Hugging Face's logo

RandomDud123456
/
Mini-Project_Models

TensorBoard
Safetensors
Model card Files
xet
Metrics Community
RandomDud123456 commited on
Commit
9f0f9bb
·
verified ·
1 Parent(s): 5c8137f

Upload 72 files

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. qwen3-150m-finetune-logs/events.out.tfevents.1757825786.Sai-Legion.23372.4 +3 -0
  2. qwen3-150m-finetuned-antonyms/checkpoint-1000/config.json +45 -0
  3. qwen3-150m-finetuned-antonyms/checkpoint-1000/generation_config.json +7 -0
  4. qwen3-150m-finetuned-antonyms/checkpoint-1000/model.safetensors +3 -0
  5. qwen3-150m-finetuned-antonyms/checkpoint-1000/optimizer.pt +3 -0
  6. qwen3-150m-finetuned-antonyms/checkpoint-1000/rng_state.pth +3 -0
  7. qwen3-150m-finetuned-antonyms/checkpoint-1000/scheduler.pt +3 -0
  8. qwen3-150m-finetuned-antonyms/checkpoint-1000/special_tokens_map.json +24 -0
  9. qwen3-150m-finetuned-antonyms/checkpoint-1000/tokenizer.json +0 -0
  10. qwen3-150m-finetuned-antonyms/checkpoint-1000/tokenizer_config.json +76 -0
  11. qwen3-150m-finetuned-antonyms/checkpoint-1000/trainer_state.json +424 -0
  12. qwen3-150m-finetuned-antonyms/checkpoint-1000/training_args.bin +3 -0
  13. qwen3-150m-finetuned-antonyms/checkpoint-1200/config.json +45 -0
  14. qwen3-150m-finetuned-antonyms/checkpoint-1200/generation_config.json +7 -0
  15. qwen3-150m-finetuned-antonyms/checkpoint-1200/model.safetensors +3 -0
  16. qwen3-150m-finetuned-antonyms/checkpoint-1200/optimizer.pt +3 -0
  17. qwen3-150m-finetuned-antonyms/checkpoint-1200/rng_state.pth +3 -0
  18. qwen3-150m-finetuned-antonyms/checkpoint-1200/scheduler.pt +3 -0
  19. qwen3-150m-finetuned-antonyms/checkpoint-1200/special_tokens_map.json +24 -0
  20. qwen3-150m-finetuned-antonyms/checkpoint-1200/tokenizer.json +0 -0
  21. qwen3-150m-finetuned-antonyms/checkpoint-1200/tokenizer_config.json +76 -0
  22. qwen3-150m-finetuned-antonyms/checkpoint-1200/trainer_state.json +502 -0
  23. qwen3-150m-finetuned-antonyms/checkpoint-1200/training_args.bin +3 -0
  24. qwen3-150m-finetuned-antonyms/checkpoint-1400/config.json +45 -0
  25. qwen3-150m-finetuned-antonyms/checkpoint-1400/generation_config.json +7 -0
  26. qwen3-150m-finetuned-antonyms/checkpoint-1400/model.safetensors +3 -0
  27. qwen3-150m-finetuned-antonyms/checkpoint-1400/optimizer.pt +3 -0
  28. qwen3-150m-finetuned-antonyms/checkpoint-1400/rng_state.pth +3 -0
  29. qwen3-150m-finetuned-antonyms/checkpoint-1400/scheduler.pt +3 -0
  30. qwen3-150m-finetuned-antonyms/checkpoint-1400/special_tokens_map.json +24 -0
  31. qwen3-150m-finetuned-antonyms/checkpoint-1400/tokenizer.json +0 -0
  32. qwen3-150m-finetuned-antonyms/checkpoint-1400/tokenizer_config.json +76 -0
  33. qwen3-150m-finetuned-antonyms/checkpoint-1400/trainer_state.json +580 -0
  34. qwen3-150m-finetuned-antonyms/checkpoint-1400/training_args.bin +3 -0
  35. qwen3-150m-finetuned-coherence/config.json +45 -0
  36. qwen3-150m-finetuned-coherence/generation_config.json +7 -0
  37. qwen3-150m-finetuned-coherence/model.safetensors +3 -0
  38. qwen3-150m-finetuned-coherence/special_tokens_map.json +24 -0
  39. qwen3-150m-finetuned-coherence/tokenizer.json +0 -0
  40. qwen3-150m-finetuned-coherence/tokenizer_config.json +76 -0
  41. qwen3-150m-finetuned-coherence/training_args.bin +3 -0
  42. qwen3-150m-lora-finetune-logs-antonyms/events.out.tfevents.1757877473.Sai-Legion.21500.15 +3 -0
  43. qwen3-150m-lora-finetuned-antonyms/checkpoint-4200/README.md +207 -0
  44. qwen3-150m-lora-finetuned-antonyms/checkpoint-4200/adapter_config.json +39 -0
  45. qwen3-150m-lora-finetuned-antonyms/checkpoint-4200/adapter_model.safetensors +3 -0
  46. qwen3-150m-lora-finetuned-antonyms/checkpoint-4200/optimizer.pt +3 -0
  47. qwen3-150m-lora-finetuned-antonyms/checkpoint-4200/rng_state.pth +3 -0
  48. qwen3-150m-lora-finetuned-antonyms/checkpoint-4200/scheduler.pt +3 -0
  49. qwen3-150m-lora-finetuned-antonyms/checkpoint-4200/special_tokens_map.json +24 -0
  50. qwen3-150m-lora-finetuned-antonyms/checkpoint-4200/tokenizer.json +0 -0
qwen3-150m-finetune-logs/events.out.tfevents.1757825786.Sai-Legion.23372.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17c2da34e7fcca34282735662f25ab98eab9587bcf9cec53c6a2ca473dde8dbf
3
+ size 44381
qwen3-150m-finetuned-antonyms/checkpoint-1000/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 2,
8
+ "eos_token_id": 3,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 2048,
14
+ "layer_types": [
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention"
27
+ ],
28
+ "max_position_embeddings": 2048,
29
+ "max_window_layers": 28,
30
+ "model_type": "qwen3",
31
+ "num_attention_heads": 12,
32
+ "num_hidden_layers": 12,
33
+ "num_key_value_heads": 12,
34
+ "pad_token_id": 1,
35
+ "rms_norm_eps": 1e-06,
36
+ "rope_scaling": null,
37
+ "rope_theta": 10000.0,
38
+ "sliding_window": null,
39
+ "tie_word_embeddings": true,
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.55.4",
42
+ "use_cache": true,
43
+ "use_sliding_window": false,
44
+ "vocab_size": 32000
45
+ }
qwen3-150m-finetuned-antonyms/checkpoint-1000/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 3,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.55.4"
7
+ }
qwen3-150m-finetuned-antonyms/checkpoint-1000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e427f84536a0cc6a0138bf2129d07bb7ce4d86b48eae5a1c4005056506b39dcc
3
+ size 551392792
qwen3-150m-finetuned-antonyms/checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12480a7712df43d80074f2cc7081ecd245b51f88de2fe78e0f58397fba7a9211
3
+ size 1102868538
qwen3-150m-finetuned-antonyms/checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:243a37024beb77e9c86d6c9c8f32f88f819d9b15ad1ea65bedb28457eb282f6b
3
+ size 14244
qwen3-150m-finetuned-antonyms/checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f259016cc597506614b5add626e56ef8e5eae5bbc08029745d96bfec83663291
3
+ size 1064
qwen3-150m-finetuned-antonyms/checkpoint-1000/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<pad>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
qwen3-150m-finetuned-antonyms/checkpoint-1000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
qwen3-150m-finetuned-antonyms/checkpoint-1000/tokenizer_config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<en>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<te>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "<mai>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "<mask>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ }
67
+ },
68
+ "bos_token": "<s>",
69
+ "clean_up_tokenization_spaces": false,
70
+ "eos_token": "</s>",
71
+ "extra_special_tokens": {},
72
+ "model_max_length": 1000000000000000019884624838656,
73
+ "pad_token": "<pad>",
74
+ "tokenizer_class": "PreTrainedTokenizerFast",
75
+ "unk_token": "<unk>"
76
+ }
qwen3-150m-finetuned-antonyms/checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,424 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1000,
3
+ "best_metric": 0.23861029744148254,
4
+ "best_model_checkpoint": "./qwen3-150m-finetuned-antonyms\\checkpoint-1000",
5
+ "epoch": 0.6736842105263158,
6
+ "eval_steps": 200,
7
+ "global_step": 1000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.013473684210526317,
14
+ "grad_norm": 2.7961366176605225,
15
+ "learning_rate": 2.5503355704697992e-06,
16
+ "loss": 2.917,
17
+ "step": 20
18
+ },
19
+ {
20
+ "epoch": 0.026947368421052633,
21
+ "grad_norm": 2.30360746383667,
22
+ "learning_rate": 5.234899328859061e-06,
23
+ "loss": 2.3528,
24
