Hugging Face's logo

Technotech
/
MagicPrompt-tinystories-33M-epoch2

PEFT
TensorBoard
English
Model card Files Metrics Community
Technotech commited on
Commit
30b176a
•
1 Parent(s): fce1f0b

Initial upload

Browse files
Files changed (47) hide show
  1. README.md +18 -1
  2. adapter_config.json +21 -0
  3. adapter_model.bin +3 -0
  4. checkpoint-1140/README.md +20 -0
  5. checkpoint-1140/adapter_config.json +21 -0
  6. checkpoint-1140/adapter_model.bin +3 -0
  7. checkpoint-1140/optimizer.pt +3 -0
  8. checkpoint-1140/rng_state.pth +3 -0
  9. checkpoint-1140/scheduler.pt +3 -0
  10. checkpoint-1140/trainer_state.json +148 -0
  11. checkpoint-1140/training_args.bin +3 -0
  12. checkpoint-1170/README.md +20 -0
  13. checkpoint-1170/adapter_config.json +21 -0
  14. checkpoint-1170/adapter_model.bin +3 -0
  15. checkpoint-1170/optimizer.pt +3 -0
  16. checkpoint-1170/rng_state.pth +3 -0
  17. checkpoint-1170/scheduler.pt +3 -0
  18. checkpoint-1170/trainer_state.json +154 -0
  19. checkpoint-1170/training_args.bin +3 -0
  20. checkpoint-1200/README.md +20 -0
  21. checkpoint-1200/adapter_config.json +21 -0
  22. checkpoint-1200/adapter_model.bin +3 -0
  23. checkpoint-1200/optimizer.pt +3 -0
  24. checkpoint-1200/rng_state.pth +3 -0
  25. checkpoint-1200/scheduler.pt +3 -0
  26. checkpoint-1200/trainer_state.json +160 -0
  27. checkpoint-1200/training_args.bin +3 -0
  28. checkpoint-1230/README.md +20 -0
  29. checkpoint-1230/adapter_config.json +21 -0
  30. checkpoint-1230/adapter_model.bin +3 -0
  31. checkpoint-1230/optimizer.pt +3 -0
  32. checkpoint-1230/rng_state.pth +3 -0
  33. checkpoint-1230/scheduler.pt +3 -0
  34. checkpoint-1230/trainer_state.json +160 -0
  35. checkpoint-1230/training_args.bin +3 -0
  36. checkpoint-1260/README.md +20 -0
  37. checkpoint-1260/adapter_config.json +21 -0
  38. checkpoint-1260/adapter_model.bin +3 -0
  39. checkpoint-1260/optimizer.pt +3 -0
  40. checkpoint-1260/rng_state.pth +3 -0
  41. checkpoint-1260/scheduler.pt +3 -0
  42. checkpoint-1260/trainer_state.json +166 -0
  43. checkpoint-1260/training_args.bin +3 -0
  44. lora.zip +3 -0
  45. runs/Jul24_13-30-25_1e592cd3bef2/events.out.tfevents.1690205426.1e592cd3bef2.140.0 +3 -0
  46. runs/Jul24_13-32-17_1e592cd3bef2/events.out.tfevents.1690205538.1e592cd3bef2.185.0 +3 -0
  47. trainer_state.json +175 -0
README.md CHANGED
@@ -1,3 +1,20 @@
1
  ---
2
- license: apache-2.0
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ library_name: peft
3
  ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: fp4
15
+ - bnb_4bit_use_double_quant: False
16
+ - bnb_4bit_compute_dtype: float32
17
+ ### Framework versions
18
+
19
+
20
+ - PEFT 0.5.0.dev0
adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "models/TinyStories-33M",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 8,
11
+ "lora_dropout": 0.0,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 8,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e022fa8cdc7bc653f9644bde72f9ddcd8830487979104289ef35901753362e8d
3
+ size 399137
checkpoint-1140/README.md ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: fp4
15
+ - bnb_4bit_use_double_quant: False
16
+ - bnb_4bit_compute_dtype: float32
17
+ ### Framework versions
18
+
19
+
20
+ - PEFT 0.5.0.dev0
checkpoint-1140/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "models/TinyStories-33M",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 8,
