Hugging Face's logo

C3DS
/
FLICC-Qwen3.5-9B-lora

Transformers
TensorBoard
Safetensors
Generated from Trainer
trl
hf_jobs
unsloth
sft
Model card Files
xet
 Metrics Community
iRanadheer commited on
Commit
0c066b6
·
verified ·
1 Parent(s): f55498d

Training in progress, step 100, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +92 -6
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1eb83c42a71ea0768bd1ab2f790b93c316eafec78f3f1752dc2cfd0cd124227e
3
  size 116429720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:358921780d53bd6ab64ec09f9b5b0d79103254eaa31ec0c77007e31e1167a5f0
3
  size 116429720
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97bfa1c11f8fa6583b590cc2bd084cfb7403ea795c02435f83051fd38376db6e
3
  size 59409573
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14bcea3fa26234a894ce0def623acd8e7c8fc3b31c07dd426b9a8a632aec3aae
3
  size 59409573
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4a9f217e852f439efa6bd32fde98d6867f11aa6ea13ddc021ba10af6a0b0934
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:718a0f3db00824213036a2c0441849791319b7d9cf189065873bb26a7020738e
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24f5a01d62553c37420cb3daa4598292ce83112b1eea45605c28c7363351a801
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa002d9d96e9a67a280e7be9eaaf255b9bf188a72a8f12282f892c6c17e361a0
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 50,
3
- "best_metric": 0.16927684843540192,
4
- "best_model_checkpoint": "FLICC-Qwen3.5-9B/checkpoint-50",
5
- "epoch": 0.24783147459727387,
6
  "eval_steps": 25,
7
- "global_step": 50,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -94,6 +94,92 @@
94
  "eval_samples_per_second": 8.814,
95
  "eval_steps_per_second": 2.241,
96
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
97
  }
98
  ],
99
  "logging_steps": 5,
@@ -113,7 +199,7 @@
113
  "attributes": {}
114
  }
115
  },
116
- "total_flos": 3.42513803207088e+16,
117
  "train_batch_size": 1,
118
  "trial_name": null,
119
  "trial_params": null
 
1
  {
2
+ "best_global_step": 100,
3
+ "best_metric": 0.15668612718582153,
4
+ "best_model_checkpoint": "FLICC-Qwen3.5-9B/checkpoint-100",
5
+ "epoch": 0.49566294919454773,
6
  "eval_steps": 25,
7
+ "global_step": 100,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
94
  "eval_samples_per_second": 8.814,
95
  "eval_steps_per_second": 2.241,
96
  "step": 50
97
+ },
98
+ {
99
+ "epoch": 0.27261462205700127,
100
+ "grad_norm": 0.08669876307249069,
101
+ "learning_rate": 0.00019732246636369605,
102
+ "loss": 0.15882112979888915,
103
+ "step": 55
104
+ },
105
+ {
106
+ "epoch": 0.29739776951672864,
107
+ "grad_norm": 0.08936048299074173,
108
+ "learning_rate": 0.00019668293727277846,
109
+ "loss": 0.17748851776123048,
110
+ "step": 60
111
+ },
112
+ {
113
+ "epoch": 0.322180916976456,
114
+ "grad_norm": 0.08769766986370087,
115
+ "learning_rate": 0.0001959762541749086,
116
+ "loss": 0.15775216817855836,
117
+ "step": 65
118
+ },
119
+ {
120
+ "epoch": 0.3469640644361834,
121
+ "grad_norm": 0.08859147131443024,
122
+ "learning_rate": 0.0001952029079178307,
123
+ "loss": 0.1502579927444458,
124
+ "step": 70
125
+ },
126
+ {
127
+ "epoch": 0.37174721189591076,
128
+ "grad_norm": 0.08570419251918793,
129
+ "learning_rate": 0.00019436343565216711,
130
+ "loss": 0.1632941722869873,
131
+ "step": 75
132
+ },
133
+ {
134
+ "epoch": 0.37174721189591076,
135
+ "eval_loss": 0.16099171340465546,
136
+ "eval_runtime": 20.0803,
137
+ "eval_samples_per_second": 8.815,
138
+ "eval_steps_per_second": 2.241,
139
+ "step": 75
140
+ },
141
+ {
142
+ "epoch": 0.3965303593556382,
143
+ "grad_norm": 0.08874429017305374,
144
+ "learning_rate": 0.00019345842045832428,
145
+ "loss": 0.16088367700576783,
146
+ "step": 80
147
+ },
148
+ {
149
+ "epoch": 0.42131350681536556,
150
+ "grad_norm": 0.08653293550014496,
151
+ "learning_rate": 0.000192488490941497,
152
+ "loss": 0.17103042602539062,
153
+ "step": 85
154
+ },
155
+ {
156
+ "epoch": 0.44609665427509293,
157
+ "grad_norm": 0.08580342680215836,
158
+ "learning_rate": 0.00019145432079505206,
159
+ "loss": 0.16303534507751466,
160
+ "step": 90
161
+ },
162
+ {
163
+ "epoch": 0.4708798017348203,
164
+ "grad_norm": 0.0754188671708107,
165
+ "learning_rate": 0.00019035662833259432,
166
+ "loss": 0.15218052864074708,
167
+ "step": 95
168
+ },
169
+ {
170
+ "epoch": 0.49566294919454773,
171
+ "grad_norm": 0.08795224130153656,
172
+ "learning_rate": 0.0001891961759890408,
173
+ "loss": 0.1582047462463379,
174
+ "step": 100
175
+ },
176
+ {
177
+ "epoch": 0.49566294919454773,
178
+ "eval_loss": 0.15668612718582153,
179
+ "eval_runtime": 20.0959,
180
+ "eval_samples_per_second": 8.808,
181
+ "eval_steps_per_second": 2.239,
182
+ "step": 100
183
  }
184
  ],
185
  "logging_steps": 5,
 
199
  "attributes": {}
200
  }
201
  },
202
+ "total_flos": 6.84180977816448e+16,
203
  "train_batch_size": 1,
204
  "trial_name": null,
205
  "trial_params": null