+ "step": 40
25
+ },
26
+ {
27
+ "epoch": 0.04042105263157895,
28
+ "grad_norm": 1.5964854955673218,
29
+ "learning_rate": 7.919463087248322e-06,
30
+ "loss": 1.8678,
31
+ "step": 60
32
+ },
33
+ {
34
+ "epoch": 0.053894736842105266,
35
+ "grad_norm": 1.4178063869476318,
36
+ "learning_rate": 1.0604026845637586e-05,
37
+ "loss": 1.7207,
38
+ "step": 80
39
+ },
40
+ {
41
+ "epoch": 0.06736842105263158,
42
+ "grad_norm": 1.6399588584899902,
43
+ "learning_rate": 1.3288590604026848e-05,
44
+ "loss": 1.5277,
45
+ "step": 100
46
+ },
47
+ {
48
+ "epoch": 0.0808421052631579,
49
+ "grad_norm": 1.6011607646942139,
50
+ "learning_rate": 1.5973154362416107e-05,
51
+ "loss": 1.4006,
52
+ "step": 120
53
+ },
54
+ {
55
+ "epoch": 0.09431578947368421,
56
+ "grad_norm": 1.3836917877197266,
57
+ "learning_rate": 1.865771812080537e-05,
58
+ "loss": 1.342,
59
+ "step": 140
60
+ },
61
+ {
62
+ "epoch": 0.10778947368421053,
63
+ "grad_norm": 1.8060948848724365,
64
+ "learning_rate": 1.9999379903772885e-05,
65
+ "loss": 1.2442,
66
+ "step": 160
67
+ },
68
+ {
69
+ "epoch": 0.12126315789473684,
70
+ "grad_norm": 1.4634225368499756,
71
+ "learning_rate": 1.999441959536959e-05,
72
+ "loss": 1.1505,
73
+ "step": 180
74
+ },
75
+ {
76
+ "epoch": 0.13473684210526315,
77
+ "grad_norm": 1.609693169593811,
78
+ "learning_rate": 1.9984501439181532e-05,
79
+ "loss": 1.0635,
80
+ "step": 200
81
+ },
82
+ {
83
+ "epoch": 0.13473684210526315,
84
+ "eval_loss": 1.1043256521224976,
85
+ "eval_runtime": 88.2411,
86
+ "eval_samples_per_second": 28.331,
87
+ "eval_steps_per_second": 14.166,
88
+ "step": 200
89
+ },
90
+ {
91
+ "epoch": 0.1482105263157895,
92
+ "grad_norm": 1.3189349174499512,
93
+ "learning_rate": 1.996963035522515e-05,
94
+ "loss": 0.9328,
95
+ "step": 220
96
+ },
97
+ {
98
+ "epoch": 0.1616842105263158,
99
+ "grad_norm": 1.6366477012634277,
100
+ "learning_rate": 1.9949813720474152e-05,
101
+ "loss": 0.8752,
102
+ "step": 240
103
+ },
104
+ {
105
+ "epoch": 0.1751578947368421,
106
+ "grad_norm": 1.3156894445419312,
107
+ "learning_rate": 1.9925061365200102e-05,
108
+ "loss": 0.811,
109
+ "step": 260
110
+ },
111
+ {
112
+ "epoch": 0.18863157894736843,
113
+ "grad_norm": 1.4519543647766113,
114
+ "learning_rate": 1.989538556809598e-05,
115
+ "loss": 0.7621,
116
+ "step": 280
117
+ },
118
+ {
119
+ "epoch": 0.20210526315789473,
120
+ "grad_norm": 1.3389956951141357,
121
+ "learning_rate": 1.986080105018521e-05,
122
+ "loss": 0.7399,
123
+ "step": 300
124
+ },
125
+ {
126
+ "epoch": 0.21557894736842106,
127
+ "grad_norm": 1.240100622177124,
128
+ "learning_rate": 1.9821324967519113e-05,
129
+ "loss": 0.6431,
130
+ "step": 320
131
+ },
132
+ {
133
+ "epoch": 0.22905263157894737,
134
+ "grad_norm": 1.7040982246398926,
135
+ "learning_rate": 1.9776976902666452e-05,
136
+ "loss": 0.5932,
137
+ "step": 340
138
+ },
139
+ {
140
+ "epoch": 0.24252631578947367,
141
+ "grad_norm": 1.1405657529830933,
142
+ "learning_rate": 1.9727778854999283e-05,
143
+ "loss": 0.5804,
144
+ "step": 360
145
+ },
146
+ {
147
+ "epoch": 0.256,
148
+ "grad_norm": 1.4422856569290161,
149
+ "learning_rate": 1.9673755229779884e-05,
150
+ "loss": 0.5823,
151
+ "step": 380
152
+ },
153
+ {
154
+ "epoch": 0.2694736842105263,
155
+ "grad_norm": 1.2760127782821655,
156
+ "learning_rate": 1.9614932826054274e-05,
157
+ "loss": 0.5321,
158
+ "step": 400
159
+ },
160
+ {
161
+ "epoch": 0.2694736842105263,
162
+ "eval_loss": 0.5738449096679688,
163
+ "eval_runtime": 64.7646,
164
+ "eval_samples_per_second": 38.601,
165
+ "eval_steps_per_second": 19.301,
166
+ "step": 400
167
+ },
168
+ {
169
+ "epoch": 0.2829473684210526,
170
+ "grad_norm": 1.2698249816894531,
171
+ "learning_rate": 1.9551340823358217e-05,
172
+ "loss": 0.5178,
173
+ "step": 420
174
+ },
175
+ {
176
+ "epoch": 0.296421052631579,
177
+ "grad_norm": 1.0051153898239136,
178
+ "learning_rate": 1.948301076724237e-05,
179
+ "loss": 0.5021,
180
+ "step": 440
181
+ },
182
+ {
183
+ "epoch": 0.3098947368421053,
184
+ "grad_norm": 1.0702327489852905,
185
+ "learning_rate": 1.9409976553623767e-05,
186
+ "loss": 0.4409,
187
+ "step": 460
188
+ },
189
+ {
190
+ "epoch": 0.3233684210526316,
191
+ "grad_norm": 1.2159368991851807,
192
+ "learning_rate": 1.9332274411971333e-05,
193
+ "loss": 0.4028,
194
+ "step": 480
195
+ },
196
+ {
197
+ "epoch": 0.3368421052631579,
198
+ "grad_norm": 1.3318655490875244,
199
+ "learning_rate": 1.924994288733386e-05,
200
+ "loss": 0.4199,
201
+ "step": 500
202
+ },
203
+ {
204
+ "epoch": 0.3503157894736842,
205
+ "grad_norm": 1.4047660827636719,
206
+ "learning_rate": 1.9163022821219252e-05,
207
+ "loss": 0.3865,
208
+ "step": 520
209
+ },
210
+ {
211
+ "epoch": 0.36378947368421055,
212
+ "grad_norm": 1.0359469652175903,
213
+ "learning_rate": 1.907155733133467e-05,
214
+ "loss": 0.3779,
215
+ "step": 540
216
+ },
217
+ {
218
+ "epoch": 0.37726315789473686,
219
+ "grad_norm": 1.1933883428573608,
220
+ "learning_rate": 1.897559179019745e-05,
221
+ "loss": 0.358,
222
+ "step": 560
223
+ },
224
+ {
225
+ "epoch": 0.39073684210526316,
226
+ "grad_norm": 1.1323217153549194,
227
+ "learning_rate": 1.8875173802627565e-05,
228
+ "loss": 0.3715,
229
+ "step": 580
230
+ },
231
+ {
232
+ "epoch": 0.40421052631578946,
233
+ "grad_norm": 1.0181940793991089,
234
+ "learning_rate": 1.8770353182132684e-05,
235
+ "loss": 0.3428,
236
+ "step": 600
237
+ },
238
+ {
239
+ "epoch": 0.40421052631578946,
240
+ "eval_loss": 0.37542256712913513,
241
+ "eval_runtime": 89.5428,
242
+ "eval_samples_per_second": 27.92,
243
+ "eval_steps_per_second": 13.96,
244
+ "step": 600
245
+ },
246
+ {
247
+ "epoch": 0.41768421052631577,
248
+ "grad_norm": 1.0640043020248413,
249
+ "learning_rate": 1.8661181926197627e-05,
250
+ "loss": 0.3183,
251
+ "step": 620
252
+ },
253
+ {
254
+ "epoch": 0.43115789473684213,
255
+ "grad_norm": 0.9247826933860779,
256
+ "learning_rate": 1.8547714190490385e-05,
257
+ "loss": 0.3054,
258
+ "step": 640
259
+ },
260
+ {
261
+ "epoch": 0.44463157894736843,
262
+ "grad_norm": 1.059590458869934,
263
+ "learning_rate": 1.8430006261997585e-05,
264
+ "loss": 0.3088,
265
+ "step": 660
266
+ },
267
+ {
268
+ "epoch": 0.45810526315789474,
269
+ "grad_norm": 1.1035728454589844,
270
+ "learning_rate": 1.8308116531102674e-05,
271
+ "loss": 0.3163,
272
+ "step": 680
273
+ },
274
+ {
275
+ "epoch": 0.47157894736842104,
276
+ "grad_norm": 1.2538524866104126,
277
+ "learning_rate": 1.81821054626207e-05,
278
+ "loss": 0.2959,
279
+ "step": 700
280
+ },
281
+ {
282
+ "epoch": 0.48505263157894735,
283
+ "grad_norm": 1.0344308614730835,
284
+ "learning_rate": 1.8052035565804024e-05,
285
+ "loss": 0.2746,
286
+ "step": 720
287
+ },
288
+ {
289
+ "epoch": 0.4985263157894737,
290
+ "grad_norm": 1.0735608339309692,
291
+ "learning_rate": 1.7917971363333896e-05,
292
+ "loss": 0.2804,
293
+ "step": 740
294
+ },
295
+ {
296
+ "epoch": 0.512,
297
+ "grad_norm": 0.9861028790473938,
298
+ "learning_rate": 1.777997935931322e-05,
299
+ "loss": 0.266,
300
+ "step": 760
301
+ },
302
+ {
303
+ "epoch": 0.5254736842105263,
304
+ "grad_norm": 1.2618284225463867,
305
+ "learning_rate": 1.7638128006276422e-05,
306
+ "loss": 0.267,
307
+ "step": 780
308
+ },
309
+ {
310
+ "epoch": 0.5389473684210526,
311
+ "grad_norm": 0.7712630033493042,
312
+ "learning_rate": 1.7492487671232784e-05,
313
+ "loss": 0.245,
314
+ "step": 800
315
+ },
316
+ {
317
+ "epoch": 0.5389473684210526,
318
+ "eval_loss": 0.2860563099384308,
319
+ "eval_runtime": 168.0857,
320
+ "eval_samples_per_second": 14.873,
321
