05,
|
253 |
+
"loss": 0.4298,
|
254 |
+
"step": 350
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.6489409643983777,
|
258 |
+
"grad_norm": 20.630115509033203,
|
259 |
+
"learning_rate": 4.350180505415163e-05,
|
260 |
+
"loss": 0.4173,
|
261 |
+
"step": 360
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.6669671022983326,
|
265 |
+
"grad_norm": 15.515020370483398,
|
266 |
+
"learning_rate": 4.332129963898917e-05,
|
267 |
+
"loss": 0.4063,
|
268 |
+
"step": 370
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.6849932401982876,
|
272 |
+
"grad_norm": 16.33180046081543,
|
273 |
+
"learning_rate": 4.314079422382672e-05,
|
274 |
+
"loss": 0.3651,
|
275 |
+
"step": 380
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.7030193780982424,
|
279 |
+
"grad_norm": 16.77664566040039,
|
280 |
+
"learning_rate": 4.296028880866426e-05,
|
281 |
+
"loss": 0.3879,
|
282 |
+
"step": 390
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.7210455159981974,
|
286 |
+
"grad_norm": 11.113824844360352,
|
287 |
+
"learning_rate": 4.277978339350181e-05,
|
288 |
+
"loss": 0.4205,
|
289 |
+
"step": 400
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.7390716538981523,
|
293 |
+
"grad_norm": 17.835678100585938,
|
294 |
+
"learning_rate": 4.259927797833935e-05,
|
295 |
+
"loss": 0.4466,
|
296 |
+
"step": 410
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.7570977917981072,
|
300 |
+
"grad_norm": 24.48379135131836,
|
301 |
+
"learning_rate": 4.24187725631769e-05,
|
302 |
+
"loss": 0.4084,
|
303 |
+
"step": 420
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.7751239296980622,
|
307 |
+
"grad_norm": 29.183530807495117,
|
308 |
+
"learning_rate": 4.223826714801444e-05,
|
309 |
+
"loss": 0.3588,
|
310 |
+
"step": 430
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.7931500675980171,
|
314 |
+
"grad_norm": 16.398386001586914,
|
315 |
+
"learning_rate": 4.205776173285199e-05,
|
316 |
+
"loss": 0.4594,
|
317 |
+
"step": 440
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.8111762054979721,
|
321 |
+
"grad_norm": 24.11660385131836,
|
322 |
+
"learning_rate": 4.187725631768953e-05,
|
323 |
+
"loss": 0.376,
|
324 |
+
"step": 450
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.829202343397927,
|
328 |
+
"grad_norm": 21.480924606323242,
|
329 |
+
"learning_rate": 4.169675090252708e-05,
|
330 |
+
"loss": 0.4035,
|
331 |
+
"step": 460
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.847228481297882,
|
335 |
+
"grad_norm": 11.91422176361084,
|
336 |
+
"learning_rate": 4.151624548736462e-05,
|
337 |
+
"loss": 0.4074,
|
338 |
+
"step": 470
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.8652546191978369,
|
342 |
+
"grad_norm": 17.17136001586914,
|
343 |
+
"learning_rate": 4.1335740072202167e-05,
|
344 |
+
"loss": 0.4259,
|
345 |
+
"step": 480
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.8832807570977917,
|
349 |
+
"grad_norm": 15.024781227111816,
