Hugging Face's logo

PedramR
/
ASR_Post-processing

TensorBoard
Safetensors
Model card Files
xet
 Metrics Community
PedramR commited on
Commit
e09aef1
·
verified ·
1 Parent(s): 3132c13

checkpoint-150

Browse files
Files changed (9) hide show
  1. verifier-qwen3.5-2b-v2/{checkpoint-50 → checkpoint-150}/README.md +0 -0
  2. verifier-qwen3.5-2b-v2/{checkpoint-50 → checkpoint-150}/adapter_config.json +0 -0
  3. verifier-qwen3.5-2b-v2/{checkpoint-50 → checkpoint-150}/adapter_model.safetensors +1 -1
  4. verifier-qwen3.5-2b-v2/{checkpoint-50 → checkpoint-150}/optimizer.pt +1 -1
  5. verifier-qwen3.5-2b-v2/{checkpoint-50 → checkpoint-150}/rng_state.pth +1 -1
  6. verifier-qwen3.5-2b-v2/{checkpoint-50 → checkpoint-150}/scheduler.pt +1 -1
  7. verifier-qwen3.5-2b-v2/{checkpoint-50 → checkpoint-150}/trainer_state.json +92 -6
  8. verifier-qwen3.5-2b-v2/{checkpoint-50 → checkpoint-150}/training_args.bin +0 -0
  9. verifier-qwen3.5-2b-v2/tb/events.out.tfevents.1790685928.073545c29144.1706.0 +2 -2
verifier-qwen3.5-2b-v2/{checkpoint-50 → checkpoint-150}/README.md RENAMED
File without changes
verifier-qwen3.5-2b-v2/{checkpoint-50 → checkpoint-150}/adapter_config.json RENAMED
File without changes
verifier-qwen3.5-2b-v2/{checkpoint-50 → checkpoint-150}/adapter_model.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1fb2633bfdd35500989f341c8945b98497adc6e807e1a3b418862786d7ace937
3
  size 134604152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5119d4731772c5145fad91b568e905541e8ed9df099fecbac4785ad6da3c39b3
3
  size 134604152
verifier-qwen3.5-2b-v2/{checkpoint-50 → checkpoint-150}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cbc7e600e906b538eeda80ccd9ab225fef84777cb5904165466f89e3c1ac2679
3
  size 269426431
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:368c452a48fb05f910ea28c0d41ec2523b077e8b814887b52f3225a2f57a0730
3
  size 269426431
verifier-qwen3.5-2b-v2/{checkpoint-50 → checkpoint-150}/rng_state.pth RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cbcc33de497823cb56b26f8ddb9c9aeaef21e68e5e67bdd8837695c7fe6ae759
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0d62c02f66851c8e8ce8922a9abf2545edcbb8b375903ed73ed89debf4523f6
3
  size 14645
verifier-qwen3.5-2b-v2/{checkpoint-50 → checkpoint-150}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b53d6a79a3b2ccf345bb64325ffaaaece122640cb1d0cc1b3fe7a89c134743f
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3d68fe671ba2b0900dd318a2837b2853470dd977e64be3690ff3f413c9aa1d7
3
  size 1465
verifier-qwen3.5-2b-v2/{checkpoint-50 → checkpoint-150}/trainer_state.json RENAMED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 50,
3
- "best_metric": 0.22349943220615387,
4
- "best_model_checkpoint": "./outputs/verifier-qwen3.5-2b-v2/checkpoint-50",
5
- "epoch": 0.18281535648994515,
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": 91.125,
52
  "eval_steps_per_second": 11.758,
53
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
54
  }
55
  ],
56
  "logging_steps": 10,
@@ -70,7 +156,7 @@
70
  "attributes": {}
71
  }
72
  },
73
- "total_flos": 1579154214199296.0,
74
  "train_batch_size": 8,
75
  "trial_name": null,
76
  "trial_params": null
 