+ "eval_steps_per_second": 7.437,
322
+ "step": 800
323
+ },
324
+ {
325
+ "epoch": 0.5524210526315789,
326
+ "grad_norm": 1.0299738645553589,
327
+ "learning_rate": 1.7343130600760068e-05,
328
+ "loss": 0.246,
329
+ "step": 820
330
+ },
331
+ {
332
+ "epoch": 0.5658947368421052,
333
+ "grad_norm": 1.2506853342056274,
334
+ "learning_rate": 1.719013088516576e-05,
335
+ "loss": 0.237,
336
+ "step": 840
337
+ },
338
+ {
339
+ "epoch": 0.5793684210526315,
340
+ "grad_norm": 0.7798528671264648,
341
+ "learning_rate": 1.7033564421733717e-05,
342
+ "loss": 0.2329,
343
+ "step": 860
344
+ },
345
+ {
346
+ "epoch": 0.592842105263158,
347
+ "grad_norm": 1.0132075548171997,
348
+ "learning_rate": 1.6873508877074443e-05,
349
+ "loss": 0.2437,
350
+ "step": 880
351
+ },
352
+ {
353
+ "epoch": 0.6063157894736843,
354
+ "grad_norm": 0.9196950197219849,
355
+ "learning_rate": 1.6710043648597656e-05,
356
+ "loss": 0.2409,
357
+ "step": 900
358
+ },
359
+ {
360
+ "epoch": 0.6197894736842106,
361
+ "grad_norm": 0.8007433414459229,
362
+ "learning_rate": 1.6543249825126285e-05,
363
+ "loss": 0.2188,
364
+ "step": 920
365
+ },
366
+ {
367
+ "epoch": 0.6332631578947369,
368
+ "grad_norm": 0.7954726219177246,
369
+ "learning_rate": 1.6373210146671437e-05,
370
+ "loss": 0.2076,
371
+ "step": 940
372
+ },
373
+ {
374
+ "epoch": 0.6467368421052632,
375
+ "grad_norm": 0.7610670924186707,
376
+ "learning_rate": 1.6200008963388216e-05,
377
+ "loss": 0.2153,
378
+ "step": 960
379
+ },
380
+ {
381
+ "epoch": 0.6602105263157895,
382
+ "grad_norm": 0.7918910980224609,
383
+ "learning_rate": 1.6023732193732886e-05,
384
+ "loss": 0.205,
385
+ "step": 980
386
+ },
387
+ {
388
+ "epoch": 0.6736842105263158,
389
+ "grad_norm": 0.8178799152374268,
390
+ "learning_rate": 1.5844467281842007e-05,
391
+ "loss": 0.1922,
392
+ "step": 1000
393
+ },
394
+ {
395
+ "epoch": 0.6736842105263158,
396
+ "eval_loss": 0.23861029744148254,
397
+ "eval_runtime": 171.498,
398
+ "eval_samples_per_second": 14.577,
399
+ "eval_steps_per_second": 7.289,
400
+ "step": 1000
401
+ }
402
+ ],
403
+ "logging_steps": 20,
404
+ "max_steps": 2970,
405
+ "num_input_tokens_seen": 0,
406
+ "num_train_epochs": 2,
407
+ "save_steps": 200,
408
+ "stateful_callbacks": {
409
+ "TrainerControl": {
410
+ "args": {
411
+ "should_epoch_stop": false,
412
+ "should_evaluate": false,
413
+ "should_log": false,
414
+ "should_save": true,
415
+ "should_training_stop": false
416
+ },
417
+ "attributes": {}
418
+ }
419
+ },
420
+ "total_flos": 1.113474465792e+16,
421
+ "train_batch_size": 2,
422
+ "trial_name": null,
423
+ "trial_params": null
424
+ }
qwen3-150m-finetuned-antonyms/checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a412f0daaffd5e2c26806635af04cb23c8d6303f45667ff9b72e81b4e25e433
3
+ size 5304
qwen3-150m-finetuned-antonyms/checkpoint-1200/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 2,
8
+ "eos_token_id": 3,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 2048,
14
+ "layer_types": [
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention"
27
+ ],
28
+ "max_position_embeddings": 2048,
29
+ "max_window_layers": 28,
30
+ "model_type": "qwen3",
31
+ "num_attention_heads": 12,
32
+ "num_hidden_layers": 12,
33
+ "num_key_value_heads": 12,
34
+ "pad_token_id": 1,
35
+ "rms_norm_eps": 1e-06,
36
+ "rope_scaling": null,
37
+ "rope_theta": 10000.0,
38
+ "sliding_window": null,
39
+ "tie_word_embeddings": true,
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.55.4",
42
+ "use_cache": true,
43
+ "use_sliding_window": false,
44
+ "vocab_size": 32000
45
+ }
qwen3-150m-finetuned-antonyms/checkpoint-1200/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 3,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.55.4"
7
+ }
qwen3-150m-finetuned-antonyms/checkpoint-1200/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:462a32e73f3a4936485b53020ad081d68b4e0dc546198309d14cac315899e2cf
3
+ size 551392792
qwen3-150m-finetuned-antonyms/checkpoint-1200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7b1ab16b599d1f46899f67ac9cbefffc5974e861930db90778996bb685dd93c
3
+ size 1102868538
qwen3-150m-finetuned-antonyms/checkpoint-1200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3905f03b154613277addb21f09efb9dda07a5e9f0835de2cf6f43a703e22bde7
3
+ size 14244
qwen3-150m-finetuned-antonyms/checkpoint-1200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a0ed83419e2437807687d8c84bc2054f55fad8dca47bd2d868ecfc370acaf55
3
+ size 1064
qwen3-150m-finetuned-antonyms/checkpoint-1200/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<pad>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
qwen3-150m-finetuned-antonyms/checkpoint-1200/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
qwen3-150m-finetuned-antonyms/checkpoint-1200/tokenizer_config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<en>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<te>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "<mai>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "<mask>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ }
67
+ },
68
+ "bos_token": "<s>",
69
+ "clean_up_tokenization_spaces": false,
70
+ "eos_token": "</s>",
71
+ "extra_special_tokens": {},
72
+ "model_max_length": 1000000000000000019884624838656,
73
+ "pad_token": "<pad>",
74
+ "tokenizer_class": "PreTrainedTokenizerFast",
75
+ "unk_token": "<unk>"
76
+ }
qwen3-150m-finetuned-antonyms/checkpoint-1200/trainer_state.json ADDED
@@ -0,0 +1,502 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1200,
3
+ "best_metric": 0.2097395956516266,
4
+ "best_model_checkpoint": "./qwen3-150m-finetuned-antonyms\\checkpoint-1200",
5
+ "epoch": 0.8084210526315789,
6
+ "eval_steps": 200,
7
+ "global_step": 1200,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.013473684210526317,
14
+ "grad_norm": 2.7961366176605225,
15
+ "learning_rate": 2.5503355704697992e-06,
16
+ "loss": 2.917,
17
+ "step": 20
18
+ },
19
+ {
20
+ "epoch": 0.026947368421052633,
21
+ "grad_norm": 2.30360746383667,
22
+ "learning_rate": 5.234899328859061e-06,
23
+ "loss": 2.3528,
24
+ "step": 40
25
+ },
26
+ {
27
+ "epoch": 0.04042105263157895,
28
+ "grad_norm": 1.5964854955673218,
29
+ "learning_rate": 7.919463087248322e-06,
30
+ "loss": 1.8678,
31
+ "step": 60
32
+ },
33
+ {
34
+ "epoch": 0.053894736842105266,
35
+ "grad_norm": 1.4178063869476318,
36
+ "learning_rate": 1.0604026845637586e-05,
37
+ "loss": 1.7207,
38
+ "step": 80
39
+ },
40
+ {
41
+ "epoch": 0.06736842105263158,
42
+ "grad_norm": 1.6399588584899902,
43
+ "learning_rate": 1.3288590604026848e-05,
44
+ "loss": 1.5277,
45
+ "step": 100
46
+ },
47
+ {
48
+ "epoch": 0.0808421052631579,
49
+ "grad_norm": 1.6011607646942139,
50
+ "learning_rate": 1.5973154362416107e-05,
51
+ "loss": 1.4006,
52
+ "step": 120
53
+ },
54
+ {
55
+ "epoch": 0.09431578947368421,
56
+ "grad_norm": 1.3836917877197266,
57
+ "learning_rate": 1.865771812080537e-05,
58
+ "loss": 1.342,
59
+ "step": 140
60
+ },
61
+ {
62
+ "epoch": 0.10778947368421053,
63
+ "grad_norm": 1.8060948848724365,
64
+ "learning_rate": 1.9999379903772885e-05,
65
+ "loss": 1.2442,
66
+ "step": 160
67
+ },
68
+ {
69
+ "epoch": 0.12126315789473684,
70
+ "grad_norm": 1.4634225368499756,
71
+ "learning_rate": 1.999441959536959e-05,
72
+ "loss": 1.1505,
73
+ "step": 180
74
+ },
75
+ {
76
+ "epoch": 0.13473684210526315,
77
+ "grad_norm": 1.609693169593811,
78
+ "learning_rate": 1.9984501439181532e-05,
79
+ "loss": 1.0635,
80
+ "step": 200
81
+ },
82
+ {
83
+ "epoch": 0.13473684210526315,
84