|
350 |
+
"learning_rate": 4.115523465703972e-05,
|
351 |
+
"loss": 0.413,
|
352 |
+
"step": 490
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.9013068949977467,
|
356 |
+
"grad_norm": 15.877848625183105,
|
357 |
+
"learning_rate": 4.0974729241877256e-05,
|
358 |
+
"loss": 0.4013,
|
359 |
+
"step": 500
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.9193330328977016,
|
363 |
+
"grad_norm": 20.711393356323242,
|
364 |
+
"learning_rate": 4.079422382671481e-05,
|
365 |
+
"loss": 0.3875,
|
366 |
+
"step": 510
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.9373591707976566,
|
370 |
+
"grad_norm": 14.360701560974121,
|
371 |
+
"learning_rate": 4.0613718411552346e-05,
|
372 |
+
"loss": 0.4025,
|
373 |
+
"step": 520
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.9553853086976115,
|
377 |
+
"grad_norm": 16.94271469116211,
|
378 |
+
"learning_rate": 4.043321299638989e-05,
|
379 |
+
"loss": 0.3971,
|
380 |
+
"step": 530
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.9734114465975665,
|
384 |
+
"grad_norm": 23.218050003051758,
|
385 |
+
"learning_rate": 4.0252707581227436e-05,
|
386 |
+
"loss": 0.4305,
|
387 |
+
"step": 540
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.9914375844975214,
|
391 |
+
"grad_norm": 25.439455032348633,
|
392 |
+
"learning_rate": 4.007220216606498e-05,
|
393 |
+
"loss": 0.3969,
|
394 |
+
"step": 550
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 1.0,
|
398 |
+
"eval_f1": 0.8410362694300518,
|
399 |
+
"eval_loss": 0.36654186248779297,
|
400 |
+
"eval_precision": 0.7994483845547675,
|
401 |
+
"eval_recall": 0.8871884564932225,
|
402 |
+
"eval_runtime": 77.9824,
|
403 |
+
"eval_samples_per_second": 59.924,
|
404 |
+
"eval_steps_per_second": 7.502,
|
405 |
+
"step": 555
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 1.0090130689499774,
|
409 |
+
"grad_norm": 23.230247497558594,
|
410 |
+
"learning_rate": 3.989169675090253e-05,
|
411 |
+
"loss": 0.3393,
|
412 |
+
"step": 560
|
413 |
+
},
|
414 |
+
{
|
415 |
+
"epoch": 1.0270392068499323,
|
416 |
+
"grad_norm": 20.747711181640625,
|
417 |
+
"learning_rate": 3.971119133574007e-05,
|
418 |
+
"loss": 0.2951,
|
419 |
+
"step": 570
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 1.0450653447498874,
|
423 |
+
"grad_norm": 16.3277645111084,
|
424 |
+
"learning_rate": 3.953068592057762e-05,
|
425 |
+
"loss": 0.3178,
|
426 |
+
"step": 580
|
427 |
+
},
|
428 |
+
{
|
429 |
+
"epoch": 1.0630914826498423,
|
430 |
+
"grad_norm": 27.63875389099121,
|
431 |
+
"learning_rate": 3.935018050541516e-05,
|
432 |
+
"loss": 0.3043,
|
433 |
+
"step": 590
|
434 |
+
},
|
435 |
+
{
|
436 |
+
"epoch": 1.0811176205497972,
|
437 |
+
"grad_norm": 24.972593307495117,
|
438 |
+
"learning_rate": 3.916967509025271e-05,
|
439 |
+
"loss": 0.3521,
|
440 |
+
"step": 600
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 1.099143758449752,
|
444 |
+
"grad_norm": 22.260204315185547,
|
445 |
