Hugging Face's logo

PedramR
/
ASR_Post-processing

TensorBoard
Safetensors
Model card Files
xet
 Metrics Community
PedramR commited on
Commit
6dc4140
·
verified ·
1 Parent(s): 7bdf59f

checkpoint-150

Browse files
Files changed (9) hide show
  1. verifier-qwen3.5-2b/{checkpoint-50 → checkpoint-150}/README.md +0 -0
  2. verifier-qwen3.5-2b/{checkpoint-50 → checkpoint-150}/adapter_config.json +0 -0
  3. verifier-qwen3.5-2b/{checkpoint-50 → checkpoint-150}/adapter_model.safetensors +1 -1
  4. verifier-qwen3.5-2b/{checkpoint-50 → checkpoint-150}/optimizer.pt +1 -1
  5. verifier-qwen3.5-2b/{checkpoint-50 → checkpoint-150}/rng_state.pth +1 -1
  6. verifier-qwen3.5-2b/{checkpoint-50 → checkpoint-150}/scheduler.pt +1 -1
  7. verifier-qwen3.5-2b/{checkpoint-50 → checkpoint-150}/trainer_state.json +92 -6
  8. verifier-qwen3.5-2b/{checkpoint-50 → checkpoint-150}/training_args.bin +0 -0
  9. verifier-qwen3.5-2b/tb/events.out.tfevents.1790667609.02b48645612f.2184.0 +2 -2
verifier-qwen3.5-2b/{checkpoint-50 → checkpoint-150}/README.md RENAMED
File without changes
verifier-qwen3.5-2b/{checkpoint-50 → checkpoint-150}/adapter_config.json RENAMED
File without changes
verifier-qwen3.5-2b/{checkpoint-50 → checkpoint-150}/adapter_model.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c5a8de60c30334041b4c06a0e4348358e83c1c17f2bf5aa3969113eef167c3f
3
  size 134604152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4d79dd8ee2636cc3dd1e22cfb16910b13a659d391671204d8e83a90018e3f4c
3
  size 134604152
verifier-qwen3.5-2b/{checkpoint-50 → checkpoint-150}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1af358958b0a66df2459142d236ab7d7bf5a8ea1b22568ab4a53a736569a7ad
3
  size 269426431
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9a5e893e8bf2e6053ad0d3d3d0a2311845ac9a65f32de7205b9217224f50dc5
3
  size 269426431
verifier-qwen3.5-2b/{checkpoint-50 → checkpoint-150}/rng_state.pth RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3f2571872b42e25feb7f0fbb5332a5a7efc943e925f422c988e8bdca12f7e76
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffe7ec2ad3766a57899742484073683fb6bebb00c616b1d25b54468fc22f2850
3
  size 14645
verifier-qwen3.5-2b/{checkpoint-50 → checkpoint-150}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96de79e7c394dcc9faab7e5becc5d0c9c718c03d9bfa80e97023ebf0ede0a452
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c2893be9da85da3b6ea68754d13bd2c7439b98cbf1e53b420288ad273018452
3
  size 1465
verifier-qwen3.5-2b/{checkpoint-50 → checkpoint-150}/trainer_state.json RENAMED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 50,
3
- "best_metric": 0.2319532334804535,
4
- "best_model_checkpoint": "./outputs/verifier-qwen3.5-2b/checkpoint-50",
5
- "epoch": 0.17271157167530224,
6
  "eval_steps": 50,
7
- "global_step": 50,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -51,6 +51,92 @@
51
  "eval_samples_per_second": 93.468,
52
  "eval_steps_per_second": 12.035,
53
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
54
  }
55
  ],
56
  "logging_steps": 10,
@@ -70,7 +156,7 @@
70
  "attributes": {}
71
  }
72
  },
73
- "total_flos": 1574967267514368.0,
74
  "train_batch_size": 8,
75
  "trial_name": null,
76
  "trial_params": null
 