1
  {
2
+ "best_global_step": 150,
3
+ "best_metric": 0.19720077514648438,
4
+ "best_model_checkpoint": "./outputs/verifier-qwen3.5-2b-v2/checkpoint-150",
5
+ "epoch": 0.5484460694698354,
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": 91.125,
52
  "eval_steps_per_second": 11.758,
53
  "step": 50
54
+ },
55
+ {
56
+ "epoch": 0.21937842778793418,
57
+ "grad_norm": 1.2185064554214478,
58
+ "learning_rate": 9.403846153846154e-05,
59
+ "loss": 0.21965584754943848,
60
+ "step": 60
61
+ },
62
+ {
63
+ "epoch": 0.25594149908592323,
64
+ "grad_norm": 3.009625196456909,
65
+ "learning_rate": 9.211538461538462e-05,
66
+ "loss": 0.20802013874053954,
67
+ "step": 70
68
+ },
69
+ {
70
+ "epoch": 0.29250457038391225,
71
+ "grad_norm": 0.9929115772247314,
72
+ "learning_rate": 9.01923076923077e-05,
73
+ "loss": 0.20940332412719725,
74
+ "step": 80
75
+ },
76
+ {
77
+ "epoch": 0.3290676416819013,
78
+ "grad_norm": 1.6556148529052734,
79
+ "learning_rate": 8.826923076923077e-05,
80
+ "loss": 0.17260411977767945,
81
+ "step": 90
82
+ },
83
+ {
84
+ "epoch": 0.3656307129798903,
85
+ "grad_norm": 1.6006988286972046,
86
+ "learning_rate": 8.634615384615385e-05,
87
+ "loss": 0.20330517292022704,
88
+ "step": 100
89
+ },
90
+ {
91
+ "epoch": 0.3656307129798903,
92
+ "eval_loss": 0.20814214646816254,
93
+ "eval_runtime": 2.3801,
94
+ "eval_samples_per_second": 91.174,
95
+ "eval_steps_per_second": 11.764,
96
+ "step": 100
97
+ },
98
+ {
99
+ "epoch": 0.40219378427787933,
100
+ "grad_norm": 3.3533239364624023,
101
+ "learning_rate": 8.442307692307693e-05,
102
+ "loss": 0.1813126564025879,
103
+ "step": 110
104
+ },
105
+ {
106
+ "epoch": 0.43875685557586835,
107
+ "grad_norm": 1.6487245559692383,
108
+ "learning_rate": 8.25e-05,
109
+ "loss": 0.20677659511566163,
110
+ "step": 120
111
+ },
112
+ {
113
+ "epoch": 0.4753199268738574,
114
+ "grad_norm": 2.074784755706787,
115
+ "learning_rate": 8.057692307692308e-05,
116
+ "loss": 0.20372426509857178,
117
+ "step": 130
118
+ },
119
+ {
120
+ "epoch": 0.5118829981718465,
121
+ "grad_norm": 2.7923927307128906,
122
+ "learning_rate": 7.865384615384616e-05,
123
+ "loss": 0.18218755722045898,
124
+ "step": 140
125
+ },
126
+ {
127
+ "epoch": 0.5484460694698354,
128
+ "grad_norm": 1.6166132688522339,
129
+ "learning_rate": 7.673076923076924e-05,
130
+ "loss": 0.217415714263916,
131
+ "step": 150
132
+ },
133
+ {
134
+ "epoch": 0.5484460694698354,
135
+ "eval_loss": 0.19720077514648438,
136
+ "eval_runtime": 2.3834,
137
+ "eval_samples_per_second": 91.046,
138
+ "eval_steps_per_second": 11.748,
139
+ "step": 150
140
  }
141
  ],
142
  "logging_steps": 10,
 
156
  "attributes": {}
157
  }
158
  },
159
+ "total_flos": 4740028835727360.0,
160
  "train_batch_size": 8,
161
  "trial_name": null,
162
  "trial_params": null
verifier-qwen3.5-2b-v2/{checkpoint-50 → checkpoint-150}/training_args.bin RENAMED
File without changes
verifier-qwen3.5-2b-v2/tb/events.out.tfevents.1790685928.073545c29144.1706.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4d01afb922f9ed3608d639aaacc020dd367f9ebb30bfc4de407806c6d18c47d
3
- size 8038
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b255f51f1b42be939e9ca659a3c51c47953fe9b5f99090894efabe26feda02ce
3
+ size 9356