+
"learning_rate": 3.898916967509025e-05,
|
446 |
+
"loss": 0.2859,
|
447 |
+
"step": 610
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 1.117169896349707,
|
451 |
+
"grad_norm": 18.97205924987793,
|
452 |
+
"learning_rate": 3.88086642599278e-05,
|
453 |
+
"loss": 0.3159,
|
454 |
+
"step": 620
|
455 |
+
},
|
456 |
+
{
|
457 |
+
"epoch": 1.135196034249662,
|
458 |
+
"grad_norm": 25.5858097076416,
|
459 |
+
"learning_rate": 3.862815884476535e-05,
|
460 |
+
"loss": 0.2881,
|
461 |
+
"step": 630
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 1.153222172149617,
|
465 |
+
"grad_norm": 16.255144119262695,
|
466 |
+
"learning_rate": 3.844765342960289e-05,
|
467 |
+
"loss": 0.356,
|
468 |
+
"step": 640
|
469 |
+
},
|
470 |
+
{
|
471 |
+
"epoch": 1.1712483100495719,
|
472 |
+
"grad_norm": 16.83954429626465,
|
473 |
+
"learning_rate": 3.826714801444044e-05,
|
474 |
+
"loss": 0.2792,
|
475 |
+
"step": 650
|
476 |
+
},
|
477 |
+
{
|
478 |
+
"epoch": 1.1892744479495267,
|
479 |
+
"grad_norm": 13.091219902038574,
|
480 |
+
"learning_rate": 3.8086642599277976e-05,
|
481 |
+
"loss": 0.3232,
|
482 |
+
"step": 660
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 1.2073005858494819,
|
486 |
+
"grad_norm": 17.03887367248535,
|
487 |
+
"learning_rate": 3.790613718411553e-05,
|
488 |
+
"loss": 0.3081,
|
489 |
+
"step": 670
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 1.2253267237494367,
|
493 |
+
"grad_norm": 24.6894588470459,
|
494 |
+
"learning_rate": 3.7725631768953066e-05,
|
495 |
+
"loss": 0.29,
|
496 |
+
"step": 680
|
497 |
+
},
|
498 |
+
{
|
499 |
+
"epoch": 1.2433528616493916,
|
500 |
+
"grad_norm": 23.55462646484375,
|
501 |
+
"learning_rate": 3.754512635379062e-05,
|
502 |
+
"loss": 0.3232,
|
503 |
+
"step": 690
|
504 |
+
},
|
505 |
+
{
|
506 |
+
"epoch": 1.2613789995493465,
|
507 |
+
"grad_norm": 44.3718147277832,
|
508 |
+
"learning_rate": 3.7364620938628155e-05,
|
509 |
+
"loss": 0.2878,
|
510 |
+
"step": 700
|
511 |
+
},
|
512 |
+
{
|
513 |
+
"epoch": 1.2794051374493014,
|
514 |
+
"grad_norm": 21.339521408081055,
|
515 |
+
"learning_rate": 3.718411552346571e-05,
|
516 |
+
"loss": 0.2625,
|
517 |
+
"step": 710
|
518 |
+
},
|
519 |
+
{
|
520 |
+
"epoch": 1.2974312753492563,
|
521 |
+
"grad_norm": 22.27944564819336,
|
522 |
+
"learning_rate": 3.700361010830325e-05,
|
523 |
+
"loss": 0.3261,
|
524 |
+
"step": 720
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 1.3154574132492114,
|
528 |
+
"grad_norm": 20.857757568359375,
|
529 |
+
"learning_rate": 3.68231046931408e-05,
|
530 |
+
"loss": 0.3194,
|
531 |
+
"step": 730
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 1.3334835511491663,
|
535 |
+
"grad_norm": 15.615569114685059,
|
536 |
+
"learning_rate": 3.664259927797834e-05,
|
537 |
+
"loss": 0.3099,
|
538 |
+
"step": 740
|
539 |
+
},
|
540 |
+
{
|
541 |
+
"epoch": 1.3515096890491212,
|
542 |
+
"grad_norm": 13.210846900939941,
|
543 |
+
