nRuaif commited on
Commit
08ba0f0
·
1 Parent(s): 10055d4

Upload folder using huggingface_hub

Browse files
checkpoint-10/README.md ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - load_in_8bit: False
10
+ - load_in_4bit: True
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: nf4
16
+ - bnb_4bit_use_double_quant: True
17
+ - bnb_4bit_compute_dtype: bfloat16
18
+ ### Framework versions
19
+
20
+
21
+ - PEFT 0.6.0.dev0
checkpoint-10/adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "NousResearch/Llama-2-13b-hf",
4
+ "bias": "none",
5
+ "fan_in_fan_out": null,
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": 0.05,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 4,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "up_proj",
18
+ "v_proj",
19
+ "gate_proj",
20
+ "k_proj",
21
+ "q_proj",
22
+ "o_proj",
23
+ "down_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM"
26
+ }
checkpoint-10/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67fd4a3a3418bbc0ed846603065e64b8116be3bfc992eb04d83bbdfcebefa231
3
+ size 31494413
checkpoint-10/adapter_model/README.md ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - load_in_8bit: False
10
+ - load_in_4bit: True
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: nf4
16
+ - bnb_4bit_use_double_quant: True
17
+ - bnb_4bit_compute_dtype: bfloat16
18
+ ### Framework versions
19
+
20
+
21
+ - PEFT 0.6.0.dev0
checkpoint-10/adapter_model/adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "NousResearch/Llama-2-13b-hf",
4
+ "bias": "none",
5
+ "fan_in_fan_out": null,
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": 0.05,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 4,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "up_proj",
18
+ "v_proj",
19
+ "gate_proj",
20
+ "k_proj",
21
+ "q_proj",
22
+ "o_proj",
23
+ "down_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM"
26
+ }
checkpoint-10/adapter_model/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67fd4a3a3418bbc0ed846603065e64b8116be3bfc992eb04d83bbdfcebefa231
3
+ size 31494413
checkpoint-10/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74d55409badc9e2d12f64f46f090ffaa0fcded60f955f648fbd1b5c02de722a7
3
+ size 125504317
checkpoint-10/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a11170ab4940450fb911eaec901717176e7513c69be23bd75c6f2b5954750bb
3
+ size 14575
checkpoint-10/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3f23bc239cbe3e7a4f862f2448a71aa49fc3b361c6c5866cc00242a779c0be4
3
+ size 627
checkpoint-10/trainer_state.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.22955523672883787,
5
+ "eval_steps": 500,
6
+ "global_step": 10,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02,
13
+ "learning_rate": 5e-05,
14
+ "loss": 1.7667,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.05,
19
+ "learning_rate": 5e-05,
20
+ "loss": 1.7274,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.07,
25
+ "learning_rate": 5e-05,
26
+ "loss": 1.656,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.09,
31
+ "learning_rate": 5e-05,
32
+ "loss": 1.7964,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.11,
37
+ "learning_rate": 5e-05,
38
+ "loss": 1.6153,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.14,
43
+ "learning_rate": 5e-05,
44
+ "loss": 1.7931,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.16,
49
+ "learning_rate": 5e-05,
50
+ "loss": 1.7548,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.18,
55
+ "learning_rate": 5e-05,
56
+ "loss": 1.7054,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.21,
61
+ "learning_rate": 5e-05,
62
+ "loss": 1.7311,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.23,
67
+ "learning_rate": 5e-05,
68
+ "loss": 1.6827,
69
+ "step": 10
70
+ }
71
+ ],
72
+ "logging_steps": 1,
73
+ "max_steps": 129,
74
+ "num_train_epochs": 3,
75
+ "save_steps": 10,
76
+ "total_flos": 4.37897752215552e+16,
77
+ "trial_name": null,
78
+ "trial_params": null
79
+ }
checkpoint-10/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:056b2d35a8edd0b4c4e1fa596b4bfb9c414a316aae917663d8deeb089d445a4e
3
+ size 4219
checkpoint-20/README.md ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - load_in_8bit: False
10
+ - load_in_4bit: True
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: nf4
16
+ - bnb_4bit_use_double_quant: True
17
+ - bnb_4bit_compute_dtype: bfloat16
18
+ ### Framework versions
19
+
20
+
21
+ - PEFT 0.6.0.dev0
checkpoint-20/adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "NousResearch/Llama-2-13b-hf",
4
+ "bias": "none",
5
+ "fan_in_fan_out": null,
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": 0.05,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 4,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "up_proj",
18
+ "v_proj",
19
+ "gate_proj",
20
+ "k_proj",
21
+ "q_proj",
22
+ "o_proj",
23
+ "down_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM"
26
+ }
checkpoint-20/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b6da7406b42629dec08fbd4d226f0436a51dc43ae4efe506e97b0ea4a9e8488
3
+ size 31494413
checkpoint-20/adapter_model/README.md ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - load_in_8bit: False