+ "eval_loss": 1.1043256521224976,
85
+ "eval_runtime": 88.2411,
86
+ "eval_samples_per_second": 28.331,
87
+ "eval_steps_per_second": 14.166,
88
+ "step": 200
89
+ },
90
+ {
91
+ "epoch": 0.1482105263157895,
92
+ "grad_norm": 1.3189349174499512,
93
+ "learning_rate": 1.996963035522515e-05,
94
+ "loss": 0.9328,
95
+ "step": 220
96
+ },
97
+ {
98
+ "epoch": 0.1616842105263158,
99
+ "grad_norm": 1.6366477012634277,
100
+ "learning_rate": 1.9949813720474152e-05,
101
+ "loss": 0.8752,
102
+ "step": 240
103
+ },
104
+ {
105
+ "epoch": 0.1751578947368421,
106
+ "grad_norm": 1.3156894445419312,
107
+ "learning_rate": 1.9925061365200102e-05,
108
+ "loss": 0.811,
109
+ "step": 260
110
+ },
111
+ {
112
+ "epoch": 0.18863157894736843,
113
+ "grad_norm": 1.4519543647766113,
114
+ "learning_rate": 1.989538556809598e-05,
115
+ "loss": 0.7621,
116
+ "step": 280
117
+ },
118
+ {
119
+ "epoch": 0.20210526315789473,
120
+ "grad_norm": 1.3389956951141357,
121
+ "learning_rate": 1.986080105018521e-05,
122
+ "loss": 0.7399,
123
+ "step": 300
124
+ },
125
+ {
126
+ "epoch": 0.21557894736842106,
127
+ "grad_norm": 1.240100622177124,
128
+ "learning_rate": 1.9821324967519113e-05,
129
+ "loss": 0.6431,
130
+ "step": 320
131
+ },
132
+ {
133
+ "epoch": 0.22905263157894737,
134
+ "grad_norm": 1.7040982246398926,
135
+ "learning_rate": 1.9776976902666452e-05,
136
+ "loss": 0.5932,
137
+ "step": 340
138
+ },
139
+ {
140
+ "epoch": 0.24252631578947367,
141
+ "grad_norm": 1.1405657529830933,
142
+ "learning_rate": 1.9727778854999283e-05,
143
+ "loss": 0.5804,
144
+ "step": 360
145
+ },
146
+ {
147
+ "epoch": 0.256,
148
+ "grad_norm": 1.4422856569290161,
149
+ "learning_rate": 1.9673755229779884e-05,
150
+ "loss": 0.5823,
151
+ "step": 380
152
+ },
153
+ {
154
+ "epoch": 0.2694736842105263,
155
+ "grad_norm": 1.2760127782821655,
156
+ "learning_rate": 1.9614932826054274e-05,
157
+ "loss": 0.5321,
158
+ "step": 400
159
+ },
160
+ {
161
+ "epoch": 0.2694736842105263,
162
+ "eval_loss": 0.5738449096679688,
163
+ "eval_runtime": 64.7646,
164
+ "eval_samples_per_second": 38.601,
165
+ "eval_steps_per_second": 19.301,
166
+ "step": 400
167
+ },
168
+ {
169
+ "epoch": 0.2829473684210526,
170
+ "grad_norm": 1.2698249816894531,
171
+ "learning_rate": 1.9551340823358217e-05,
172
+ "loss": 0.5178,
173
+ "step": 420
174
+ },
175
+ {
176
+ "epoch": 0.296421052631579,
177
+ "grad_norm": 1.0051153898239136,
178
+ "learning_rate": 1.948301076724237e-05,
179
+ "loss": 0.5021,
180
+ "step": 440
181
+ },
182
+ {
183
+ "epoch": 0.3098947368421053,
184
+ "grad_norm": 1.0702327489852905,
185
+ "learning_rate": 1.9409976553623767e-05,
186
+ "loss": 0.4409,
187
+ "step": 460
188
+ },
189
+ {
190
+ "epoch": 0.3233684210526316,
191
+ "grad_norm": 1.2159368991851807,
192
+ "learning_rate": 1.9332274411971333e-05,
193
+ "loss": 0.4028,
194
+ "step": 480
195
+ },
196
+ {
197
+ "epoch": 0.3368421052631579,
198
+ "grad_norm": 1.3318655490875244,
199
+ "learning_rate": 1.924994288733386e-05,
200
+ "loss": 0.4199,
201
+ "step": 500
202
+ },
203
+ {
204
+ "epoch": 0.3503157894736842,
205
+ "grad_norm": 1.4047660827636719,
206
+ "learning_rate": 1.9163022821219252e-05,
207
+ "loss": 0.3865,
208
+ "step": 520
209
+ },
210
+ {
211
+ "epoch": 0.36378947368421055,
212
+ "grad_norm": 1.0359469652175903,
213
+ "learning_rate": 1.907155733133467e-05,
214
+ "loss": 0.3779,
215
+ "step": 540
216
+ },
217
+ {
218
+ "epoch": 0.37726315789473686,
219
+ "grad_norm": 1.1933883428573608,
220
+ "learning_rate": 1.897559179019745e-05,
221
+ "loss": 0.358,
222
+ "step": 560
223
+ },
224
+ {
225
+ "epoch": 0.39073684210526316,
226
+ "grad_norm": 1.1323217153549194,
227
+ "learning_rate": 1.8875173802627565e-05,
228
+ "loss": 0.3715,
229
+ "step": 580
230
+ },
231
+ {
232
+ "epoch": 0.40421052631578946,
233
+ "grad_norm": 1.0181940793991089,
234
+ "learning_rate": 1.8770353182132684e-05,
235
+ "loss": 0.3428,
236
+ "step": 600
237
+ },
238
+ {
239
+ "epoch": 0.40421052631578946,
240
+ "eval_loss": 0.37542256712913513,
241
+ "eval_runtime": 89.5428,
242
+ "eval_samples_per_second": 27.92,
243
+ "eval_steps_per_second": 13.96,
244
+ "step": 600
245
+ },
246
+ {
247
+ "epoch": 0.41768421052631577,
248
+ "grad_norm": 1.0640043020248413,
249
+ "learning_rate": 1.8661181926197627e-05,
250
+ "loss": 0.3183,
251
+ "step": 620
252
+ },
253
+ {
254
+ "epoch": 0.43115789473684213,
255
+ "grad_norm": 0.9247826933860779,
256
+ "learning_rate": 1.8547714190490385e-05,
257
+ "loss": 0.3054,
258
+ "step": 640
259
+ },
260
+ {
261
+ "epoch": 0.44463157894736843,
262
+ "grad_norm": 1.059590458869934,
263
+ "learning_rate": 1.8430006261997585e-05,
264
+ "loss": 0.3088,
265
+ "step": 660
266
+ },
267
+ {
268
+ "epoch": 0.45810526315789474,
269
+ "grad_norm": 1.1035728454589844,
270
+ "learning_rate": 1.8308116531102674e-05,
271
+ "loss": 0.3163,
272
+ "step": 680
273
+ },
274
+ {
275
+ "epoch": 0.47157894736842104,
276
+ "grad_norm": 1.2538524866104126,
277
+ "learning_rate": 1.81821054626207e-05,
278
+ "loss": 0.2959,
279
+ "step": 700
280
+ },
281
+ {
282
+ "epoch": 0.48505263157894735,
283
+ "grad_norm": 1.0344308614730835,
284
+ "learning_rate": 1.8052035565804024e-05,
285
+ "loss": 0.2746,
286
+ "step": 720
287
+ },
288
+ {
289
+ "epoch": 0.4985263157894737,
290
+ "grad_norm": 1.0735608339309692,
291
+ "learning_rate": 1.7917971363333896e-05,
292
+ "loss": 0.2804,
293
+ "step": 740
294
+ },
295
+ {
296
+ "epoch": 0.512,
297
+ "grad_norm": 0.9861028790473938,
298
+ "learning_rate": 1.777997935931322e-05,
299
+ "loss": 0.266,
300
+ "step": 760
301
+ },
302
+ {
303
+ "epoch": 0.5254736842105263,
304
+ "grad_norm": 1.2618284225463867,
305
+ "learning_rate": 1.7638128006276422e-05,
306
+ "loss": 0.267,
307
+ "step": 780
308
+ },
309
+ {
310
+ "epoch": 0.5389473684210526,
311
+ "grad_norm": 0.7712630033493042,
312
+ "learning_rate": 1.7492487671232784e-05,
313
+ "loss": 0.245,
314
+ "step": 800
315
+ },
316
+ {
317
+ "epoch": 0.5389473684210526,
318
+ "eval_loss": 0.2860563099384308,
319
+ "eval_runtime": 168.0857,
320
+ "eval_samples_per_second": 14.873,
321
+ "eval_steps_per_second": 7.437,
322
+ "step": 800
323
+ },
324
+ {
325
+ "epoch": 0.5524210526315789,
326
+ "grad_norm": 1.0299738645553589,
327
+ "learning_rate": 1.7343130600760068e-05,
328
+ "loss": 0.246,
329
+ "step": 820
330
+ },
331
+ {
332
+ "epoch": 0.5658947368421052,
333
+ "grad_norm": 1.2506853342056274,
334
+ "learning_rate": 1.719013088516576e-05,
335
+ "loss": 0.237,
336
+ "step": 840
337
+ },
338
+ {
339
+ "epoch": 0.5793684210526315,
340
+ "grad_norm": 0.7798528671264648,
341
+ "learning_rate": 1.7033564421733717e-05,
342
+ "loss": 0.2329,
343
+ "step": 860
344
+ },
345
+ {
346
+ "epoch": 0.592842105263158,
347
+ "grad_norm": 1.0132075548171997,
348
+ "learning_rate": 1.6873508877074443e-05,
349
+ "loss": 0.2437,
350
+ "step": 880
351
+ },
352
+ {
353
+ "epoch": 0.6063157894736843,
354
+ "grad_norm": 0.9196950197219849,
355
+ "learning_rate": 1.6710043648597656e-05,
356
+ "loss": 0.2409,
357
+ "step": 900
358
+ },
359
+ {
360
+ "epoch": 0.6197894736842106,
361
+ "grad_norm": 0.8007433414459229,
362
+ "learning_rate": 1.6543249825126285e-05,
363
+ "loss": 0.2188,
364
+ "step": 920
365
+ },
366
+ {
367
+ "epoch": 0.6332631578947369,
368
+ "grad_norm": 0.7954726219177246,
369
+ "learning_rate": 1.6373210146671437e-05,
370
+ "loss": 0.2076,
371
+ "step": 940
372
+ },
373
+ {
374
+ "epoch": 0.6467368421052632,
375
+ "grad_norm": 0.7610670924186707,
376
+ "learning_rate": 1.6200008963388216e-05,