"learning_rate": 3.646209386281589e-05,
|
544 |
+
"loss": 0.2961,
|
545 |
+
"step": 750
|
546 |
+
},
|
547 |
+
{
|
548 |
+
"epoch": 1.3695358269490763,
|
549 |
+
"grad_norm": 20.196102142333984,
|
550 |
+
"learning_rate": 3.628158844765343e-05,
|
551 |
+
"loss": 0.3099,
|
552 |
+
"step": 760
|
553 |
+
},
|
554 |
+
{
|
555 |
+
"epoch": 1.3875619648490312,
|
556 |
+
"grad_norm": 14.043251991271973,
|
557 |
+
"learning_rate": 3.610108303249098e-05,
|
558 |
+
"loss": 0.3548,
|
559 |
+
"step": 770
|
560 |
+
},
|
561 |
+
{
|
562 |
+
"epoch": 1.405588102748986,
|
563 |
+
"grad_norm": 31.82477569580078,
|
564 |
+
"learning_rate": 3.592057761732852e-05,
|
565 |
+
"loss": 0.3255,
|
566 |
+
"step": 780
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 1.423614240648941,
|
570 |
+
"grad_norm": 19.933557510375977,
|
571 |
+
"learning_rate": 3.574007220216607e-05,
|
572 |
+
"loss": 0.3404,
|
573 |
+
"step": 790
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 1.4416403785488958,
|
577 |
+
"grad_norm": 27.846755981445312,
|
578 |
+
"learning_rate": 3.555956678700361e-05,
|
579 |
+
"loss": 0.3054,
|
580 |
+
"step": 800
|
581 |
+
},
|
582 |
+
{
|
583 |
+
"epoch": 1.4596665164488507,
|
584 |
+
"grad_norm": 18.607879638671875,
|
585 |
+
"learning_rate": 3.537906137184116e-05,
|
586 |
+
"loss": 0.2802,
|
587 |
+
"step": 810
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 1.4776926543488058,
|
591 |
+
"grad_norm": 29.801652908325195,
|
592 |
+
"learning_rate": 3.51985559566787e-05,
|
593 |
+
"loss": 0.2975,
|
594 |
+
"step": 820
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 1.4957187922487607,
|
598 |
+
"grad_norm": 21.80506134033203,
|
599 |
+
"learning_rate": 3.5018050541516247e-05,
|
600 |
+
"loss": 0.3251,
|
601 |
+
"step": 830
|
602 |
+
},
|
603 |
+
{
|
604 |
+
"epoch": 1.5137449301487156,
|
605 |
+
"grad_norm": 12.826874732971191,
|
606 |
+
"learning_rate": 3.483754512635379e-05,
|
607 |
+
"loss": 0.2943,
|
608 |
+
"step": 840
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 1.5317710680486707,
|
612 |
+
"grad_norm": 23.97177505493164,
|
613 |
+
"learning_rate": 3.4657039711191336e-05,
|
614 |
+
"loss": 0.3221,
|
615 |
+
"step": 850
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 1.5497972059486256,
|
619 |
+
"grad_norm": 20.326284408569336,
|
620 |
+
"learning_rate": 3.447653429602888e-05,
|
621 |
+
"loss": 0.3276,
|
622 |
+
"step": 860
|
623 |
+
},
|
624 |
+
{
|
625 |
+
"epoch": 1.5678233438485805,
|
626 |
+
"grad_norm": 19.27255630493164,
|
627 |
+
"learning_rate": 3.4296028880866426e-05,
|
628 |
+
"loss": 0.3338,
|
629 |
+
"step": 870
|
630 |
+
},
|
631 |
+
{
|
632 |
+
"epoch": 1.5858494817485354,
|
633 |
+
"grad_norm": 17.299917221069336,
|
634 |
+
"learning_rate": 3.411552346570397e-05,
|
635 |
+
"loss": 0.3177,
|
636 |
+
"step": 880
|
637 |
+
},
|
638 |
+
{
|
639 |
+
"epoch": 1.6038756196484902,
|
640 |
+
"grad_norm": 15.277181625366211,
|
641 |
+