11
+ "lora_dropout": 0.0,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 8,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
checkpoint-1140/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d909dc95705437534d125cdebe079a7e9c3e27efd8360dac47ee7e6748bc6554
3
+ size 399137
checkpoint-1140/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba7ac3e51c5e6fbcf7305df4ada2b232e6d75f391d612a0d7b929e9d18eba003
3
+ size 800441
checkpoint-1140/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1784c9e20ffdc46b706882695c2108245d7626a328b6d70a37d079ad1fbbc989
3
+ size 14575
checkpoint-1140/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fc8fd1543b451b703d9b826913159ea6331680363ef7241dd3924cf46db8a8c
3
+ size 627
checkpoint-1140/trainer_state.json ADDED
@@ -0,0 +1,148 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.78125,
5
+ "global_step": 1140,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.08,
12
+ "learning_rate": 5e-05,
13
+ "loss": 10.9274,
14
+ "step": 50
15
+ },
16
+ {
17
+ "epoch": 0.16,
18
+ "learning_rate": 0.0001,
19
+ "loss": 9.7447,
20
+ "step": 100
21
+ },
22
+ {
23
+ "epoch": 0.23,
24
+ "learning_rate": 0.0001,
25
+ "loss": 7.7718,
26
+ "step": 150
27
+ },
28
+ {
29
+ "epoch": 0.31,
30
+ "learning_rate": 0.0001,
31
+ "loss": 6.8433,
32
+ "step": 200
33
+ },
34
+ {
35
+ "epoch": 0.39,
36
+ "learning_rate": 0.0001,
37
+ "loss": 6.399,
38
+ "step": 250
39
+ },
40
+ {
41
+ "epoch": 0.47,
42
+ "learning_rate": 0.0001,
43
+ "loss": 6.1445,
44
+ "step": 300
45
+ },
46
+ {
47
+ "epoch": 0.55,
48
+ "learning_rate": 0.0001,
49
+ "loss": 5.9761,
50
+ "step": 350
51
+ },
52
+ {
53
+ "epoch": 0.62,
54
+ "learning_rate": 0.0001,
55
+ "loss": 5.8578,
56
+ "step": 400
57
+ },
58
+ {
59
+ "epoch": 0.7,
60
+ "learning_rate": 0.0001,
61
+ "loss": 5.7772,
62
+ "step": 450
63
+ },
64
+ {
65
+ "epoch": 0.78,
66
+ "learning_rate": 0.0001,
67
+ "loss": 5.7197,
68
+ "step": 500
69
+ },
70
+ {
71
+ "epoch": 0.86,
72
+ "learning_rate": 0.0001,
73
+ "loss": 5.633,
74
+ "step": 550
75
+ },
76
+ {
77
+ "epoch": 0.94,
78
+ "learning_rate": 0.0001,
79
+ "loss": 5.6076,
80
+ "step": 600
81
+ },
82
+ {
83
+ "epoch": 1.02,
84
+ "learning_rate": 0.0001,
85
+ "loss": 5.5512,
86
+ "step": 650
87
+ },
88
+ {
89
+ "epoch": 1.09,
90
+ "learning_rate": 0.0001,
91
+ "loss": 5.5049,
92
+ "step": 700
93
+ },
94
+ {
95
+ "epoch": 1.17,
96
+ "learning_rate": 0.0001,
97
+ "loss": 5.4586,
98
+ "step": 750
99
+ },
100
+ {
101
+ "epoch": 1.25,
102
+ "learning_rate": 0.0001,
103
+ "loss": 5.4495,
104
+ "step": 800
105
+ },
106
+ {
107
+ "epoch": 1.33,
108
+ "learning_rate": 0.0001,
109
+ "loss": 5.4038,
110
+ "step": 850
111
+ },
112
+ {
113
+ "epoch": 1.41,
114
+ "learning_rate": 0.0001,
115
+ "loss": 5.3907,
116
+ "step": 900
117
+ },
118
+ {
119
+ "epoch": 1.48,
120
+ "learning_rate": 0.0001,
121
+ "loss": 5.3733,
122
+ "step": 950
123
+ },
124
+ {
125
+ "epoch": 1.56,
126
+ "learning_rate": 0.0001,
127
+ "loss": 5.3187,
128
+ "step": 1000
129
+ },
130
+ {
131
+ "epoch": 1.64,
132
+ "learning_rate": 0.0001,
133
+ "loss": 5.2799,
134
+ "step": 1050
135
+ },
136
+ {
137
+ "epoch": 1.72,
138
+ "learning_rate": 0.0001,
139
+ "loss": 5.2512,
140
+ "step": 1100
141
+ }
142
+ ],
143
+ "max_steps": 1280,
144
+ "num_train_epochs": 2,
145
+ "total_flos": 1681312938983424.0,
146
+ "trial_name": null,
147