10
+ - load_in_4bit: True
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: nf4
16
+ - bnb_4bit_use_double_quant: True
17
+ - bnb_4bit_compute_dtype: bfloat16
18
+ ### Framework versions
19
+
20
+
21
+ - PEFT 0.6.0.dev0
checkpoint-20/adapter_model/adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "NousResearch/Llama-2-13b-hf",
4
+ "bias": "none",
5
+ "fan_in_fan_out": null,
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": 0.05,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 4,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "up_proj",
18
+ "v_proj",
19
+ "gate_proj",
20
+ "k_proj",
21
+ "q_proj",
22
+ "o_proj",
23
+ "down_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM"
26
+ }
checkpoint-20/adapter_model/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b6da7406b42629dec08fbd4d226f0436a51dc43ae4efe506e97b0ea4a9e8488
3
+ size 31494413
checkpoint-20/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71a08457863ca2cb623ca115f24e2b74d5a686747d1aec9706089c364cb19e41
3
+ size 125504317
checkpoint-20/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f834ad020c1324fb2c966581df1ae2046dc51e5a909aa761e65b75922dd2efb2
3
+ size 14575
checkpoint-20/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e64bd2871a807ae2da11c5073d611b4d4223c336499ef21e9e856aaa448a1a35
3
+ size 627
checkpoint-20/trainer_state.json ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.45911047345767575,
5
+ "eval_steps": 500,
6
+ "global_step": 20,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02,
13
+ "learning_rate": 5e-05,
14
+ "loss": 1.7667,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.05,
19
+ "learning_rate": 5e-05,
20
+ "loss": 1.7274,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.07,
25
+ "learning_rate": 5e-05,
26
+ "loss": 1.656,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.09,
31
+ "learning_rate": 5e-05,
32
+ "loss": 1.7964,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.11,
37
+ "learning_rate": 5e-05,
38
+ "loss": 1.6153,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.14,
43
+ "learning_rate": 5e-05,
44
+ "loss": 1.7931,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.16,
49
+ "learning_rate": 5e-05,
50
+ "loss": 1.7548,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.18,
55
+ "learning_rate": 5e-05,
56
+ "loss": 1.7054,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.21,
61
+ "learning_rate": 5e-05,
62
+ "loss": 1.7311,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.23,
67
+ "learning_rate": 5e-05,
68
+ "loss": 1.6827,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.25,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.7158,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.28,
79
+ "learning_rate": 5e-05,
80
+ "loss": 1.6599,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.3,
85
+ "learning_rate": 5e-05,
86
+ "loss": 1.6991,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.32,
91
+ "learning_rate": 5e-05,
92
+ "loss": 1.6628,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.34,
97
+ "learning_rate": 5e-05,
98
+ "loss": 1.6188,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.37,
103
+ "learning_rate": 5e-05,
104
+ "loss": 1.6868,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.39,
109
+ "learning_rate": 5e-05,
110
+ "loss": 1.6854,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.41,
115
+ "learning_rate": 5e-05,
116
+ "loss": 1.5938,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.44,
121
+ "learning_rate": 5e-05,
122
+ "loss": 1.6603,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.46,
127
+ "learning_rate": 5e-05,
128
+ "loss": 1.561,
129
+ "step": 20
130
+ }
131
+ ],
132
+ "logging_steps": 1,
133
+ "max_steps": 129,
134
+ "num_train_epochs": 3,
135
+ "save_steps": 10,
136
+ "total_flos": 8.884714919952384e+16,
137
+ "trial_name": null,
138
+ "trial_params": null
139
+ }
checkpoint-20/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:056b2d35a8edd0b4c4e1fa596b4bfb9c414a316aae917663d8deeb089d445a4e
3
+ size 4219
checkpoint-30/README.md ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - load_in_8bit: False
10
+ - load_in_4bit: True
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: nf4
16
+ - bnb_4bit_use_double_quant: True
17
+ - bnb_4bit_compute_dtype: bfloat16
18
+ ### Framework versions
19
+
20
+
21
+ - PEFT 0.6.0.dev0
checkpoint-30/adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "NousResearch/Llama-2-13b-hf",
4
+ "bias": "none",
5
+ "fan_in_fan_out": null,
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": 0.05,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 4,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "up_proj",
18
+ "v_proj",
19
+ "gate_proj",
20
+ "k_proj",
21
+ "q_proj",
22
+ "o_proj",
23
+ "down_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM"
26
+ }
checkpoint-30/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6fcc63edc1ffcda424b4eeea79da75a17e8f27a3b5534b154d7687ffd6931e1
3
+ size 31494413
checkpoint-30/adapter_model/README.md ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - load_in_8bit: False
10