"learning_rate": 3.3935018050541516e-05,
|
642 |
+
"loss": 0.2773,
|
643 |
+
"step": 890
|
644 |
+
},
|
645 |
+
{
|
646 |
+
"epoch": 1.6219017575484451,
|
647 |
+
"grad_norm": 27.945833206176758,
|
648 |
+
"learning_rate": 3.375451263537907e-05,
|
649 |
+
"loss": 0.3417,
|
650 |
+
"step": 900
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 1.6399278954484002,
|
654 |
+
"grad_norm": 25.78679847717285,
|
655 |
+
"learning_rate": 3.3574007220216606e-05,
|
656 |
+
"loss": 0.2959,
|
657 |
+
"step": 910
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 1.6579540333483551,
|
661 |
+
"grad_norm": 17.608028411865234,
|
662 |
+
"learning_rate": 3.339350180505416e-05,
|
663 |
+
"loss": 0.273,
|
664 |
+
"step": 920
|
665 |
+
},
|
666 |
+
{
|
667 |
+
"epoch": 1.67598017124831,
|
668 |
+
"grad_norm": 17.937299728393555,
|
669 |
+
"learning_rate": 3.3212996389891696e-05,
|
670 |
+
"loss": 0.3121,
|
671 |
+
"step": 930
|
672 |
+
},
|
673 |
+
{
|
674 |
+
"epoch": 1.694006309148265,
|
675 |
+
"grad_norm": 22.207386016845703,
|
676 |
+
"learning_rate": 3.303249097472924e-05,
|
677 |
+
"loss": 0.3389,
|
678 |
+
"step": 940
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"epoch": 1.71203244704822,
|
682 |
+
"grad_norm": 40.351959228515625,
|
683 |
+
"learning_rate": 3.2851985559566786e-05,
|
684 |
+
"loss": 0.3138,
|
685 |
+
"step": 950
|
686 |
+
},
|
687 |
+
{
|
688 |
+
"epoch": 1.7300585849481749,
|
689 |
+
"grad_norm": 23.845033645629883,
|
690 |
+
"learning_rate": 3.267148014440433e-05,
|
691 |
+
"loss": 0.2865,
|
692 |
+
"step": 960
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 1.7480847228481298,
|
696 |
+
"grad_norm": 18.095985412597656,
|
697 |
+
"learning_rate": 3.249097472924188e-05,
|
698 |
+
"loss": 0.294,
|
699 |
+
"step": 970
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 1.7661108607480847,
|
703 |
+
"grad_norm": 25.775617599487305,
|
704 |
+
"learning_rate": 3.231046931407942e-05,
|
705 |
+
"loss": 0.2785,
|
706 |
+
"step": 980
|
707 |
+
},
|
708 |
+
{
|
709 |
+
"epoch": 1.7841369986480395,
|
710 |
+
"grad_norm": 20.0789737701416,
|
711 |
+
"learning_rate": 3.212996389891697e-05,
|
712 |
+
"loss": 0.3533,
|
713 |
+
"step": 990
|
714 |
+
},
|
715 |
+
{
|
716 |
+
"epoch": 1.8021631365479944,
|
717 |
+
"grad_norm": 26.862163543701172,
|
718 |
+
"learning_rate": 3.194945848375451e-05,
|
719 |
+
"loss": 0.2957,
|
720 |
+
"step": 1000
|
721 |
+
},
|
722 |
+
{
|
723 |
+
"epoch": 1.8201892744479495,
|
724 |
+
"grad_norm": 24.20423698425293,
|
725 |
+
"learning_rate": 3.176895306859206e-05,
|
726 |
+
"loss": 0.3195,
|
727 |
+
"step": 1010
|
728 |
+
},
|
729 |
+
{
|
730 |
+
"epoch": 1.8382154123479044,
|
731 |
+
"grad_norm": 25.36762809753418,
|
732 |
+
"learning_rate": 3.15884476534296e-05,
|
733 |
+
"loss": 0.2823,
|
734 |
+
"step": 1020
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 1.8562415502478595,
|
738 |
+
"grad_norm": 37.54848098754883,
|
739 |
+
