Hugging Face's logo

jfranklin-foundry
/
Qwen-Qwen1.5-1.8B-1726833051

PEFT
Safetensors
Model card Files Community
Qwen-Qwen1.5-1.8B-1726833051
File size: 4,697 Bytes 
2f4f33a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
184
185
186
187
188
189
190
 
{
  "best_metric": 0.9539479613304138,
  "best_model_checkpoint": "outputs/checkpoint-231",
  "epoch": 6.995951417004049,
  "eval_steps": 500,
  "global_step": 324,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4318488529014845,
      "grad_norm": 0.7265238165855408,
      "learning_rate": 4e-05,
      "loss": 2.2901,
      "step": 20
    },
    {
      "epoch": 0.863697705802969,
      "grad_norm": 0.4902186989784241,
      "learning_rate": 8e-05,
      "loss": 2.0553,
      "step": 40
    },
    {
      "epoch": 0.9932523616734144,
      "eval_loss": 1.7082113027572632,
      "eval_runtime": 11.6752,
      "eval_samples_per_second": 31.862,
      "eval_steps_per_second": 4.026,
      "step": 46
    },
    {
      "epoch": 1.2955465587044535,
      "grad_norm": 0.5778974294662476,
      "learning_rate": 0.00012,
      "loss": 1.9034,
      "step": 60
    },
    {
      "epoch": 1.7273954116059378,
      "grad_norm": 0.818723201751709,
      "learning_rate": 0.00016,
      "loss": 1.6895,
      "step": 80
    },
    {
      "epoch": 1.9865047233468287,
      "eval_loss": 1.3229522705078125,
      "eval_runtime": 11.7014,
      "eval_samples_per_second": 31.791,
      "eval_steps_per_second": 4.017,
      "step": 92
    },
    {
      "epoch": 2.1592442645074224,
      "grad_norm": 1.2037190198898315,
      "learning_rate": 0.0002,
      "loss": 1.5763,
      "step": 100
    },
    {
      "epoch": 2.591093117408907,
      "grad_norm": 1.2296253442764282,
      "learning_rate": 0.00019978499773373596,
      "loss": 1.3997,
      "step": 120
    },
    {
      "epoch": 2.979757085020243,
      "eval_loss": 1.0936287641525269,
      "eval_runtime": 11.7036,
      "eval_samples_per_second": 31.785,
      "eval_steps_per_second": 4.016,
      "step": 138
    },
    {
      "epoch": 3.0229419703103915,
      "grad_norm": 1.3699569702148438,
      "learning_rate": 0.0001991409154544338,
      "loss": 1.3491,
      "step": 140
    },
    {
      "epoch": 3.454790823211876,
      "grad_norm": 1.451266884803772,
      "learning_rate": 0.00019807052274508773,
      "loss": 1.1626,
      "step": 160
    },
    {
      "epoch": 3.8866396761133606,
      "grad_norm": 1.3704801797866821,
      "learning_rate": 0.0001965784223428638,
      "loss": 1.1558,
      "step": 180
    },
    {
      "epoch": 3.9946018893387314,
      "eval_loss": 0.9916501641273499,
      "eval_runtime": 11.7248,
      "eval_samples_per_second": 31.728,
      "eval_steps_per_second": 4.009,
      "step": 185
    },
    {
      "epoch": 4.318488529014845,
      "grad_norm": 1.6158828735351562,
      "learning_rate": 0.0001946710303471214,
      "loss": 1.0048,
      "step": 200
    },
    {
      "epoch": 4.75033738191633,
      "grad_norm": 1.7279417514801025,
      "learning_rate": 0.00019235654862989537,
      "loss": 1.0293,
      "step": 220
    },
    {
      "epoch": 4.987854251012146,
      "eval_loss": 0.9539479613304138,
      "eval_runtime": 11.7041,
      "eval_samples_per_second": 31.784,
      "eval_steps_per_second": 4.016,
      "step": 231
    },
    {
      "epoch": 5.182186234817814,
      "grad_norm": 1.5809475183486938,
      "learning_rate": 0.00018964492956747425,
      "loss": 0.966,
      "step": 240
    },
    {
      "epoch": 5.614035087719298,
      "grad_norm": 1.6080421209335327,
      "learning_rate": 0.00018654783324473137,
      "loss": 0.8655,
      "step": 260
    },
    {
      "epoch": 5.98110661268556,
      "eval_loss": 0.979802131652832,
      "eval_runtime": 11.7244,
      "eval_samples_per_second": 31.729,
      "eval_steps_per_second": 4.009,
      "step": 277
    },
    {
      "epoch": 6.045883940620783,
      "grad_norm": 1.3081737756729126,
      "learning_rate": 0.00018307857731623132,
      "loss": 0.8181,
      "step": 280
    },
    {
      "epoch": 6.477732793522267,
      "grad_norm": 1.4086545705795288,
      "learning_rate": 0.0001792520797397116,
      "loss": 0.689,
      "step": 300
    },
    {
      "epoch": 6.909581646423752,
      "grad_norm": 1.4386905431747437,
      "learning_rate": 0.00017508479462818833,
      "loss": 0.768,
      "step": 320
    },
    {
      "epoch": 6.995951417004049,
      "eval_loss": 1.0414738655090332,
      "eval_runtime": 11.7025,
      "eval_samples_per_second": 31.788,
      "eval_steps_per_second": 4.016,
      "step": 324
    }
  ],
  "logging_steps": 20,
  "max_steps": 1058,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 23,
  "save_steps": 500,
  "total_flos": 2.873505652518912e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}