Hugging Face's logo

ellendagher
/
MNLP_M3_mcqa_model_test_22

Safetensors
qwen3
Model card Files
xet
Community
MNLP_M3_mcqa_model_test_22
File size: 4,494 Bytes 
64db8a7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
 
{
  "best_global_step": 1037,
  "best_metric": 0.49640655517578125,
  "best_model_checkpoint": "./mcqa_model_test_2/checkpoint-1037",
  "epoch": 0.9995180722891567,
  "eval_steps": 500,
  "global_step": 1037,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04819277108433735,
      "grad_norm": 42.9211540222168,
      "learning_rate": 4.2307692307692304e-07,
      "loss": 0.7894,
      "step": 50
    },
    {
      "epoch": 0.0963855421686747,
      "grad_norm": 72.75926208496094,
      "learning_rate": 9.038461538461538e-07,
      "loss": 0.6269,
      "step": 100
    },
    {
      "epoch": 0.14457831325301204,
      "grad_norm": 73.69217681884766,
      "learning_rate": 9.571275455519828e-07,
      "loss": 0.5828,
      "step": 150
    },
    {
      "epoch": 0.1927710843373494,
      "grad_norm": 49.02070617675781,
      "learning_rate": 9.035369774919614e-07,
      "loss": 0.5468,
      "step": 200
    },
    {
      "epoch": 0.24096385542168675,
      "grad_norm": 36.791542053222656,
      "learning_rate": 8.4994640943194e-07,
      "loss": 0.6211,
      "step": 250
    },
    {
      "epoch": 0.2891566265060241,
      "grad_norm": 76.28284454345703,
      "learning_rate": 7.963558413719184e-07,
      "loss": 0.5783,
      "step": 300
    },
    {
      "epoch": 0.3373493975903614,
      "grad_norm": 42.93614196777344,
      "learning_rate": 7.42765273311897e-07,
      "loss": 0.5927,
      "step": 350
    },
    {
      "epoch": 0.3855421686746988,
      "grad_norm": 68.8043212890625,
      "learning_rate": 6.891747052518756e-07,
      "loss": 0.5652,
      "step": 400
    },
    {
      "epoch": 0.43373493975903615,
      "grad_norm": 58.556663513183594,
      "learning_rate": 6.355841371918542e-07,
      "loss": 0.5515,
      "step": 450
    },
    {
      "epoch": 0.4819277108433735,
      "grad_norm": 47.458282470703125,
      "learning_rate": 5.819935691318327e-07,
      "loss": 0.5392,
      "step": 500
    },
    {
      "epoch": 0.5301204819277109,
      "grad_norm": 53.92032241821289,
      "learning_rate": 5.284030010718113e-07,
      "loss": 0.5744,
      "step": 550
    },
    {
      "epoch": 0.5783132530120482,
      "grad_norm": 61.76318359375,
      "learning_rate": 4.748124330117899e-07,
      "loss": 0.5361,
      "step": 600
    },
    {
      "epoch": 0.6265060240963856,
      "grad_norm": 40.69456481933594,
      "learning_rate": 4.2122186495176846e-07,
      "loss": 0.6077,
      "step": 650
    },
    {
      "epoch": 0.6746987951807228,
      "grad_norm": 80.4998550415039,
      "learning_rate": 3.6763129689174703e-07,
      "loss": 0.5567,
      "step": 700
    },
    {
      "epoch": 0.7228915662650602,
      "grad_norm": 45.61492156982422,
      "learning_rate": 3.140407288317256e-07,
      "loss": 0.5114,
      "step": 750
    },
    {
      "epoch": 0.7710843373493976,
      "grad_norm": 47.459102630615234,
      "learning_rate": 2.6045016077170417e-07,
      "loss": 0.4868,
      "step": 800
    },
    {
      "epoch": 0.8192771084337349,
      "grad_norm": 86.90262603759766,
      "learning_rate": 2.0685959271168274e-07,
      "loss": 0.5324,
      "step": 850
    },
    {
      "epoch": 0.8674698795180723,
      "grad_norm": 45.50479507446289,
      "learning_rate": 1.532690246516613e-07,
      "loss": 0.5092,
      "step": 900
    },
    {
      "epoch": 0.9156626506024096,
      "grad_norm": 44.45884323120117,
      "learning_rate": 9.967845659163988e-08,
      "loss": 0.556,
      "step": 950
    },
    {
      "epoch": 0.963855421686747,
      "grad_norm": 54.122867584228516,
      "learning_rate": 4.608788853161844e-08,
      "loss": 0.4876,
      "step": 1000
    },
    {
      "epoch": 0.9995180722891567,
      "eval_loss": 0.49640655517578125,
      "eval_runtime": 69.0344,
      "eval_samples_per_second": 45.064,
      "eval_steps_per_second": 5.635,
      "step": 1037
    }
  ],
  "logging_steps": 50,
  "max_steps": 1037,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7892894912348160.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}