+ "trial_params": null
148
+ }
checkpoint-1140/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5f26e97f1b0119d5c7b424eb78527d3e827728609abbb61280f6b4a8e9dc581
3
+ size 3899
checkpoint-1170/README.md ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: fp4
15
+ - bnb_4bit_use_double_quant: False
16
+ - bnb_4bit_compute_dtype: float32
17
+ ### Framework versions
18
+
19
+
20
+ - PEFT 0.5.0.dev0
checkpoint-1170/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "models/TinyStories-33M",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 8,
11
+ "lora_dropout": 0.0,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 8,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
checkpoint-1170/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:592853ea8ac946a7e85959377ef59fe2976ef60dc7132b618d8d4dde51910ce1
3
+ size 399137
checkpoint-1170/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2aea12e00c50124eeb2de87ed16fea8249588387019777dde5e63d37603dca8
3
+ size 800441
checkpoint-1170/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1784c9e20ffdc46b706882695c2108245d7626a328b6d70a37d079ad1fbbc989
3
+ size 14575
checkpoint-1170/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abad2225bfa3230cf8da04adab5fb3785ca77402d7aa341a0d50b72d71c1eb17
3
+ size 627
checkpoint-1170/trainer_state.json ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.828125,
5
+ "global_step": 1170,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.08,
12
+ "learning_rate": 5e-05,
13
+ "loss": 10.9274,
14
+ "step": 50
15
+ },
16
+ {
17
+ "epoch": 0.16,
18
+ "learning_rate": 0.0001,
19
+ "loss": 9.7447,
20
+ "step": 100
21
+ },
22
+ {
23
+ "epoch": 0.23,
24
+ "learning_rate": 0.0001,
25
+ "loss": 7.7718,
26
+ "step": 150
27
+ },
28
+ {
29
+ "epoch": 0.31,
30
+ "learning_rate": 0.0001,
31
+ "loss": 6.8433,
32
+ "step": 200
33
+ },
34
+ {
35
+ "epoch": 0.39,
36
+ "learning_rate": 0.0001,
37
+ "loss": 6.399,
38
+ "step": 250
39
+ },
40
+ {
41
+ "epoch": 0.47,
42
+ "learning_rate": 0.0001,
43
+ "loss": 6.1445,
44
+ "step": 300
45
+ },
46
+ {
47
+ "epoch": 0.55,
48
+ "learning_rate": 0.0001,
49
+ "loss": 5.9761,
50
+ "step": 350
51
+ },
52
+ {
53
+ "epoch": 0.62,
54
+ "learning_rate": 0.0001,
55
+ "loss": 5.8578,
56
+ "step": 400
57
+ },
58
+ {
59
+ "epoch": 0.7,
60
+ "learning_rate": 0.0001,
61
+ "loss": 5.7772,
62
+ "step": 450
63
+ },
64
+ {
65
+ "epoch": 0.78,
66
+ "learning_rate": 0.0001,
67
+ "loss": 5.7197,
68
+ "step": 500
69
+ },
70
+ {
71
+ "epoch": 0.86,
72
+ "learning_rate": 0.0001,
73
+ "loss": 5.633,
74
+ "step": 550
75
+ },
76
+ {
77
+ "epoch": 0.94,
78
+ "learning_rate": 0.0001,
79
+ "loss": 5.6076,
80
+ "step": 600
81
+ },
82
+ {
83
+ "epoch": 1.02,
84
+ "learning_rate": 0.0001,
85
+ "loss": 5.5512,
86
+ "step": 650
87
+ },
88
+ {
89
+ "epoch": 1.09,
90
+ "learning_rate": 0.0001,
91
+ "loss": 5.5049,
92
+ "step": 700
93
+ },
94
+ {
95
+ "epoch": 1.17,
96
+ "learning_rate": 0.0001,
97
+ "loss": 5.4586,
98
+ "step": 750
99
+ },
100
+ {
101
+ "epoch": 1.25,
102
+ "learning_rate": 0.0001,
103
+ "loss": 5.4495,
104
+ "step": 800
105
+ },
106
+ {
107
+ "epoch": 1.33,
108
+ "learning_rate": 0.0001,
109
+ "loss": 5.4038,
110
+ "step": 850
111
+ },
112
+ {
113
+ "epoch": 1.41,
114
+ "learning_rate": 0.0001,
115
+ "loss": 5.3907,
116
+ "step": 900
117
+ },
118
+ {
119
+ "epoch": 1.48,
120
+ "learning_rate": 0.0001,
121
+ "loss": 5.3733,
122