377
+ "loss": 0.2153,
378
+ "step": 960
379
+ },
380
+ {
381
+ "epoch": 0.6602105263157895,
382
+ "grad_norm": 0.7918910980224609,
383
+ "learning_rate": 1.6023732193732886e-05,
384
+ "loss": 0.205,
385
+ "step": 980
386
+ },
387
+ {
388
+ "epoch": 0.6736842105263158,
389
+ "grad_norm": 0.8178799152374268,
390
+ "learning_rate": 1.5844467281842007e-05,
391
+ "loss": 0.1922,
392
+ "step": 1000
393
+ },
394
+ {
395
+ "epoch": 0.6736842105263158,
396
+ "eval_loss": 0.23861029744148254,
397
+ "eval_runtime": 171.498,
398
+ "eval_samples_per_second": 14.577,
399
+ "eval_steps_per_second": 7.289,
400
+ "step": 1000
401
+ },
402
+ {
403
+ "epoch": 0.6871578947368421,
404
+ "grad_norm": 0.8836315870285034,
405
+ "learning_rate": 1.5662303154154764e-05,
406
+ "loss": 0.1997,
407
+ "step": 1020
408
+ },
409
+ {
410
+ "epoch": 0.7006315789473684,
411
+ "grad_norm": 0.9780408143997192,
412
+ "learning_rate": 1.5477330175299964e-05,
413
+ "loss": 0.2065,
414
+ "step": 1040
415
+ },
416
+ {
417
+ "epoch": 0.7141052631578947,
418
+ "grad_norm": 0.7557224631309509,
419
+ "learning_rate": 1.5289640103269626e-05,
420
+ "loss": 0.2015,
421
+ "step": 1060
422
+ },
423
+ {
424
+ "epoch": 0.7275789473684211,
425
+ "grad_norm": 0.813556969165802,
426
+ "learning_rate": 1.5099326043901361e-05,
427
+ "loss": 0.201,
428
+ "step": 1080
429
+ },
430
+ {
431
+ "epoch": 0.7410526315789474,
432
+ "grad_norm": 0.5978159308433533,
433
+ "learning_rate": 1.4906482404692133e-05,
434
+ "loss": 0.1862,
435
+ "step": 1100
436
+ },
437
+ {
438
+ "epoch": 0.7545263157894737,
439
+ "grad_norm": 0.8261023163795471,
440
+ "learning_rate": 1.471120484796634e-05,
441
+ "loss": 0.1946,
442
+ "step": 1120
443
+ },
444
+ {
445
+ "epoch": 0.768,
446
+ "grad_norm": 0.6979694366455078,
447
+ "learning_rate": 1.4513590243421394e-05,
448
+ "loss": 0.1763,
449
+ "step": 1140
450
+ },
451
+ {
452
+ "epoch": 0.7814736842105263,
453
+ "grad_norm": 0.7573559880256653,
454
+ "learning_rate": 1.4313736620074389e-05,
455
+ "loss": 0.1825,
456
+ "step": 1160
457
+ },
458
+ {
459
+ "epoch": 0.7949473684210526,
460
+ "grad_norm": 0.6948429346084595,
461
+ "learning_rate": 1.4111743117633676e-05,
462
+ "loss": 0.1835,
463
+ "step": 1180
464
+ },
465
+ {
466
+ "epoch": 0.8084210526315789,
467
+ "grad_norm": 0.7930866479873657,
468
+ "learning_rate": 1.3907709937319451e-05,
469
+ "loss": 0.1852,
470
+ "step": 1200
471
+ },
472
+ {
473
+ "epoch": 0.8084210526315789,
474
+ "eval_loss": 0.2097395956516266,
475
+ "eval_runtime": 169.5737,
476
+ "eval_samples_per_second": 14.743,
477
+ "eval_steps_per_second": 7.371,
478
+ "step": 1200
479
+ }
480
+ ],
481
+ "logging_steps": 20,
482
+ "max_steps": 2970,
483
+ "num_input_tokens_seen": 0,
484
+ "num_train_epochs": 2,
485
+ "save_steps": 200,
486
+ "stateful_callbacks": {
487
+ "TrainerControl": {
488
+ "args": {
489
+ "should_epoch_stop": false,
490
+ "should_evaluate": false,
491
+ "should_log": false,
492
+ "should_save": true,
493
+ "should_training_stop": false
494
+ },
495
+ "attributes": {}
496
+ }
497
+ },
498
+ "total_flos": 1.3361693589504e+16,
499
+ "train_batch_size": 2,
500
+ "trial_name": null,
501
+ "trial_params": null
502
+ }
qwen3-150m-finetuned-antonyms/checkpoint-1200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a412f0daaffd5e2c26806635af04cb23c8d6303f45667ff9b72e81b4e25e433
3
+ size 5304
qwen3-150m-finetuned-antonyms/checkpoint-1400/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 2,
8
+ "eos_token_id": 3,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 2048,
14
+ "layer_types": [
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention"
27
+ ],
28
+ "max_position_embeddings": 2048,
29
+ "max_window_layers": 28,
30
+ "model_type": "qwen3",
31
+ "num_attention_heads": 12,
32
+ "num_hidden_layers": 12,
33
+ "num_key_value_heads": 12,
34
+ "pad_token_id": 1,
35
+ "rms_norm_eps": 1e-06,
36
+ "rope_scaling": null,
37
+ "rope_theta": 10000.0,
38
+ "sliding_window": null,
39
+ "tie_word_embeddings": true,
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.55.4",
42
+ "use_cache": true,
43
+ "use_sliding_window": false,
44
+ "vocab_size": 32000
45
+ }
qwen3-150m-finetuned-antonyms/checkpoint-1400/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 3,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.55.4"
7
+ }
qwen3-150m-finetuned-antonyms/checkpoint-1400/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:397684d9fa6022e669b07692bcdecdf0f8e6ee1fa2de3be85c62a8512f5e2741
3
+ size 551392792
qwen3-150m-finetuned-antonyms/checkpoint-1400/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1fab8185b58c67fdbe9c4af8d00a7c4e203c2147f514401206f4b8fe97f0f05
3
+ size 1102868538
qwen3-150m-finetuned-antonyms/checkpoint-1400/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff39c56748cc5e85691d62bfd6a79e60ab92c1f59b698543eba03446c493cd5c
3
+ size 14244
qwen3-150m-finetuned-antonyms/checkpoint-1400/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:727efae6b2f9ee37e1e5756f41156bac19e15adede5c8242c737cd13b543e9f8
3
+ size 1064
qwen3-150m-finetuned-antonyms/checkpoint-1400/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<pad>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
qwen3-150m-finetuned-antonyms/checkpoint-1400/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
qwen3-150m-finetuned-antonyms/checkpoint-1400/tokenizer_config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<en>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<te>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "<mai>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "<mask>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ }
67
+ },
68
+ "bos_token": "<s>",
69
+ "clean_up_tokenization_spaces": false,
70
+ "eos_token": "</s>",
71
+ "extra_special_tokens": {},
72
+ "model_max_length": 1000000000000000019884624838656,
73
+ "pad_token": "<pad>",
74
+ "tokenizer_class": "PreTrainedTokenizerFast",
75
+ "unk_token": "<unk>"
76
+ }
qwen3-150m-finetuned-antonyms/checkpoint-1400/trainer_state.json ADDED
@@ -0,0 +1,580 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1400,
3
+ "best_metric": 0.19134877622127533,
4
+ "best_model_checkpoint": "./qwen3-150m-finetuned-antonyms\\checkpoint-1400",
5
+ "epoch": 0.9431578947368421,
6
+ "eval_steps": 200,
7
+ "global_step": 1400,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.013473684210526317,
14
+ "grad_norm": 2.7961366176605225,
15
+ "learning_rate": 2.5503355704697992e-06,
16
+ "loss": 2.917,
17
+ "step": 20
18
+ },
19
+ {
20
+ "epoch": 0.026947368421052633,
21
+ "grad_norm": 2.30360746383667,
22
+ "learning_rate": 5.234899328859061e-06,
23
+ "loss": 2.3528,
24
+ "step": 40
25
+ },
26
+ {
27
+ "epoch": 0.04042105263157895,
28
+ "grad_norm": 1.5964854955673218,
29
+ "learning_rate": 7.919463087248322e-06,
30
+ "loss": 1.8678,
31
+ "step": 60
32
+ },
33
+ {
34
+ "epoch": 0.053894736842105266,
35
+ "grad_norm": 1.4178063869476318,
36
+ "learning_rate": 1.0604026845637586e-05,
37
+ "loss": 1.7207,
38
+ "step": 80
39
+ },
40
+ {
41
+ "epoch": 0.06736842105263158,
42
+ "grad_norm": 1.6399588584899902,
43
+ "learning_rate": 1.3288590604026848e-05,
44
+ "loss": 1.5277,
45
+ "step": 100
46
+ },
47
+ {
48
+ "epoch": 0.0808421052631579,
49
+ "grad_norm": 1.6011607646942139,
50
+ "learning_rate": 1.5973154362416107e-05,
51
+ "loss": 1.4006,
52
+ "step": 120
53
+ },
54
+ {
55
+ "epoch": 0.09431578947368421,
56
+ "grad_norm": 1.3836917877197266,
57
+ "learning_rate": 1.865771812080537e-05,
58
+ "loss": 1.342,
59
