Hugging Face's logo

scilo
/
qwen_finetuned_11_5

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
david-scilo commited on
Commit
fbe5452
•
1 Parent(s): f2e990c

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +157 -0
trainer_state.json ADDED
@@ -0,0 +1,157 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 50.0,
5
+ "eval_steps": 5,
6
+ "global_step": 50,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 5.0,
13
+ "eval_loss": 3.9932637214660645,
14
+ "eval_runtime": 0.7232,
15
+ "eval_samples_per_second": 6.913,
16
+ "eval_steps_per_second": 1.383,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 10.0,
21
+ "grad_norm": 447.8272848066355,
22
+ "learning_rate": 9.698463103929542e-06,
23
+ "loss": 3.3273,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 10.0,
28
+ "eval_loss": 2.1877388954162598,
29
+ "eval_runtime": 1.187,
30
+ "eval_samples_per_second": 4.212,
31
+ "eval_steps_per_second": 0.842,
32
+ "step": 10
33
+ },
34
+ {
35
+ "epoch": 15.0,
36
+ "eval_loss": 2.1877388954162598,
37
+ "eval_runtime": 0.7203,
38
+ "eval_samples_per_second": 6.941,
39
+ "eval_steps_per_second": 1.388,
40
+ "step": 15
41
+ },
42
+ {
43
+ "epoch": 20.0,
44
+ "grad_norm": 196.9862804871096,
45
+ "learning_rate": 7.500000000000001e-06,
46
+ "loss": 1.7156,
47
+ "step": 20
48
+ },
49
+ {
50
+ "epoch": 20.0,
51
+ "eval_loss": 1.5716664791107178,
52
+ "eval_runtime": 0.8611,
53
+ "eval_samples_per_second": 5.806,
54
+ "eval_steps_per_second": 1.161,
55
+ "step": 20
56
+ },
57
+ {
58
+ "epoch": 25.0,
59
+ "eval_loss": 1.5716664791107178,
60
+ "eval_runtime": 0.7273,
61
+ "eval_samples_per_second": 6.875,
62
+ "eval_steps_per_second": 1.375,
63
+ "step": 25
64
+ },
65
+ {
66
+ "epoch": 30.0,
67
+ "grad_norm": 195.98568962834594,
68
+ "learning_rate": 4.131759111665349e-06,
69
+ "loss": 1.3707,
70
+ "step": 30
71
+ },
72
+ {
73
+ "epoch": 30.0,
74
+ "eval_loss": 1.355377435684204,
75
+ "eval_runtime": 1.3581,
76
+ "eval_samples_per_second": 3.682,
77
+ "eval_steps_per_second": 0.736,
78
+ "step": 30
79
+ },
80
+ {
81
+ "epoch": 35.0,
82
+ "eval_loss": 1.355377435684204,
83
+ "eval_runtime": 0.7213,
84
+ "eval_samples_per_second": 6.932,
85
+ "eval_steps_per_second": 1.386,
86
+ "step": 35
87
+ },
88
+ {
89
+ "epoch": 40.0,
90
+ "grad_norm": 131.74931566909007,
91
+ "learning_rate": 1.1697777844051105e-06,
92
+ "loss": 1.1402,
93
+ "step": 40
94
+ },
95
+ {
96
+ "epoch": 40.0,
97
+ "eval_loss": 1.2805026769638062,
98
+ "eval_runtime": 0.9702,
99
+ "eval_samples_per_second": 5.153,
100
+ "eval_steps_per_second": 1.031,
101
+ "step": 40
102
+ },
103
+ {
104
+ "epoch": 45.0,
105
+ "eval_loss": 1.2805026769638062,
106
+ "eval_runtime": 0.715,
107
+ "eval_samples_per_second": 6.993,
108
+ "eval_steps_per_second": 1.399,
109
+ "step": 45
110
+ },
111
+ {
112
+ "epoch": 50.0,
113
+ "grad_norm": 107.57180038242872,
114
+ "learning_rate": 0.0,
115
+ "loss": 1.0501,
116
+ "step": 50
117
+ },
118
+ {
119
+ "epoch": 50.0,
120
+ "eval_loss": 1.2817479372024536,
121
+ "eval_runtime": 1.1532,
122
+ "eval_samples_per_second": 4.336,
123
+ "eval_steps_per_second": 0.867,
124
+ "step": 50
125
+ },
126
+ {
127
+ "epoch": 50.0,
128
+ "step": 50,
129
+ "total_flos": 2010511278080.0,
130
+ "train_loss": 1.720783920288086,
131
+ "train_runtime": 395.0445,
132
+ "train_samples_per_second": 5.696,
133
+ "train_steps_per_second": 0.127
134
+ }
135
+ ],
136
+ "logging_steps": 10,
137
+ "max_steps": 50,
138
+ "num_input_tokens_seen": 0,
139
+ "num_train_epochs": 50,
140
+ "save_steps": 50,
141
+ "stateful_callbacks": {
142
+ "TrainerControl": {
143
+ "args": {
144
+ "should_epoch_stop": false,
145
+ "should_evaluate": false,
146
+ "should_log": false,
147
+ "should_save": true,
148
+ "should_training_stop": true
149
+ },
150
+ "attributes": {}
151
+ }
152
+ },
153
+ "total_flos": 2010511278080.0,
154
+ "train_batch_size": 5,
155
+ "trial_name": null,
156
+ "trial_params": null
157
+ }