+ "step": 950
123
+ },
124
+ {
125
+ "epoch": 1.56,
126
+ "learning_rate": 0.0001,
127
+ "loss": 5.3187,
128
+ "step": 1000
129
+ },
130
+ {
131
+ "epoch": 1.64,
132
+ "learning_rate": 0.0001,
133
+ "loss": 5.2799,
134
+ "step": 1050
135
+ },
136
+ {
137
+ "epoch": 1.72,
138
+ "learning_rate": 0.0001,
139
+ "loss": 5.2512,
140
+ "step": 1100
141
+ },
142
+ {
143
+ "epoch": 1.8,
144
+ "learning_rate": 0.0001,
145
+ "loss": 5.2537,
146
+ "step": 1150
147
+ }
148
+ ],
149
+ "max_steps": 1280,
150
+ "num_train_epochs": 2,
151
+ "total_flos": 1723338082123776.0,
152
+ "trial_name": null,
153
+ "trial_params": null
154
+ }
checkpoint-1170/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5f26e97f1b0119d5c7b424eb78527d3e827728609abbb61280f6b4a8e9dc581
3
+ size 3899
checkpoint-1200/README.md ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: fp4
15
+ - bnb_4bit_use_double_quant: False
16
+ - bnb_4bit_compute_dtype: float32
17
+ ### Framework versions
18
+
19
+
20
+ - PEFT 0.5.0.dev0
checkpoint-1200/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "models/TinyStories-33M",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 8,
11
+ "lora_dropout": 0.0,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 8,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
checkpoint-1200/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58b0b40537121e6640166b361636e3d6e631b7ef0fa83a37e1a7f9eab67a94f6
3
+ size 399137
checkpoint-1200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1fd36f9437e0b96215a775dc47a932460b43808f5eca8e08995b26c9c963e58
3
+ size 800441
checkpoint-1200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1784c9e20ffdc46b706882695c2108245d7626a328b6d70a37d079ad1fbbc989
3
+ size 14575
checkpoint-1200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6dd98e7cfba210fc65c065e454c54d2036e5d839020e37f887e58b9a1078c28
3
+ size 627
checkpoint-1200/trainer_state.json ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.875,
5
+ "global_step": 1200,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.08,
12
+ "learning_rate": 5e-05,
13
+ "loss": 10.9274,
14
+ "step": 50
15
+ },
16
+ {
17
+ "epoch": 0.16,
18
+ "learning_rate": 0.0001,
19
+ "loss": 9.7447,
20
+ "step": 100
21
+ },
22
+ {
23
+ "epoch": 0.23,
24
+ "learning_rate": 0.0001,
25
+ "loss": 7.7718,
26
+ "step": 150
27
+ },
28
+ {
29
+ "epoch": 0.31,
30
+ "learning_rate": 0.0001,
31
+ "loss": 6.8433,
32
+ "step": 200
33
+ },
34
+ {
35
+ "epoch": 0.39,
36
+ "learning_rate": 0.0001,
37
+ "loss": 6.399,
38
+ "step": 250
39
+ },
40
+ {
41
+ "epoch": 0.47,
42
+ "learning_rate": 0.0001,
43
+ "loss": 6.1445,
44
+ "step": 300
45
+ },
46
+ {
47
+ "epoch": 0.55,
48
+ "learning_rate": 0.0001,
49
+ "loss": 5.9761,
50
+ "step": 350
51
+ },
52
+ {
53
+ "epoch": 0.62,
54
+ "learning_rate": 0.0001,
55
+ "loss": 5.8578,
56
+ "step": 400
57
+ },
58
+ {
59
+ "epoch": 0.7,
60
+ "learning_rate": 0.0001,
61
+ "loss": 5.7772,
62
+ "step": 450
63
+ },
64
+ {
65
+ "epoch": 0.78,
66
+ "learning_rate": 0.0001,
67
+ "loss": 5.7197,
68
+ "step": 500
69
+ },
70
+ {
71
+ "epoch": 0.86,
72
+ "learning_rate": 0.0001,
73
+ "loss": 5.633,
74
+ "step": 550
75
+ },
76
+ {
77
+ "epoch": 0.94,
78
+ "learning_rate": 0.0001,
79
+ "loss": 5.6076,
80
+ "step": 600
81
+ },
82
+ {
83
+ "epoch": 1.02,
84
+ "learning_rate": 0.0001,
85
+ "loss": 5.5512,
86
+ "step": 650
87
+ },
88
+ {
89
+ "epoch": 1.09,