+ - load_in_4bit: True
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: nf4
16
+ - bnb_4bit_use_double_quant: True
17
+ - bnb_4bit_compute_dtype: bfloat16
18
+ ### Framework versions
19
+
20
+
21
+ - PEFT 0.6.0.dev0
checkpoint-30/adapter_model/adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "NousResearch/Llama-2-13b-hf",
4
+ "bias": "none",
5
+ "fan_in_fan_out": null,
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": 0.05,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 4,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "up_proj",
18
+ "v_proj",
19
+ "gate_proj",
20
+ "k_proj",
21
+ "q_proj",
22
+ "o_proj",
23
+ "down_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM"
26
+ }
checkpoint-30/adapter_model/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6fcc63edc1ffcda424b4eeea79da75a17e8f27a3b5534b154d7687ffd6931e1
3
+ size 31494413
checkpoint-30/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d5de6d5c52c3d24089ca51dc0452c99b5461d213b610a7a1de7130b47a33c2a
3
+ size 125504317
checkpoint-30/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b63c98d5bc0c13cbc2260248b7a3f1a7a407a627d11d527ecc7f53e37782b0b9
3
+ size 14575
checkpoint-30/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:298c19c2d0215ea63da7419132c9dac6c9c75fdd531e32dfc1cb87dbb0aa8259
3
+ size 627
checkpoint-30/trainer_state.json ADDED
@@ -0,0 +1,199 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.6886657101865137,
5
+ "eval_steps": 500,
6
+ "global_step": 30,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02,
13
+ "learning_rate": 5e-05,
14
+ "loss": 1.7667,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.05,
19
+ "learning_rate": 5e-05,
20
+ "loss": 1.7274,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.07,
25
+ "learning_rate": 5e-05,
26
+ "loss": 1.656,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.09,
31
+ "learning_rate": 5e-05,
32
+ "loss": 1.7964,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.11,
37
+ "learning_rate": 5e-05,
38
+ "loss": 1.6153,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.14,
43
+ "learning_rate": 5e-05,
44
+ "loss": 1.7931,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.16,
49
+ "learning_rate": 5e-05,
50
+ "loss": 1.7548,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.18,
55
+ "learning_rate": 5e-05,
56
+ "loss": 1.7054,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.21,
61
+ "learning_rate": 5e-05,
62
+ "loss": 1.7311,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.23,
67
+ "learning_rate": 5e-05,
68
+ "loss": 1.6827,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.25,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.7158,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.28,
79
+ "learning_rate": 5e-05,
80
+ "loss": 1.6599,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.3,
85
+ "learning_rate": 5e-05,
86
+ "loss": 1.6991,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.32,
91
+ "learning_rate": 5e-05,
92
+ "loss": 1.6628,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.34,
97
+ "learning_rate": 5e-05,
98
+ "loss": 1.6188,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.37,
103
+ "learning_rate": 5e-05,
104
+ "loss": 1.6868,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.39,
109
+ "learning_rate": 5e-05,
110
+ "loss": 1.6854,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.41,
115
+ "learning_rate": 5e-05,
116
+ "loss": 1.5938,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.44,
121
+ "learning_rate": 5e-05,
122
+ "loss": 1.6603,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.46,
127
+ "learning_rate": 5e-05,
128
+ "loss": 1.561,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.48,
133
+ "learning_rate": 5e-05,
134
+ "loss": 1.6162,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.51,
139
+ "learning_rate": 5e-05,
140
+ "loss": 1.6159,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.53,
145
+ "learning_rate": 5e-05,
146
+ "loss": 1.6414,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.55,
151
+ "learning_rate": 5e-05,
152
+ "loss": 1.6915,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.57,
157
+ "learning_rate": 5e-05,
158
+ "loss": 1.6853,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.6,
163
+ "learning_rate": 5e-05,
164
+ "loss": 1.6563,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.62,
169
+ "learning_rate": 5e-05,
170
+ "loss": 1.6622,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.64,
175
+ "learning_rate": 5e-05,
176
+ "loss": 1.638,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.67,
181
+ "learning_rate": 5e-05,
182
+ "loss": 1.66,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.69,
187
+ "learning_rate": 5e-05,
188
+ "loss": 1.6565,
189
+ "step": 30
190
+ }
191
+ ],
192
+ "logging_steps": 1,
193
+ "max_steps": 129,
194
+ "num_train_epochs": 3,
195
+ "save_steps": 10,
196
+ "total_flos": 1.3296259208577024e+17,
197
+ "trial_name": null,
198
+ "trial_params": null
199
+ }
checkpoint-30/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:056b2d35a8edd0b4c4e1fa596b4bfb9c414a316aae917663d8deeb089d445a4e
3
+ size 4219