"learning_rate": 3.140794223826715e-05,
|
740 |
+
"loss": 0.3557,
|
741 |
+
"step": 1030
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 1.8742676881478144,
|
745 |
+
"grad_norm": 24.26515769958496,
|
746 |
+
"learning_rate": 3.12274368231047e-05,
|
747 |
+
"loss": 0.3194,
|
748 |
+
"step": 1040
|
749 |
+
},
|
750 |
+
{
|
751 |
+
"epoch": 1.8922938260477693,
|
752 |
+
"grad_norm": 22.1879940032959,
|
753 |
+
"learning_rate": 3.104693140794224e-05,
|
754 |
+
"loss": 0.2912,
|
755 |
+
"step": 1050
|
756 |
+
},
|
757 |
+
{
|
758 |
+
"epoch": 1.9103199639477242,
|
759 |
+
"grad_norm": 21.703449249267578,
|
760 |
+
"learning_rate": 3.086642599277979e-05,
|
761 |
+
"loss": 0.2635,
|
762 |
+
"step": 1060
|
763 |
+
},
|
764 |
+
{
|
765 |
+
"epoch": 1.928346101847679,
|
766 |
+
"grad_norm": 33.39324951171875,
|
767 |
+
"learning_rate": 3.0685920577617325e-05,
|
768 |
+
"loss": 0.2943,
|
769 |
+
"step": 1070
|
770 |
+
},
|
771 |
+
{
|
772 |
+
"epoch": 1.946372239747634,
|
773 |
+
"grad_norm": 21.398008346557617,
|
774 |
+
"learning_rate": 3.0505415162454877e-05,
|
775 |
+
"loss": 0.353,
|
776 |
+
"step": 1080
|
777 |
+
},
|
778 |
+
{
|
779 |
+
"epoch": 1.9643983776475888,
|
780 |
+
"grad_norm": 17.463472366333008,
|
781 |
+
"learning_rate": 3.032490974729242e-05,
|
782 |
+
"loss": 0.2934,
|
783 |
+
"step": 1090
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"epoch": 1.982424515547544,
|
787 |
+
"grad_norm": 32.96004104614258,
|
788 |
+
"learning_rate": 3.0144404332129967e-05,
|
789 |
+
"loss": 0.3206,
|
790 |
+
"step": 1100
|
791 |
+
},
|
792 |
+
{
|
793 |
+
"epoch": 2.0,
|
794 |
+
"grad_norm": 22.864667892456055,
|
795 |
+
"learning_rate": 2.996389891696751e-05,
|
796 |
+
"loss": 0.2765,
|
797 |
+
"step": 1110
|
798 |
+
},
|
799 |
+
{
|
800 |
+
"epoch": 2.0,
|
801 |
+
"eval_f1": 0.8415584415584415,
|
802 |
+
"eval_loss": 0.3972894847393036,
|
803 |
+
"eval_precision": 0.7748344370860927,
|
804 |
+
"eval_recall": 0.9208570179274158,
|
805 |
+
"eval_runtime": 67.5759,
|
806 |
+
"eval_samples_per_second": 69.152,
|
807 |
+
"eval_steps_per_second": 8.657,
|
808 |
+
"step": 1110
|
809 |
+
}
|
810 |
+
],
|
811 |
+
"logging_steps": 10,
|
812 |
+
"max_steps": 2770,
|
813 |
+
"num_input_tokens_seen": 0,
|
814 |
+
"num_train_epochs": 5,
|
815 |
+
"save_steps": 500,
|
816 |
+
"stateful_callbacks": {
|
817 |
+
"TrainerControl": {
|
818 |
+
"args": {
|
819 |
+
"should_epoch_stop": false,
|
820 |
+
"should_evaluate": false,
|
821 |
+
"should_log": false,
|
822 |
+
"should_save": true,
|
823 |
+
"should_training_stop": false
|
824 |
+
},
|
825 |
+
"attributes": {}
|
826 |
+
}
|
827 |
+
},
|
828 |
+
"total_flos": 3.858514256176742e+16,
|
829 |
+
"train_batch_size": 8,
|
830 |
+
"trial_name": null,
|
831 |
+
"trial_params": null
|
832 |
+
}
|
checkpoint-1110/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd360ff6566a7421740b08164da56480ee843ecd9962d79899c9150e4be0d68e
|
3 |
+
size 5432
|