90
+ "learning_rate": 0.0001,
91
+ "loss": 5.5049,
92
+ "step": 700
93
+ },
94
+ {
95
+ "epoch": 1.17,
96
+ "learning_rate": 0.0001,
97
+ "loss": 5.4586,
98
+ "step": 750
99
+ },
100
+ {
101
+ "epoch": 1.25,
102
+ "learning_rate": 0.0001,
103
+ "loss": 5.4495,
104
+ "step": 800
105
+ },
106
+ {
107
+ "epoch": 1.33,
108
+ "learning_rate": 0.0001,
109
+ "loss": 5.4038,
110
+ "step": 850
111
+ },
112
+ {
113
+ "epoch": 1.41,
114
+ "learning_rate": 0.0001,
115
+ "loss": 5.3907,
116
+ "step": 900
117
+ },
118
+ {
119
+ "epoch": 1.48,
120
+ "learning_rate": 0.0001,
121
+ "loss": 5.3733,
122
+ "step": 950
123
+ },
124
+ {
125
+ "epoch": 1.56,
126
+ "learning_rate": 0.0001,
127
+ "loss": 5.3187,
128
+ "step": 1000
129
+ },
130
+ {
131
+ "epoch": 1.64,
132
+ "learning_rate": 0.0001,
133
+ "loss": 5.2799,
134
+ "step": 1050
135
+ },
136
+ {
137
+ "epoch": 1.72,
138
+ "learning_rate": 0.0001,
139
+ "loss": 5.2512,
140
+ "step": 1100
141
+ },
142
+ {
143
+ "epoch": 1.8,
144
+ "learning_rate": 0.0001,
145
+ "loss": 5.2537,
146
+ "step": 1150
147
+ },
148
+ {
149
+ "epoch": 1.88,
150
+ "learning_rate": 0.0001,
151
+ "loss": 5.2417,
152
+ "step": 1200
153
+ }
154
+ ],
155
+ "max_steps": 1280,
156
+ "num_train_epochs": 2,
157
+ "total_flos": 1768152832376832.0,
158
+ "trial_name": null,
159
+ "trial_params": null
160
+ }
checkpoint-1200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5f26e97f1b0119d5c7b424eb78527d3e827728609abbb61280f6b4a8e9dc581
3
+ size 3899
checkpoint-1230/README.md ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: fp4
15
+ - bnb_4bit_use_double_quant: False
16
+ - bnb_4bit_compute_dtype: float32
17
+ ### Framework versions
18
+
19
+
20
+ - PEFT 0.5.0.dev0
checkpoint-1230/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "models/TinyStories-33M",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 8,
11
+ "lora_dropout": 0.0,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 8,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
checkpoint-1230/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10e76dbaec80c330cbd1d5c539c14a2efd75119b6bb7103168aeb03d14dfe2a7
3
+ size 399137
checkpoint-1230/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c2738002a15d9ded5a097db304db7794321d203cc1d264ebc211e2d3ef9c9b9
3
+ size 800441
checkpoint-1230/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1784c9e20ffdc46b706882695c2108245d7626a328b6d70a37d079ad1fbbc989
3
+ size 14575
checkpoint-1230/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b42493eb50d1931817386a6a0f83ebf07686ed5ccab92ca4ff6722bcbe117645
3
+ size 627
checkpoint-1230/trainer_state.json ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.921875,
5
+ "global_step": 1230,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.08,
12
+ "learning_rate": 5e-05,
13
+ "loss": 10.9274,
14
+ "step": 50
15
+ },
16
+ {
17
+ "epoch": 0.16,
18
+ "learning_rate": 0.0001,
19
+ "loss": 9.7447,
20
+ "step": 100
21
+ },
22
+ {
23
+ "epoch": 0.23,
24
+ "learning_rate": 0.0001,
25
+ "loss": 7.7718,
26
+ "step": 150
27
+ },
28
+ {
29
+ "epoch": 0.31,
30
+ "learning_rate": 0.0001,
31
+ "loss": 6.8433,
32
+ "step": 200
33
+ },
34
+ {
35
+ "epoch": 0.39,
36
+ "learning_rate": 0.0001,
37
+ "loss": 6.399,
38
+ "step": 250
39
+ },
40
+ {
41
+ "epoch": 0.47,
42
+ "learning_rate": 0.0001,
43
+ "loss": 6.1445,
44
+ "step": 300
45
+ },
46
+ {
47
+ "epoch": 0.55,