+ "step": 140
60
+ },
61
+ {
62
+ "epoch": 0.10778947368421053,
63
+ "grad_norm": 1.8060948848724365,
64
+ "learning_rate": 1.9999379903772885e-05,
65
+ "loss": 1.2442,
66
+ "step": 160
67
+ },
68
+ {
69
+ "epoch": 0.12126315789473684,
70
+ "grad_norm": 1.4634225368499756,
71
+ "learning_rate": 1.999441959536959e-05,
72
+ "loss": 1.1505,
73
+ "step": 180
74
+ },
75
+ {
76
+ "epoch": 0.13473684210526315,
77
+ "grad_norm": 1.609693169593811,
78
+ "learning_rate": 1.9984501439181532e-05,
79
+ "loss": 1.0635,
80
+ "step": 200
81
+ },
82
+ {
83
+ "epoch": 0.13473684210526315,
84
+ "eval_loss": 1.1043256521224976,
85
+ "eval_runtime": 88.2411,
86
+ "eval_samples_per_second": 28.331,
87
+ "eval_steps_per_second": 14.166,
88
+ "step": 200
89
+ },
90
+ {
91
+ "epoch": 0.1482105263157895,
92
+ "grad_norm": 1.3189349174499512,
93
+ "learning_rate": 1.996963035522515e-05,
94
+ "loss": 0.9328,
95
+ "step": 220
96
+ },
97
+ {
98
+ "epoch": 0.1616842105263158,
99
+ "grad_norm": 1.6366477012634277,
100
+ "learning_rate": 1.9949813720474152e-05,
101
+ "loss": 0.8752,
102
+ "step": 240
103
+ },
104
+ {
105
+ "epoch": 0.1751578947368421,
106
+ "grad_norm": 1.3156894445419312,
107
+ "learning_rate": 1.9925061365200102e-05,
108
+ "loss": 0.811,
109
+ "step": 260
110
+ },
111
+ {
112
+ "epoch": 0.18863157894736843,
113
+ "grad_norm": 1.4519543647766113,
114
+ "learning_rate": 1.989538556809598e-05,
115
+ "loss": 0.7621,
116
+ "step": 280
117
+ },
118
+ {
119
+ "epoch": 0.20210526315789473,
120
+ "grad_norm": 1.3389956951141357,
121
+ "learning_rate": 1.986080105018521e-05,
122
+ "loss": 0.7399,
123
+ "step": 300
124
+ },
125
+ {
126
+ "epoch": 0.21557894736842106,
127
+ "grad_norm": 1.240100622177124,
128
+ "learning_rate": 1.9821324967519113e-05,
129
+ "loss": 0.6431,
130
+ "step": 320
131
+ },
132
+ {
133
+ "epoch": 0.22905263157894737,
134
+ "grad_norm": 1.7040982246398926,
135
+ "learning_rate": 1.9776976902666452e-05,
136
+ "loss": 0.5932,
137
+ "step": 340
138
+ },
139
+ {
140
+ "epoch": 0.24252631578947367,
141
+ "grad_norm": 1.1405657529830933,
142
+ "learning_rate": 1.9727778854999283e-05,
143
+ "loss": 0.5804,
144
+ "step": 360
145
+ },
146
+ {
147
+ "epoch": 0.256,
148
+ "grad_norm": 1.4422856569290161,
149
+ "learning_rate": 1.9673755229779884e-05,
150
+ "loss": 0.5823,
151
+ "step": 380
152
+ },
153
+ {
154
+ "epoch": 0.2694736842105263,
155
+ "grad_norm": 1.2760127782821655,
156
+ "learning_rate": 1.9614932826054274e-05,
157
+ "loss": 0.5321,
158
+ "step": 400
159
+ },
160
+ {
161
+ "epoch": 0.2694736842105263,
162
+ "eval_loss": 0.5738449096679688,
163
+ "eval_runtime": 64.7646,
164
+ "eval_samples_per_second": 38.601,
165
+ "eval_steps_per_second": 19.301,
166
+ "step": 400
167
+ },
168
+ {
169
+ "epoch": 0.2829473684210526,
170
+ "grad_norm": 1.2698249816894531,
171
+ "learning_rate": 1.9551340823358217e-05,
172
+ "loss": 0.5178,
173
+ "step": 420
174
+ },
175
+ {
176
+ "epoch": 0.296421052631579,
177
+ "grad_norm": 1.0051153898239136,
178
+ "learning_rate": 1.948301076724237e-05,
179
+ "loss": 0.5021,
180
+ "step": 440
181
+ },
182
+ {
183
+ "epoch": 0.3098947368421053,
184
+ "grad_norm": 1.0702327489852905,
185
+ "learning_rate": 1.9409976553623767e-05,
186
+ "loss": 0.4409,
187
+ "step": 460
188
+ },
189
+ {
190
+ "epoch": 0.3233684210526316,
191
+ "grad_norm": 1.2159368991851807,
192
+ "learning_rate": 1.9332274411971333e-05,
193
+ "loss": 0.4028,
194
+ "step": 480
195
+ },
196
+ {
197
+ "epoch": 0.3368421052631579,
198
+ "grad_norm": 1.3318655490875244,
199
+ "learning_rate": 1.924994288733386e-05,
200
+ "loss": 0.4199,
201
+ "step": 500
202
+ },
203
+ {
204
+ "epoch": 0.3503157894736842,
205
+ "grad_norm": 1.4047660827636719,
206
+ "learning_rate": 1.9163022821219252e-05,
207
+ "loss": 0.3865,
208
+ "step": 520
209
+ },
210
+ {
211
+ "epoch": 0.36378947368421055,
212
+ "grad_norm": 1.0359469652175903,
213
+ "learning_rate": 1.907155733133467e-05,
214
+ "loss": 0.3779,
215
+ "step": 540
216
+ },
217
+ {
218
+ "epoch": 0.37726315789473686,
219
+ "grad_norm": 1.1933883428573608,
220
+ "learning_rate": 1.897559179019745e-05,
221
+ "loss": 0.358,
222
+ "step": 560
223
+ },
224
+ {
225
+ "epoch": 0.39073684210526316,
226
+ "grad_norm": 1.1323217153549194,
227
+ "learning_rate": 1.8875173802627565e-05,
228
+ "loss": 0.3715,
229
+ "step": 580
230
+ },
231
+ {
232
+ "epoch": 0.40421052631578946,
233
+ "grad_norm": 1.0181940793991089,
234
+ "learning_rate": 1.8770353182132684e-05,
235
+ "loss": 0.3428,
236
+ "step": 600
237
+ },
238
+ {
239
+ "epoch": 0.40421052631578946,
240
+ "eval_loss": 0.37542256712913513,
241
+ "eval_runtime": 89.5428,
242
+ "eval_samples_per_second": 27.92,
243
+ "eval_steps_per_second": 13.96,
244
+ "step": 600
245
+ },
246
+ {
247
+ "epoch": 0.41768421052631577,
248
+ "grad_norm": 1.0640043020248413,
249
+ "learning_rate": 1.8661181926197627e-05,
250
+ "loss": 0.3183,
251
+ "step": 620
252
+ },
253
+ {
254
+ "epoch": 0.43115789473684213,
255
+ "grad_norm": 0.9247826933860779,
256
+ "learning_rate": 1.8547714190490385e-05,
257
+ "loss": 0.3054,
258
+ "step": 640
259
+ },
260
+ {
261
+ "epoch": 0.44463157894736843,
262
+ "grad_norm": 1.059590458869934,
263
+ "learning_rate": 1.8430006261997585e-05,
264
+ "loss": 0.3088,
265
+ "step": 660
266
+ },
267
+ {
268
+ "epoch": 0.45810526315789474,
269
+ "grad_norm": 1.1035728454589844,
270
+ "learning_rate": 1.8308116531102674e-05,
271
+ "loss": 0.3163,
272
+ "step": 680
273
+ },
274
+ {
275
+ "epoch": 0.47157894736842104,
276
+ "grad_norm": 1.2538524866104126,
277
+ "learning_rate": 1.81821054626207e-05,
278
+ "loss": 0.2959,
279
+ "step": 700
280
+ },
281
+ {
282
+ "epoch": 0.48505263157894735,
283
+ "grad_norm": 1.0344308614730835,
284
+ "learning_rate": 1.8052035565804024e-05,
285
+ "loss": 0.2746,
286
+ "step": 720
287
+ },
288
+ {
289
+ "epoch": 0.4985263157894737,
290
+ "grad_norm": 1.0735608339309692,
291
+ "learning_rate": 1.7917971363333896e-05,
292
+ "loss": 0.2804,
293
+ "step": 740
294
+ },
295
+ {
296
+ "epoch": 0.512,
297
+ "grad_norm": 0.9861028790473938,
298
+ "learning_rate": 1.777997935931322e-05,
299
+ "loss": 0.266,
300
+ "step": 760
301
+ },
302
+ {
303
+ "epoch": 0.5254736842105263,
304
+ "grad_norm": 1.2618284225463867,
305
+ "learning_rate": 1.7638128006276422e-05,
306
+ "loss": 0.267,
307
+ "step": 780
308
+ },
309
+ {
310
+ "epoch": 0.5389473684210526,
311
+ "grad_norm": 0.7712630033493042,
312
+ "learning_rate": 1.7492487671232784e-05,
313
+ "loss": 0.245,
314
+ "step": 800
315
+ },
316
+ {
317
+ "epoch": 0.5389473684210526,
318
+ "eval_loss": 0.2860563099384308,
319
+ "eval_runtime": 168.0857,
320
+ "eval_samples_per_second": 14.873,
321
+ "eval_steps_per_second": 7.437,
322
+ "step": 800
323
+ },
324
+ {
325
+ "epoch": 0.5524210526315789,
326
+ "grad_norm": 1.0299738645553589,
327
+ "learning_rate": 1.7343130600760068e-05,
328
+ "loss": 0.246,
329
+ "step": 820
330
+ },
331
+ {
332
+ "epoch": 0.5658947368421052,
333
+ "grad_norm": 1.2506853342056274,
334
+ "learning_rate": 1.719013088516576e-05,
335
+ "loss": 0.237,
336
+ "step": 840
337
+ },
338
+ {
339
+ "epoch": 0.5793684210526315,
340
+ "grad_norm": 0.7798528671264648,
341
+ "learning_rate": 1.7033564421733717e-05,
342
+ "loss": 0.2329,
343
+ "step": 860
344
+ },
345
+ {
346
+ "epoch": 0.592842105263158,
347
+ "grad_norm": 1.0132075548171997,
348
+ "learning_rate": 1.6873508877074443e-05,
349
+ "loss": 0.2437,
350
+ "step": 880
351
+ },
352
+ {
353
+ "epoch": 0.6063157894736843,
354
+ "grad_norm": 0.9196950197219849,