1
  {
2
+ "best_global_step": 150,
3
+ "best_metric": 0.22001148760318756,
4
+ "best_model_checkpoint": "./outputs/verifier-qwen3.5-2b/checkpoint-150",
5
+ "epoch": 0.5181347150259067,
6
  "eval_steps": 50,
7
+ "global_step": 150,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
51
  "eval_samples_per_second": 93.468,
52
  "eval_steps_per_second": 12.035,
53
  "step": 50
54
+ },
55
+ {
56
+ "epoch": 0.20725388601036268,
57
+ "grad_norm": 2.8002288341522217,
58
+ "learning_rate": 9.455535390199638e-05,
59
+ "loss": 0.243744421005249,
60
+ "step": 60
61
+ },
62
+ {
63
+ "epoch": 0.24179620034542315,
64
+ "grad_norm": 0.9533204436302185,
65
+ "learning_rate": 9.274047186932849e-05,
66
+ "loss": 0.20114145278930665,
67
+ "step": 70
68
+ },
69
+ {
70
+ "epoch": 0.2763385146804836,
71
+ "grad_norm": 2.6727805137634277,
72
+ "learning_rate": 9.092558983666062e-05,
73
+ "loss": 0.20959975719451904,
74
+ "step": 80
75
+ },
76
+ {
77
+ "epoch": 0.31088082901554404,
78
+ "grad_norm": 1.7005524635314941,
79
+ "learning_rate": 8.911070780399275e-05,
80
+ "loss": 0.18495588302612304,
81
+ "step": 90
82
+ },
83
+ {
84
+ "epoch": 0.3454231433506045,
85
+ "grad_norm": 0.9392720460891724,
86
+ "learning_rate": 8.729582577132486e-05,
87
+ "loss": 0.20825526714324952,
88
+ "step": 100
89
+ },
90
+ {
91
+ "epoch": 0.3454231433506045,
92
+ "eval_loss": 0.2274889498949051,
93
+ "eval_runtime": 1.9564,
94
+ "eval_samples_per_second": 119.096,
95
+ "eval_steps_per_second": 15.334,
96
+ "step": 100
97
+ },
98
+ {
99
+ "epoch": 0.3799654576856649,
100
+ "grad_norm": 1.6563022136688232,
101
+ "learning_rate": 8.5480943738657e-05,
102
+ "loss": 0.2126215696334839,
103
+ "step": 110
104
+ },
105
+ {
106
+ "epoch": 0.41450777202072536,
107
+ "grad_norm": 1.256416916847229,
108
+ "learning_rate": 8.366606170598912e-05,
109
+ "loss": 0.1954953193664551,
110
+ "step": 120
111
+ },
112
+ {
113
+ "epoch": 0.44905008635578586,
114
+ "grad_norm": 1.5402225255966187,
115
+ "learning_rate": 8.185117967332124e-05,
116
+ "loss": 0.18174756765365602,
117
+ "step": 130
118
+ },
119
+ {
120
+ "epoch": 0.4835924006908463,
121
+ "grad_norm": 1.518054723739624,
122
+ "learning_rate": 8.003629764065335e-05,
123
+ "loss": 0.1569438695907593,
124
+ "step": 140
125
+ },
126
+ {
127
+ "epoch": 0.5181347150259067,
128
+ "grad_norm": 1.6671258211135864,
129
+ "learning_rate": 7.822141560798548e-05,
130
+ "loss": 0.19996687173843383,
131
+ "step": 150
132
+ },
133
+ {
134
+ "epoch": 0.5181347150259067,
135
+ "eval_loss": 0.22001148760318756,
136
+ "eval_runtime": 1.9657,
137
+ "eval_samples_per_second": 118.534,
138
+ "eval_steps_per_second": 15.262,
139
+ "step": 150
140
  }
141
  ],
142
  "logging_steps": 10,
 
156
  "attributes": {}
157
  }
158
  },
159
+ "total_flos": 4732870507524096.0,
160
  "train_batch_size": 8,
161
  "trial_name": null,
162
  "trial_params": null
verifier-qwen3.5-2b/{checkpoint-50 → checkpoint-150}/training_args.bin RENAMED
File without changes
verifier-qwen3.5-2b/tb/events.out.tfevents.1790667609.02b48645612f.2184.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7bc0c836710de04ffd4ed93a1d8fad183d4d256050b54e23a9ab91790f58abec
3
- size 8035
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b07a76a9793f1fa59fbaf62500ac8628582631ee8d915790a0901da4e2e953b
3
+ size 9353