48
+ "learning_rate": 0.0001,
49
+ "loss": 5.9761,
50
+ "step": 350
51
+ },
52
+ {
53
+ "epoch": 0.62,
54
+ "learning_rate": 0.0001,
55
+ "loss": 5.8578,
56
+ "step": 400
57
+ },
58
+ {
59
+ "epoch": 0.7,
60
+ "learning_rate": 0.0001,
61
+ "loss": 5.7772,
62
+ "step": 450
63
+ },
64
+ {
65
+ "epoch": 0.78,
66
+ "learning_rate": 0.0001,
67
+ "loss": 5.7197,
68
+ "step": 500
69
+ },
70
+ {
71
+ "epoch": 0.86,
72
+ "learning_rate": 0.0001,
73
+ "loss": 5.633,
74
+ "step": 550
75
+ },
76
+ {
77
+ "epoch": 0.94,
78
+ "learning_rate": 0.0001,
79
+ "loss": 5.6076,
80
+ "step": 600
81
+ },
82
+ {
83
+ "epoch": 1.02,
84
+ "learning_rate": 0.0001,
85
+ "loss": 5.5512,
86
+ "step": 650
87
+ },
88
+ {
89
+ "epoch": 1.09,
90
+ "learning_rate": 0.0001,
91
+ "loss": 5.5049,
92
+ "step": 700
93
+ },
94
+ {
95
+ "epoch": 1.17,
96
+ "learning_rate": 0.0001,
97
+ "loss": 5.4586,
98
+ "step": 750
99
+ },
100
+ {
101
+ "epoch": 1.25,
102
+ "learning_rate": 0.0001,
103
+ "loss": 5.4495,
104
+ "step": 800
105
+ },
106
+ {
107
+ "epoch": 1.33,
108
+ "learning_rate": 0.0001,
109
+ "loss": 5.4038,
110
+ "step": 850
111
+ },
112
+ {
113
+ "epoch": 1.41,
114
+ "learning_rate": 0.0001,
115
+ "loss": 5.3907,
116
+ "step": 900
117
+ },
118
+ {
119
+ "epoch": 1.48,
120
+ "learning_rate": 0.0001,
121
+ "loss": 5.3733,
122
+ "step": 950
123
+ },
124
+ {
125
+ "epoch": 1.56,
126
+ "learning_rate": 0.0001,
127
+ "loss": 5.3187,
128
+ "step": 1000
129
+ },
130
+ {
131
+ "epoch": 1.64,
132
+ "learning_rate": 0.0001,
133
+ "loss": 5.2799,
134
+ "step": 1050
135
+ },
136
+ {
137
+ "epoch": 1.72,
138
+ "learning_rate": 0.0001,
139
+ "loss": 5.2512,
140
+ "step": 1100
141
+ },
142
+ {
143
+ "epoch": 1.8,
144
+ "learning_rate": 0.0001,
145
+ "loss": 5.2537,
146
+ "step": 1150
147
+ },
148
+ {
149
+ "epoch": 1.88,
150
+ "learning_rate": 0.0001,
151
+ "loss": 5.2417,
152
+ "step": 1200
153
+ }
154
+ ],
155
+ "max_steps": 1280,
156
+ "num_train_epochs": 2,
157
+ "total_flos": 1812383328632832.0,
158
+ "trial_name": null,
159
+ "trial_params": null
160
+ }
checkpoint-1230/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5f26e97f1b0119d5c7b424eb78527d3e827728609abbb61280f6b4a8e9dc581
3
+ size 3899
checkpoint-1260/README.md ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: fp4
15
+ - bnb_4bit_use_double_quant: False
16
+ - bnb_4bit_compute_dtype: float32
17
+ ### Framework versions
18
+
19
+
20
+ - PEFT 0.5.0.dev0
checkpoint-1260/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "models/TinyStories-33M",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 8,
11
+ "lora_dropout": 0.0,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 8,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
checkpoint-1260/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a487dc0da239751d16277cba92a93fb3f2028c7d08d27a0931900d6886c348b4
3
+ size 399137
checkpoint-1260/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd1519dc76fe53fe97cdf6d2db8299f39b13820a42e3d1443324add2b66aa428
3
+ size 800441
checkpoint-1260/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1784c9e20ffdc46b706882695c2108245d7626a328b6d70a37d079ad1fbbc989
3
+ size 14575
checkpoint-1260/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:547e051ad964f463adf073ebbf9fed974490d2a4f6e2855e0550398319cc30b1
3
+ size 627
checkpoint-1260/trainer_state.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.96875,
5
+ "global_step": 1260,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.08,
12
+ "learning_rate": 5e-05,
13
+ "loss": 10.9274,
14
+ "step": 50
15
+ },
16
+ {
17
+ "epoch": 0.16,
18
+ "learning_rate": 0.0001,
19
+ "loss": 9.7447,
20
+ "step": 100
21
+ },
22
+ {
23
+ "epoch": 0.23,
24
+ "learning_rate": 0.0001,
25
+ "loss": 7.7718,
26
+ "step": 150
27
+ },
28
+ {
29
+ "epoch": 0.31,
30
+ "learning_rate": 0.0001,
31
+ "loss": 6.8433,
32
+ "step": 200
33
+ },
34
+ {
35
+ "epoch": 0.39,
36
+ "learning_rate": 0.0001,
37
+ "loss": 6.399,
38
+ "step": 250
39
+ },
40
+ {
41
+ "epoch": 0.47,
42
+ "learning_rate": 0.0001,
43
+ "loss": 6.1445,
44
+ "step": 300
45
+ },
46
+ {
47
+ "epoch": 0.55,
48
+ "learning_rate": 0.0001,
49
+ "loss": 5.9761,
50
+ "step": 350
51
+ },
52
+ {
53
+ "epoch": 0.62,
54
+ "learning_rate": 0.0001,
55
+ "loss": 5.8578,
56
+ "step": 400
57
+ },
58
+ {
59
+ "epoch": 0.7,
60
+ "learning_rate": 0.0001,
61
+ "loss": 5.7772,
62
+ "step": 450
63
+ },
64
+ {
65
+ "epoch": 0.78,
66
+ "learning_rate": 0.0001,
67
+ "loss": 5.7197,
68
+ "step": 500
69
+ },
70
+ {
71
+ "epoch": 0.86,
72
+ "learning_rate": 0.0001,
73
+ "loss": 5.633,
74
+ "step": 550
75
+ },
76
+ {
77
+ "epoch": 0.94,
78
+ "learning_rate": 0.0001,
79
+ "loss": 5.6076,
80
+ "step": 600
81
+ },
82
+ {
83
+ "epoch": 1.02,
84
+ "learning_rate": 0.0001,
85
+ "loss": 5.5512,
86
+ "step": 650
87
+ },
88
+ {
89
+ "epoch": 1.09,
90
+ "learning_rate": 0.0001,
91
+ "loss": 5.5049,
92
+ "step": 700
93
+ },
94
+ {
95
+ "epoch": 1.17,
96
+ "learning_rate": 0.0001,
97
+ "loss": 5.4586,
98
+ "step": 750
99
+ },
100
+ {
101
+ "epoch": 1.25,
102
+ "learning_rate": 0.0001,
103
+ "loss": 5.4495,
104
+ "step": 800
105
+ },
106
+ {
107
+ "epoch": 1.33,
108
+ "learning_rate": 0.0001,
109
+ "loss": 5.4038,
110
+ "step": 850
111
+ },
112
+ {
113
+ "epoch": 1.41,
114
+ "learning_rate": 0.0001,
115
+ "loss": 5.3907,
116
+ "step": 900
117
+ },
118
+ {
119
+ "epoch": 1.48,
120
+ "learning_rate": 0.0001,
121
+ "loss": 5.3733,
122
+ "step": 950
123
+ },
124
+ {
125
+ "epoch": 1.56,
126
+ "learning_rate": 0.0001,
127
+ "loss": 5.3187,
128
+ "step": 1000
129
+ },
130
+ {
131
+ "epoch": 1.64,
132
+ "learning_rate": 0.0001,
133
+ "loss": 5.2799,
134
+ "step": 1050
135
+ },
136
+ {
137
+ "epoch": 1.72,
138
+ "learning_rate": 0.0001,
139
+ "loss": 5.2512,
140
+ "step": 1100
141
+ },
142
+ {
143
+ "epoch": 1.8,
144
+ "learning_rate": 0.0001,
145
+ "loss": 5.2537,
146
+ "step": 1150
147
+ },
148
+ {
149
+ "epoch": 1.88,
150
+ "learning_rate": 0.0001,
151
+ "loss": 5.2417,
152
+ "step": 1200
153
+ },
154
+ {
155
+ "epoch": 1.95,
156
+ "learning_rate": 0.0001,
157
+ "loss": 5.1957,
158
+ "step": 1250
159
+ }
160
+ ],
161
+ "max_steps": 1280,
162
+ "num_train_epochs": 2,
163
+ "total_flos": 1859633842028544.0,
164
+ "trial_name": null,
165
+ "trial_params": null
166
+ }
checkpoint-1260/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5f26e97f1b0119d5c7b424eb78527d3e827728609abbb61280f6b4a8e9dc581
3
+ size 3899
lora.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fbdd529110ebd5ef2054df4af9cbec5db7c8724dac5f41cc820137fee6b8f4d
3
+ size 479
runs/Jul24_13-30-25_1e592cd3bef2/events.out.tfevents.1690205426.1e592cd3bef2.140.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:151193b573ea44f25e6889f5aa4acdee8aec38d61cab1051abe4811b11823e8c
3
+ size 4849