355
+ "learning_rate": 1.6710043648597656e-05,
356
+ "loss": 0.2409,
357
+ "step": 900
358
+ },
359
+ {
360
+ "epoch": 0.6197894736842106,
361
+ "grad_norm": 0.8007433414459229,
362
+ "learning_rate": 1.6543249825126285e-05,
363
+ "loss": 0.2188,
364
+ "step": 920
365
+ },
366
+ {
367
+ "epoch": 0.6332631578947369,
368
+ "grad_norm": 0.7954726219177246,
369
+ "learning_rate": 1.6373210146671437e-05,
370
+ "loss": 0.2076,
371
+ "step": 940
372
+ },
373
+ {
374
+ "epoch": 0.6467368421052632,
375
+ "grad_norm": 0.7610670924186707,
376
+ "learning_rate": 1.6200008963388216e-05,
377
+ "loss": 0.2153,
378
+ "step": 960
379
+ },
380
+ {
381
+ "epoch": 0.6602105263157895,
382
+ "grad_norm": 0.7918910980224609,
383
+ "learning_rate": 1.6023732193732886e-05,
384
+ "loss": 0.205,
385
+ "step": 980
386
+ },
387
+ {
388
+ "epoch": 0.6736842105263158,
389
+ "grad_norm": 0.8178799152374268,
390
+ "learning_rate": 1.5844467281842007e-05,
391
+ "loss": 0.1922,
392
+ "step": 1000
393
+ },
394
+ {
395
+ "epoch": 0.6736842105263158,
396
+ "eval_loss": 0.23861029744148254,
397
+ "eval_runtime": 171.498,
398
+ "eval_samples_per_second": 14.577,
399
+ "eval_steps_per_second": 7.289,
400
+ "step": 1000
401
+ },
402
+ {
403
+ "epoch": 0.6871578947368421,
404
+ "grad_norm": 0.8836315870285034,
405
+ "learning_rate": 1.5662303154154764e-05,
406
+ "loss": 0.1997,
407
+ "step": 1020
408
+ },
409
+ {
410
+ "epoch": 0.7006315789473684,
411
+ "grad_norm": 0.9780408143997192,
412
+ "learning_rate": 1.5477330175299964e-05,
413
+ "loss": 0.2065,
414
+ "step": 1040
415
+ },
416
+ {
417
+ "epoch": 0.7141052631578947,
418
+ "grad_norm": 0.7557224631309509,
419
+ "learning_rate": 1.5289640103269626e-05,
420
+ "loss": 0.2015,
421
+ "step": 1060
422
+ },
423
+ {
424
+ "epoch": 0.7275789473684211,
425
+ "grad_norm": 0.813556969165802,
426
+ "learning_rate": 1.5099326043901361e-05,
427
+ "loss": 0.201,
428
+ "step": 1080
429
+ },
430
+ {
431
+ "epoch": 0.7410526315789474,
432
+ "grad_norm": 0.5978159308433533,
433
+ "learning_rate": 1.4906482404692133e-05,
434
+ "loss": 0.1862,
435
+ "step": 1100
436
+ },
437
+ {
438
+ "epoch": 0.7545263157894737,
439
+ "grad_norm": 0.8261023163795471,
440
+ "learning_rate": 1.471120484796634e-05,
441
+ "loss": 0.1946,
442
+ "step": 1120
443
+ },
444
+ {
445
+ "epoch": 0.768,
446
+ "grad_norm": 0.6979694366455078,
447
+ "learning_rate": 1.4513590243421394e-05,
448
+ "loss": 0.1763,
449
+ "step": 1140
450
+ },
451
+ {
452
+ "epoch": 0.7814736842105263,
453
+ "grad_norm": 0.7573559880256653,
454
+ "learning_rate": 1.4313736620074389e-05,
455
+ "loss": 0.1825,
456
+ "step": 1160
457
+ },
458
+ {
459
+ "epoch": 0.7949473684210526,
460
+ "grad_norm": 0.6948429346084595,
461
+ "learning_rate": 1.4111743117633676e-05,
462
+ "loss": 0.1835,
463
+ "step": 1180
464
+ },
465
+ {
466
+ "epoch": 0.8084210526315789,
467
+ "grad_norm": 0.7930866479873657,
468
+ "learning_rate": 1.3907709937319451e-05,
469
+ "loss": 0.1852,
470
+ "step": 1200
471
+ },
472
+ {
473
+ "epoch": 0.8084210526315789,
474
+ "eval_loss": 0.2097395956516266,
475
+ "eval_runtime": 169.5737,
476
+ "eval_samples_per_second": 14.743,
477
+ "eval_steps_per_second": 7.371,
478
+ "step": 1200
479
+ },
480
+ {
481
+ "epoch": 0.8218947368421052,
482
+ "grad_norm": 0.6302672624588013,
483
+ "learning_rate": 1.3701738292157778e-05,
484
+ "loss": 0.1776,
485
+ "step": 1220
486
+ },
487
+ {
488
+ "epoch": 0.8353684210526315,
489
+ "grad_norm": 0.8323765397071838,
490
+ "learning_rate": 1.3493930356772705e-05,
491
+ "loss": 0.1793,
492
+ "step": 1240
493
+ },
494
+ {
495
+ "epoch": 0.8488421052631578,
496
+ "grad_norm": 0.6844717264175415,
497
+ "learning_rate": 1.328438921670134e-05,
498
+ "loss": 0.1652,
499
+ "step": 1260
500
+ },
501
+ {
502
+ "epoch": 0.8623157894736843,
503
+ "grad_norm": 0.8403880000114441,
504
+ "learning_rate": 1.3073218817257091e-05,
505
+ "loss": 0.174,
506
+ "step": 1280
507
+ },
508
+ {
509
+ "epoch": 0.8757894736842106,
510
+ "grad_norm": 0.7015041708946228,
511
+ "learning_rate": 1.2860523911966367e-05,
512
+ "loss": 0.164,
513
+ "step": 1300
514
+ },
515
+ {
516
+ "epoch": 0.8892631578947369,
517
+ "grad_norm": 0.7717349529266357,
518
+ "learning_rate": 1.2646410010604397e-05,
519
+ "loss": 0.1738,
520
+ "step": 1320
521
+ },
522
+ {
523
+ "epoch": 0.9027368421052632,
524
+ "grad_norm": 0.7405645847320557,
525
+ "learning_rate": 1.2430983326855873e-05,
526
+ "loss": 0.1743,
527
+ "step": 1340
528
+ },
529
+ {
530
+ "epoch": 0.9162105263157895,
531
+ "grad_norm": 0.5770362019538879,
532
+ "learning_rate": 1.2214350725626412e-05,
533
+ "loss": 0.161,
534
+ "step": 1360
535
+ },
536
+ {
537
+ "epoch": 0.9296842105263158,
538
+ "grad_norm": 0.8527249693870544,
539
+ "learning_rate": 1.1996619670030996e-05,
540
+ "loss": 0.1672,
541
+ "step": 1380
542
+ },
543
+ {
544
+ "epoch": 0.9431578947368421,
545
+ "grad_norm": 0.632085382938385,
546
+ "learning_rate": 1.177789816808563e-05,
547
+ "loss": 0.1621,
548
+ "step": 1400
549
+ },
550
+ {
551
+ "epoch": 0.9431578947368421,
552
+ "eval_loss": 0.19134877622127533,
553
+ "eval_runtime": 171.2315,
554
+ "eval_samples_per_second": 14.6,
555
+ "eval_steps_per_second": 7.3,
556
+ "step": 1400
557
+ }
558
+ ],
559
+ "logging_steps": 20,
560
+ "max_steps": 2970,
561
+ "num_input_tokens_seen": 0,
562
+ "num_train_epochs": 2,
563
+ "save_steps": 200,
564
+ "stateful_callbacks": {
565
+ "TrainerControl": {
566
+ "args": {
567
+ "should_epoch_stop": false,
568
+ "should_evaluate": false,
569
+ "should_log": false,
570
+ "should_save": true,
571
+ "should_training_stop": false
572
+ },
573
+ "attributes": {}
574
+ }
575
+ },
576
+ "total_flos": 1.5588642521088e+16,
577
+ "train_batch_size": 2,
578
+ "trial_name": null,
579
+ "trial_params": null
580
+ }
qwen3-150m-finetuned-antonyms/checkpoint-1400/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a412f0daaffd5e2c26806635af04cb23c8d6303f45667ff9b72e81b4e25e433
3
+ size 5304
qwen3-150m-finetuned-coherence/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 2,
8
+ "eos_token_id": 3,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 2048,
14
+ "layer_types": [
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention"
27
+ ],
28
+ "max_position_embeddings": 2048,
29
+ "max_window_layers": 28,
30
+ "model_type": "qwen3",
31
+ "num_attention_heads": 12,
32
+ "num_hidden_layers": 12,
33
+ "num_key_value_heads": 12,
34
+ "pad_token_id": 1,
35
+ "rms_norm_eps": 1e-06,
36
+ "rope_scaling": null,
37
+ "rope_theta": 10000.0,
38
+ "sliding_window": null,
39
+ "tie_word_embeddings": true,
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.55.4",
42
+ "use_cache": true,
43
+ "use_sliding_window": false,
44
+ "vocab_size": 32000
45
+ }
qwen3-150m-finetuned-coherence/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 3,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.55.4"
7
+ }
qwen3-150m-finetuned-coherence/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b8f382919990f42c759118cd048ed70d91dfb5c0f7bb5a4fa0f0a5d8af6de2b
3
+ size 551392792
qwen3-150m-finetuned-coherence/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<pad>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
qwen3-150m-finetuned-coherence/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
qwen3-150m-finetuned-coherence/tokenizer_config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<en>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<te>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "<mai>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "<mask>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ }
67
+ },
68
+ "bos_token": "<s>",
69
+ "clean_up_tokenization_spaces": false,
70
+ "eos_token": "</s>",
71
+ "extra_special_tokens": {},
72
+ "model_max_length": 1000000000000000019884624838656,
73
+ "pad_token": "<pad>",
74
+ "tokenizer_class": "PreTrainedTokenizerFast",
75
+ "unk_token": "<unk>"
76
+ }
qwen3-150m-finetuned-coherence/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42ce8a14b90abc12d09ad1bff5f1e06a1650b59f2fc92456af0b5aee5b95345d
3
+ size 5304
qwen3-150m-lora-finetune-logs-antonyms/events.out.tfevents.1757877473.Sai-Legion.21500.15 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5b1776bb810af8611770ee3158fd19e4764fefd59b74cc1220dc92a35b1c772
3
+ size 58128
qwen3-150m-lora-finetuned-antonyms/checkpoint-4200/README.md ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: c:\Users\vsai2\Documents\LAMA\training\qwen3-150m-multilingual-checkpoints\checkpoint-26000
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:c:\Users\vsai2\Documents\LAMA\training\qwen3-150m-multilingual-checkpoints\checkpoint-26000
7
+ - lora
8
+ - transformers
9
+ ---
10
+
11
+ # Model Card for Model ID
12
+
13
+ <!-- Provide a quick summary of what the model is/does. -->
14
+
15
+
16
+
17
+ ## Model Details
18
+
19
+ ### Model Description
20
+
21
+ <!-- Provide a longer summary of what this model is. -->
22
+
23
+
24
+
25
+ - **Developed by:** [More Information Needed]
26
+ - **Funded by [optional]:** [More Information Needed]
27
+ - **Shared by [optional]:** [More Information Needed]
28
+ - **Model type:** [More Information Needed]
29
+ - **Language(s) (NLP):** [More Information Needed]
30
+ - **License:** [More Information Needed]
31
+ - **Finetuned from model [optional]:** [More Information Needed]
32
+
33
+ ### Model Sources [optional]
34
+
35
+ <!-- Provide the basic links for the model. -->
36
+
37
+ - **Repository:** [More Information Needed]
38
+ - **Paper [optional]:** [More Information Needed]
39
+ - **Demo [optional]:** [More Information Needed]
40
+
41
+ ## Uses
42
+
43
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
44
+
45
+ ### Direct Use
46
+
47
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
48
+
49
+ [More Information Needed]
50
+
51
+ ### Downstream Use [optional]
52
+
53
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
54
+
55
+ [More Information Needed]
56
+
57
+ ### Out-of-Scope Use
58
+
59
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
60
+
61
+ [More Information Needed]
62
+
63
+ ## Bias, Risks, and Limitations
64
+
65
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
66
+
67
+ [More Information Needed]
68
+
69
+ ### Recommendations
70
+
71
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
72
+
73
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
74
+
75
+ ## How to Get Started with the Model
76
+
77
+ Use the code below to get started with the model.
78
+
79
+ [More Information Needed]
80
+
81
+ ## Training Details
82
+
83
+ ### Training Data
84
+
85
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
86
+
87
+ [More Information Needed]
88
+
89
+ ### Training Procedure
90
+
91
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
92
+
93
+ #### Preprocessing [optional]
94
+
95
+ [More Information Needed]
96
+
97
+
98
+ #### Training Hyperparameters
99
+
100
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
101
+
102
+ #### Speeds, Sizes, Times [optional]
103
+
104
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
105
+
106
+ [More Information Needed]
107
+
108
+ ## Evaluation
109
+
110
+ <!-- This section describes the evaluation protocols and provides the results. -->
111
+
112
+ ### Testing Data, Factors & Metrics
113
+
114
+ #### Testing Data
115
+
116
+ <!-- This should link to a Dataset Card if possible. -->
117
+
118
+ [More Information Needed]
119
+
120
+ #### Factors
121
+
122
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
123
+
124
+ [More Information Needed]
125
+
126
+ #### Metrics
127
+
128
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
129
+
130
+ [More Information Needed]
131
+
132
+ ### Results
133
+
134
+ [More Information Needed]
135
+
136
+ #### Summary
137
+
138
+
139
+
140
+ ## Model Examination [optional]
141
+
142
+ <!-- Relevant interpretability work for the model goes here -->
143
+
144
+ [More Information Needed]
145
+
146
+ ## Environmental Impact
147
+
148
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
149
+
150
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
151
+
152
+ - **Hardware Type:** [More Information Needed]
153
+ - **Hours used:** [More Information Needed]
154
+ - **Cloud Provider:** [More Information Needed]
155
+ - **Compute Region:** [More Information Needed]
156
+ - **Carbon Emitted:** [More Information Needed]
157
+
158
+ ## Technical Specifications [optional]
159
+
160
+ ### Model Architecture and Objective
161
+
162
+ [More Information Needed]
163
+
164
+ ### Compute Infrastructure
165
+
166
+ [More Information Needed]
167
+
168
+ #### Hardware
169
+
170
+ [More Information Needed]
171
+
172
+ #### Software
173
+
174
+ [More Information Needed]
175
+
176
+ ## Citation [optional]
177
+
178
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
179
+
180
+ **BibTeX:**
181
+
182
+ [More Information Needed]
183
+
184
+ **APA:**
185
+
186
+ [More Information Needed]
187
+
188
+ ## Glossary [optional]
189
+
190
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
191
+
192
+ [More Information Needed]
193
+
194
+ ## More Information [optional]
195
+
196
+ [More Information Needed]
197
+
198
+ ## Model Card Authors [optional]
199
+
200
+ [More Information Needed]
201
+
202
+ ## Model Card Contact
203
+
204
+ [More Information Needed]
205
+ ### Framework versions
206
+
207
+ - PEFT 0.17.1
qwen3-150m-lora-finetuned-antonyms/checkpoint-4200/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "c:\\Users\\vsai2\\Documents\\LAMA\\training\\qwen3-150m-multilingual-checkpoints\\checkpoint-26000",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 32,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.1,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 16,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "v_proj",
29
+ "q_proj",
30
+ "o_proj",
31
+ "k_proj"
32
+ ],
33
+ "target_parameters": null,
34
+ "task_type": "CAUSAL_LM",
35
+ "trainable_token_indices": null,
36
+ "use_dora": false,
37
+ "use_qalora": false,
38
+ "use_rslora": false
39
+ }
qwen3-150m-lora-finetuned-antonyms/checkpoint-4200/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc6d70ffbda4cefb54d9747218b65bc3d2a8d4695f8ab8206e08bf0d6fa061e6
3
+ size 7090536
qwen3-150m-lora-finetuned-antonyms/checkpoint-4200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:888aeae7a648bfea0613788b73882d9936bf0a85dd21badd638f36057524f6ed
3
+ size 14236666
qwen3-150m-lora-finetuned-antonyms/checkpoint-4200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6742e9aedbb18cd57e77c6a370ac184036662ffd5d7d8f51377ec9f414a9a705
3
+ size 14244
qwen3-150m-lora-finetuned-antonyms/checkpoint-4200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12fc30ca2c48d51e9e7e17fb238e1615ff4b754d3a52eb27c6eb0589d54d8fc4
3
+ size 1064
qwen3-150m-lora-finetuned-antonyms/checkpoint-4200/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<pad>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
qwen3-150m-lora-finetuned-antonyms/checkpoint-4200/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff