Hugging Face's logo

clejordan
/
MNLP_M3_quantized_model

Text Generation
Transformers
Safetensors
qwen3
conversational
text-generation-inference
8-bit precision
bitsandbytes
Model card Files
xet
 Community
clejordan commited on
Commit
ded5c59
·
verified ·
1 Parent(s): bf775a2

Delete checkpoint-8760/trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. checkpoint-8760/trainer_state.json +0 -177
checkpoint-8760/trainer_state.json DELETED
@@ -1,177 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 3.0,
6
- "eval_steps": 500,
7
- "global_step": 8760,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 0.17123287671232876,
14
- "grad_norm": 0.17268113791942596,
15
- "learning_rate": 0.00018867579908675802,
16
- "loss": 0.1977,
17
- "step": 500
18
- },
19
- {
20
- "epoch": 0.3424657534246575,
21
- "grad_norm": 0.2097366750240326,
22
- "learning_rate": 0.00017726027397260274,
23
- "loss": 0.1371,
24
- "step": 1000
25
- },
26
- {
27
- "epoch": 0.5136986301369864,
28
- "grad_norm": 0.2663485109806061,
29
- "learning_rate": 0.0001658447488584475,
30
- "loss": 0.1345,
31
- "step": 1500
32
- },
33
- {
34
- "epoch": 0.684931506849315,
35
- "grad_norm": 0.16753822565078735,
36
- "learning_rate": 0.00015442922374429225,
37
- "loss": 0.1346,
38
- "step": 2000
39
- },
40
- {
41
- "epoch": 0.8561643835616438,
42
- "grad_norm": 0.1972370743751526,
43
- "learning_rate": 0.00014301369863013697,
44
- "loss": 0.1346,
45
- "step": 2500
46
- },
47
- {
48
- "epoch": 1.0,
49
- "eval_loss": 0.13700313866138458,
50
- "eval_runtime": 31.6412,
51
- "eval_samples_per_second": 31.604,
52
- "eval_steps_per_second": 7.901,
53
- "step": 2920
54
- },
55
- {
56
- "epoch": 1.0273972602739727,
57
- "grad_norm": 0.22729772329330444,
58
- "learning_rate": 0.00013159817351598174,
59
- "loss": 0.1305,
60
- "step": 3000
61
- },
62
- {
63
- "epoch": 1.1986301369863013,
64
- "grad_norm": 0.2352839708328247,
65
- "learning_rate": 0.00012018264840182649,
66
- "loss": 0.1164,
67
- "step": 3500
68
- },
69
- {
70
- "epoch": 1.36986301369863,
71
- "grad_norm": 0.1942291408777237,
72
- "learning_rate": 0.00010876712328767125,
73
- "loss": 0.1177,
74
- "step": 4000
75
- },
76
- {
77
- "epoch": 1.541095890410959,
78
- "grad_norm": 0.19947709143161774,
79
- "learning_rate": 9.735159817351599e-05,
80
- "loss": 0.1193,
81
- "step": 4500
82
- },
83
- {
84
- "epoch": 1.7123287671232876,
85
- "grad_norm": 0.23757582902908325,
86
- "learning_rate": 8.593607305936074e-05,
87
- "loss": 0.1158,
88
- "step": 5000
89
- },
90
- {
91
- "epoch": 1.8835616438356164,
92
- "grad_norm": 0.27170926332473755,
93
- "learning_rate": 7.452054794520548e-05,
94
- "loss": 0.1183,
95
- "step": 5500
96
- },
97
- {
98
- "epoch": 2.0,
99
- "eval_loss": 0.1377769559621811,
100
- "eval_runtime": 31.7008,
101
- "eval_samples_per_second": 31.545,
102
- "eval_steps_per_second": 7.886,
103
- "step": 5840
104
- },
105
- {
106
- "epoch": 2.0547945205479454,
107
- "grad_norm": 0.29543906450271606,
108
- "learning_rate": 6.310502283105023e-05,
109
- "loss": 0.1097,
110
- "step": 6000
111
- },
112
- {
113
- "epoch": 2.2260273972602738,
114
- "grad_norm": 0.4334782063961029,
115
- "learning_rate": 5.1689497716894973e-05,
116
- "loss": 0.0995,
117
- "step": 6500
118
- },
119
- {
120
- "epoch": 2.3972602739726026,
121
- "grad_norm": 0.28854918479919434,
122
- "learning_rate": 4.027397260273973e-05,
123
- "loss": 0.0986,
124
- "step": 7000
125
- },
126
- {
127
- "epoch": 2.5684931506849313,
128
- "grad_norm": 0.2981366515159607,
129
- "learning_rate": 2.8858447488584477e-05,
130
- "loss": 0.0982,
131
- "step": 7500
132
- },
133
- {
134
- "epoch": 2.73972602739726,
135
- "grad_norm": 0.28199276328086853,
136
- "learning_rate": 1.7442922374429226e-05,
137
- "loss": 0.0985,
138
- "step": 8000
139
- },
140
- {
141
- "epoch": 2.910958904109589,
142
- "grad_norm": 0.34423625469207764,
143
- "learning_rate": 6.027397260273973e-06,
144
- "loss": 0.0983,
145
- "step": 8500
146
- },
147
- {
148
- "epoch": 3.0,
149
- "eval_loss": 0.14507943391799927,
150
- "eval_runtime": 31.6284,
151
- "eval_samples_per_second": 31.617,
152
- "eval_steps_per_second": 7.904,
153
- "step": 8760
154
- }
155
- ],
156
- "logging_steps": 500,
157
- "max_steps": 8760,
158
- "num_input_tokens_seen": 0,
159
- "num_train_epochs": 3,
160
- "save_steps": 500,
161
- "stateful_callbacks": {
162
- "TrainerControl": {
163
- "args": {
164
- "should_epoch_stop": false,
165
- "should_evaluate": false,
166
- "should_log": false,
167
- "should_save": true,
168
- "should_training_stop": true
169
- },
170
- "attributes": {}
171
- }
172
- },
173
- "total_flos": 4.795227490693939e+16,
174
- "train_batch_size": 4,
175
- "trial_name": null,
176
- "trial_params": null
177
- }