runs/Jul24_13-32-17_1e592cd3bef2/events.out.tfevents.1690205538.1e592cd3bef2.185.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d18413cdd8455be5e8f531f3012dfa7791858b895381fa1a0f4911db2435aa95
3
+ size 8969
trainer_state.json ADDED
@@ -0,0 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "global_step": 1280,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.08,
12
+ "learning_rate": 5e-05,
13
+ "loss": 10.9274,
14
+ "step": 50
15
+ },
16
+ {
17
+ "epoch": 0.16,
18
+ "learning_rate": 0.0001,
19
+ "loss": 9.7447,
20
+ "step": 100
21
+ },
22
+ {
23
+ "epoch": 0.23,
24
+ "learning_rate": 0.0001,
25
+ "loss": 7.7718,
26
+ "step": 150
27
+ },
28
+ {
29
+ "epoch": 0.31,
30
+ "learning_rate": 0.0001,
31
+ "loss": 6.8433,
32
+ "step": 200
33
+ },
34
+ {
35
+ "epoch": 0.39,
36
+ "learning_rate": 0.0001,
37
+ "loss": 6.399,
38
+ "step": 250
39
+ },
40
+ {
41
+ "epoch": 0.47,
42
+ "learning_rate": 0.0001,
43
+ "loss": 6.1445,
44
+ "step": 300
45
+ },
46
+ {
47
+ "epoch": 0.55,
48
+ "learning_rate": 0.0001,
49
+ "loss": 5.9761,
50
+ "step": 350
51
+ },
52
+ {
53
+ "epoch": 0.62,
54
+ "learning_rate": 0.0001,
55
+ "loss": 5.8578,
56
+ "step": 400
57
+ },
58
+ {
59
+ "epoch": 0.7,
60
+ "learning_rate": 0.0001,
61
+ "loss": 5.7772,
62
+ "step": 450
63
+ },
64
+ {
65
+ "epoch": 0.78,
66
+ "learning_rate": 0.0001,
67
+ "loss": 5.7197,
68
+ "step": 500
69
+ },
70
+ {
71
+ "epoch": 0.86,
72
+ "learning_rate": 0.0001,
73
+ "loss": 5.633,
74
+ "step": 550
75
+ },
76
+ {
77
+ "epoch": 0.94,
78
+ "learning_rate": 0.0001,
79
+ "loss": 5.6076,
80
+ "step": 600
81
+ },
82
+ {
83
+ "epoch": 1.02,
84
+ "learning_rate": 0.0001,
85
+ "loss": 5.5512,
86
+ "step": 650
87
+ },
88
+ {
89
+ "epoch": 1.09,
90
+ "learning_rate": 0.0001,
91
+ "loss": 5.5049,
92
+ "step": 700
93
+ },
94
+ {
95
+ "epoch": 1.17,
96
+ "learning_rate": 0.0001,
97
+ "loss": 5.4586,
98
+ "step": 750
99
+ },
100
+ {
101
+ "epoch": 1.25,
102
+ "learning_rate": 0.0001,
103
+ "loss": 5.4495,
104
+ "step": 800
105
+ },
106
+ {
107
+ "epoch": 1.33,
108
+ "learning_rate": 0.0001,
109
+ "loss": 5.4038,
110
+ "step": 850
111
+ },
112
+ {
113
+ "epoch": 1.41,
114
+ "learning_rate": 0.0001,
115
+ "loss": 5.3907,
116
+ "step": 900
117
+ },
118
+ {
119
+ "epoch": 1.48,
120
+ "learning_rate": 0.0001,
121
+ "loss": 5.3733,
122
+ "step": 950
123
+ },
124
+ {
125
+ "epoch": 1.56,
126
+ "learning_rate": 0.0001,
127
+ "loss": 5.3187,
128
+ "step": 1000
129
+ },
130
+ {
131
+ "epoch": 1.64,
132
+ "learning_rate": 0.0001,
133
+ "loss": 5.2799,
134
+ "step": 1050
135
+ },
136
+ {
137
+ "epoch": 1.72,
138
+ "learning_rate": 0.0001,
139
+ "loss": 5.2512,
140
+ "step": 1100
141
+ },
142
+ {
143
+ "epoch": 1.8,
144
+ "learning_rate": 0.0001,
145
+ "loss": 5.2537,
146
+ "step": 1150
147
+ },
148
+ {
149
+ "epoch": 1.88,
150
+ "learning_rate": 0.0001,
151
+ "loss": 5.2417,
152
+ "step": 1200
153
+ },
154
+ {
155
+ "epoch": 1.95,
156
+ "learning_rate": 0.0001,
157
+ "loss": 5.1957,
158
+ "step": 1250
159
+ },
160
+ {
161
+ "epoch": 2.0,
162
+ "step": 1280,
163
+ "total_flos": 1889639433529344.0,
164
+ "train_loss": 6.061862027645111,
165
+ "train_runtime": 2497.1163,
166
+ "train_samples_per_second": 65.604,
167
+ "train_steps_per_second": 0.513
168
+ }
169
+ ],
170
+ "max_steps": 1280,
171
+ "num_train_epochs": 2,
172
+ "total_flos": 1889639433529344.0,
173
+ "trial_name": null,
174
+ "trial_params": null
175
+ }