Upload folder using huggingface_hub

#4
by CreatorPhan - opened
This view is limited to 50 files because it contains too many changes.  See the raw diff here.
Files changed (50) hide show
  1. adapter_model.bin +1 -1
  2. checkpoint-100/README.md +138 -0
  3. checkpoint-100/adapter_config.json +25 -0
  4. checkpoint-100/adapter_model.bin +3 -0
  5. checkpoint-100/optimizer.pt +3 -0
  6. checkpoint-100/rng_state.pth +3 -0
  7. checkpoint-100/scheduler.pt +3 -0
  8. checkpoint-100/special_tokens_map.json +6 -0
  9. checkpoint-100/tokenizer.json +3 -0
  10. checkpoint-100/tokenizer_config.json +10 -0
  11. checkpoint-100/trainer_state.json +619 -0
  12. checkpoint-100/training_args.bin +3 -0
  13. checkpoint-200/README.md +60 -0
  14. checkpoint-200/adapter_config.json +25 -0
  15. checkpoint-200/adapter_model.bin +3 -0
  16. checkpoint-200/optimizer.pt +3 -0
  17. checkpoint-200/rng_state.pth +3 -0
  18. checkpoint-200/scheduler.pt +3 -0
  19. checkpoint-200/special_tokens_map.json +6 -0
  20. checkpoint-200/tokenizer.json +3 -0
  21. checkpoint-200/tokenizer_config.json +10 -0
  22. checkpoint-200/trainer_state.json +1219 -0
  23. checkpoint-200/training_args.bin +3 -0
  24. checkpoint-300/README.md +60 -0
  25. checkpoint-300/adapter_config.json +25 -0
  26. checkpoint-300/adapter_model.bin +3 -0
  27. checkpoint-300/optimizer.pt +3 -0
  28. checkpoint-300/rng_state.pth +3 -0
  29. checkpoint-300/scheduler.pt +3 -0
  30. checkpoint-300/special_tokens_map.json +6 -0
  31. checkpoint-300/tokenizer.json +3 -0
  32. checkpoint-300/tokenizer_config.json +10 -0
  33. checkpoint-300/trainer_state.json +1819 -0
  34. checkpoint-300/training_args.bin +3 -0
  35. checkpoint-400/README.md +60 -0
  36. checkpoint-400/adapter_config.json +25 -0
  37. checkpoint-400/adapter_model.bin +3 -0
  38. checkpoint-400/optimizer.pt +3 -0
  39. checkpoint-400/rng_state.pth +3 -0
  40. checkpoint-400/scheduler.pt +3 -0
  41. checkpoint-400/special_tokens_map.json +6 -0
  42. checkpoint-400/tokenizer.json +3 -0
  43. checkpoint-400/tokenizer_config.json +10 -0
  44. checkpoint-400/trainer_state.json +2419 -0
  45. checkpoint-400/training_args.bin +3 -0
  46. checkpoint-500/README.md +60 -0
  47. checkpoint-500/adapter_config.json +25 -0
  48. checkpoint-500/adapter_model.bin +3 -0
  49. checkpoint-500/optimizer.pt +3 -0
  50. checkpoint-500/rng_state.pth +3 -0
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7b701342ea311c1e25f0f6953505f048df3f56027dc5c764b95df4491bfde1c
3
  size 39409357
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22fbdcaf7857de1b74e03d99a156e9d6d448734b321467b134a7651acfe0c5fa
3
  size 39409357
checkpoint-100/README.md ADDED
@@ -0,0 +1,138 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: True
10
+ - load_in_4bit: False
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: fp4
16
+ - bnb_4bit_use_double_quant: False
17
+ - bnb_4bit_compute_dtype: float32
18
+
19
+ The following `bitsandbytes` quantization config was used during training:
20
+ - quant_method: bitsandbytes
21
+ - load_in_8bit: True
22
+ - load_in_4bit: False
23
+ - llm_int8_threshold: 6.0
24
+ - llm_int8_skip_modules: None
25
+ - llm_int8_enable_fp32_cpu_offload: False
26
+ - llm_int8_has_fp16_weight: False
27
+ - bnb_4bit_quant_type: fp4
28
+ - bnb_4bit_use_double_quant: False
29
+ - bnb_4bit_compute_dtype: float32
30
+
31
+ The following `bitsandbytes` quantization config was used during training:
32
+ - quant_method: bitsandbytes
33
+ - load_in_8bit: True
34
+ - load_in_4bit: False
35
+ - llm_int8_threshold: 6.0
36
+ - llm_int8_skip_modules: None
37
+ - llm_int8_enable_fp32_cpu_offload: False
38
+ - llm_int8_has_fp16_weight: False
39
+ - bnb_4bit_quant_type: fp4
40
+ - bnb_4bit_use_double_quant: False
41
+ - bnb_4bit_compute_dtype: float32
42
+
43
+ The following `bitsandbytes` quantization config was used during training:
44
+ - quant_method: bitsandbytes
45
+ - load_in_8bit: True
46
+ - load_in_4bit: False
47
+ - llm_int8_threshold: 6.0
48
+ - llm_int8_skip_modules: None
49
+ - llm_int8_enable_fp32_cpu_offload: False
50
+ - llm_int8_has_fp16_weight: False
51
+ - bnb_4bit_quant_type: fp4
52
+ - bnb_4bit_use_double_quant: False
53
+ - bnb_4bit_compute_dtype: float32
54
+
55
+ The following `bitsandbytes` quantization config was used during training:
56
+ - quant_method: bitsandbytes
57
+ - load_in_8bit: True
58
+ - load_in_4bit: False
59
+ - llm_int8_threshold: 6.0
60
+ - llm_int8_skip_modules: None
61
+ - llm_int8_enable_fp32_cpu_offload: False
62
+ - llm_int8_has_fp16_weight: False
63
+ - bnb_4bit_quant_type: fp4
64
+ - bnb_4bit_use_double_quant: False
65
+ - bnb_4bit_compute_dtype: float32
66
+
67
+ The following `bitsandbytes` quantization config was used during training:
68
+ - quant_method: bitsandbytes
69
+ - load_in_8bit: True
70
+ - load_in_4bit: False
71
+ - llm_int8_threshold: 6.0
72
+ - llm_int8_skip_modules: None
73
+ - llm_int8_enable_fp32_cpu_offload: False
74
+ - llm_int8_has_fp16_weight: False
75
+ - bnb_4bit_quant_type: fp4
76
+ - bnb_4bit_use_double_quant: False
77
+ - bnb_4bit_compute_dtype: float32
78
+
79
+ The following `bitsandbytes` quantization config was used during training:
80
+ - quant_method: bitsandbytes
81
+ - load_in_8bit: True
82
+ - load_in_4bit: False
83
+ - llm_int8_threshold: 6.0
84
+ - llm_int8_skip_modules: None
85
+ - llm_int8_enable_fp32_cpu_offload: False
86
+ - llm_int8_has_fp16_weight: False
87
+ - bnb_4bit_quant_type: fp4
88
+ - bnb_4bit_use_double_quant: False
89
+ - bnb_4bit_compute_dtype: float32
90
+
91
+ The following `bitsandbytes` quantization config was used during training:
92
+ - quant_method: bitsandbytes
93
+ - load_in_8bit: True
94
+ - load_in_4bit: False
95
+ - llm_int8_threshold: 6.0
96
+ - llm_int8_skip_modules: None
97
+ - llm_int8_enable_fp32_cpu_offload: False
98
+ - llm_int8_has_fp16_weight: False
99
+ - bnb_4bit_quant_type: fp4
100
+ - bnb_4bit_use_double_quant: False
101
+ - bnb_4bit_compute_dtype: float32
102
+
103
+ The following `bitsandbytes` quantization config was used during training:
104
+ - quant_method: bitsandbytes
105
+ - load_in_8bit: True
106
+ - load_in_4bit: False
107
+ - llm_int8_threshold: 6.0
108
+ - llm_int8_skip_modules: None
109
+ - llm_int8_enable_fp32_cpu_offload: False
110
+ - llm_int8_has_fp16_weight: False
111
+ - bnb_4bit_quant_type: fp4
112
+ - bnb_4bit_use_double_quant: False
113
+ - bnb_4bit_compute_dtype: float32
114
+
115
+ The following `bitsandbytes` quantization config was used during training:
116
+ - quant_method: bitsandbytes
117
+ - load_in_8bit: True
118
+ - load_in_4bit: False
119
+ - llm_int8_threshold: 6.0
120
+ - llm_int8_skip_modules: None
121
+ - llm_int8_enable_fp32_cpu_offload: False
122
+ - llm_int8_has_fp16_weight: False
123
+ - bnb_4bit_quant_type: fp4
124
+ - bnb_4bit_use_double_quant: False
125
+ - bnb_4bit_compute_dtype: float32
126
+ ### Framework versions
127
+
128
+ - PEFT 0.6.0.dev0
129
+ - PEFT 0.6.0.dev0
130
+ - PEFT 0.6.0.dev0
131
+ - PEFT 0.6.0.dev0
132
+ - PEFT 0.6.0.dev0
133
+ - PEFT 0.6.0.dev0
134
+ - PEFT 0.6.0.dev0
135
+ - PEFT 0.6.0.dev0
136
+ - PEFT 0.6.0.dev0
137
+
138
+ - PEFT 0.6.0.dev0
checkpoint-100/adapter_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "bigscience/bloomz-3b",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "lora_alpha": 16,
12
+ "lora_dropout": 0.0,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 8,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "dense_4h_to_h",
20
+ "dense",
21
+ "dense_h_to_4h",
22
+ "query_key_value"
23
+ ],
24
+ "task_type": "CAUSAL_LM"
25
+ }
checkpoint-100/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8335990cc53e924dd84264d3c9f79ff9c558d5b3398b3e77273713338fe9152d
3
+ size 39409357
checkpoint-100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bace7c30bbad8abd3be9019a0d69fc2cab14aeca0e48fcb0e5ae051d6fdc579
3
+ size 78844421
checkpoint-100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2278a87cdf86c3f9219223c847f6b27f6b7f15b8226b617f38936e8ff2cbcde
3
+ size 14575
checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1640c3b85caa3e129cded850309149bec1a2e020090ed853140950215c11127
3
+ size 627
checkpoint-100/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
checkpoint-100/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85b00d7db4df5df2e3f01cacc3feda246002a672f3356eec7f4b04a22eb0dfbe
3
+ size 14500570
checkpoint-100/tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "<pad>",
8
+ "tokenizer_class": "BloomTokenizer",
9
+ "unk_token": "<unk>"
10
+ }
checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,619 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.5586592178770949,
5
+ "eval_steps": 500,
6
+ "global_step": 100,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 0.00019972067039106145,
14
+ "loss": 2.6443,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 0.00019944134078212292,
20
+ "loss": 2.4104,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.02,
25
+ "learning_rate": 0.00019916201117318435,
26
+ "loss": 2.4975,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.02,
31
+ "learning_rate": 0.00019888268156424582,
32
+ "loss": 2.3513,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.03,
37
+ "learning_rate": 0.0001986033519553073,
38
+ "loss": 2.4274,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.03,
43
+ "learning_rate": 0.00019832402234636873,
44
+ "loss": 2.3628,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.04,
49
+ "learning_rate": 0.0001980446927374302,
50
+ "loss": 2.3567,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.04,
55
+ "learning_rate": 0.00019776536312849163,
56
+ "loss": 2.4121,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.05,
61
+ "learning_rate": 0.00019748603351955307,
62
+ "loss": 2.4033,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.06,
67
+ "learning_rate": 0.00019720670391061454,
68
+ "loss": 2.2805,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.06,
73
+ "learning_rate": 0.00019692737430167598,
74
+ "loss": 2.2639,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.07,
79
+ "learning_rate": 0.00019664804469273744,
80
+ "loss": 2.2724,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.07,
85
+ "learning_rate": 0.00019636871508379888,
86
+ "loss": 2.332,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.08,
91
+ "learning_rate": 0.00019608938547486035,
92
+ "loss": 2.2261,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.08,
97
+ "learning_rate": 0.00019581005586592182,
98
+ "loss": 2.2208,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.09,
103
+ "learning_rate": 0.00019553072625698326,
104
+ "loss": 2.3351,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.09,
109
+ "learning_rate": 0.0001952513966480447,
110
+ "loss": 2.2475,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.1,
115
+ "learning_rate": 0.00019497206703910616,
116
+ "loss": 2.3283,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.11,
121
+ "learning_rate": 0.0001946927374301676,
122
+ "loss": 2.1346,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.11,
127
+ "learning_rate": 0.00019441340782122907,
128
+ "loss": 2.131,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.12,
133
+ "learning_rate": 0.0001941340782122905,
134
+ "loss": 2.1718,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.12,
139
+ "learning_rate": 0.00019385474860335195,
140
+ "loss": 2.2446,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.13,
145
+ "learning_rate": 0.0001935754189944134,
146
+ "loss": 2.306,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.13,
151
+ "learning_rate": 0.00019329608938547488,
152
+ "loss": 2.1908,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.14,
157
+ "learning_rate": 0.00019301675977653632,
158
+ "loss": 2.2844,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.15,
163
+ "learning_rate": 0.00019273743016759779,
164
+ "loss": 2.2235,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.15,
169
+ "learning_rate": 0.00019245810055865922,
170
+ "loss": 2.1842,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.16,
175
+ "learning_rate": 0.00019217877094972066,
176
+ "loss": 2.2675,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.16,
181
+ "learning_rate": 0.00019189944134078213,
182
+ "loss": 2.2532,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.17,
187
+ "learning_rate": 0.00019162011173184357,
188
+ "loss": 2.1788,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.17,
193
+ "learning_rate": 0.00019134078212290504,
194
+ "loss": 2.2494,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.18,
199
+ "learning_rate": 0.0001910614525139665,
200
+ "loss": 2.1995,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.18,
205
+ "learning_rate": 0.00019078212290502794,
206
+ "loss": 2.1451,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.19,
211
+ "learning_rate": 0.0001905027932960894,
212
+ "loss": 2.223,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.2,
217
+ "learning_rate": 0.00019022346368715085,
218
+ "loss": 2.2854,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.2,
223
+ "learning_rate": 0.0001899441340782123,
224
+ "loss": 2.2265,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.21,
229
+ "learning_rate": 0.00018966480446927375,
230
+ "loss": 2.1214,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.21,
235
+ "learning_rate": 0.0001893854748603352,
236
+ "loss": 2.1898,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.22,
241
+ "learning_rate": 0.00018910614525139666,
242
+ "loss": 2.1974,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.22,
247
+ "learning_rate": 0.0001888268156424581,
248
+ "loss": 2.2259,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.23,
253
+ "learning_rate": 0.00018854748603351957,
254
+ "loss": 2.2094,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.23,
259
+ "learning_rate": 0.00018826815642458103,
260
+ "loss": 2.1731,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.24,
265
+ "learning_rate": 0.00018798882681564247,
266
+ "loss": 2.2373,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.25,
271
+ "learning_rate": 0.0001877094972067039,
272
+ "loss": 2.2295,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.25,
277
+ "learning_rate": 0.00018743016759776538,
278
+ "loss": 2.1947,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.26,
283
+ "learning_rate": 0.00018715083798882682,
284
+ "loss": 2.2115,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.26,
289
+ "learning_rate": 0.00018687150837988828,
290
+ "loss": 2.1224,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.27,
295
+ "learning_rate": 0.00018659217877094972,
296
+ "loss": 2.2137,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.27,
301
+ "learning_rate": 0.00018631284916201116,
302
+ "loss": 2.2338,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.28,
307
+ "learning_rate": 0.00018603351955307266,
308
+ "loss": 2.1298,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.28,
313
+ "learning_rate": 0.0001857541899441341,
314
+ "loss": 2.0883,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.29,
319
+ "learning_rate": 0.00018547486033519553,
320
+ "loss": 2.1216,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.3,
325
+ "learning_rate": 0.000185195530726257,
326
+ "loss": 2.2112,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.3,
331
+ "learning_rate": 0.00018491620111731844,
332
+ "loss": 2.1224,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.31,
337
+ "learning_rate": 0.0001846368715083799,
338
+ "loss": 2.2375,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.31,
343
+ "learning_rate": 0.00018435754189944135,
344
+ "loss": 2.2235,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.32,
349
+ "learning_rate": 0.00018407821229050279,
350
+ "loss": 2.1682,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.32,
355
+ "learning_rate": 0.00018379888268156425,
356
+ "loss": 2.2077,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.33,
361
+ "learning_rate": 0.00018351955307262572,
362
+ "loss": 2.1596,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.34,
367
+ "learning_rate": 0.00018324022346368716,
368
+ "loss": 2.1311,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.34,
373
+ "learning_rate": 0.00018296089385474862,
374
+ "loss": 2.1333,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.35,
379
+ "learning_rate": 0.00018268156424581006,
380
+ "loss": 2.0901,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.35,
385
+ "learning_rate": 0.00018240223463687153,
386
+ "loss": 2.1971,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.36,
391
+ "learning_rate": 0.00018212290502793297,
392
+ "loss": 2.2602,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.36,
397
+ "learning_rate": 0.0001818435754189944,
398
+ "loss": 2.2194,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.37,
403
+ "learning_rate": 0.00018156424581005588,
404
+ "loss": 2.1218,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.37,
409
+ "learning_rate": 0.00018128491620111731,
410
+ "loss": 2.2049,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.38,
415
+ "learning_rate": 0.00018100558659217878,
416
+ "loss": 2.1521,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.39,
421
+ "learning_rate": 0.00018072625698324025,
422
+ "loss": 2.112,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.39,
427
+ "learning_rate": 0.0001804469273743017,
428
+ "loss": 2.1906,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.4,
433
+ "learning_rate": 0.00018016759776536313,
434
+ "loss": 2.1717,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.4,
439
+ "learning_rate": 0.0001798882681564246,
440
+ "loss": 2.0712,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.41,
445
+ "learning_rate": 0.00017960893854748603,
446
+ "loss": 2.141,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.41,
451
+ "learning_rate": 0.0001793296089385475,
452
+ "loss": 2.0656,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.42,
457
+ "learning_rate": 0.00017905027932960894,
458
+ "loss": 2.1125,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.42,
463
+ "learning_rate": 0.00017877094972067038,
464
+ "loss": 2.0869,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.43,
469
+ "learning_rate": 0.00017849162011173187,
470
+ "loss": 2.2478,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.44,
475
+ "learning_rate": 0.0001782122905027933,
476
+ "loss": 2.1535,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.44,
481
+ "learning_rate": 0.00017793296089385475,
482
+ "loss": 2.1927,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.45,
487
+ "learning_rate": 0.00017765363128491622,
488
+ "loss": 2.1213,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.45,
493
+ "learning_rate": 0.00017737430167597766,
494
+ "loss": 2.0981,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.46,
499
+ "learning_rate": 0.00017709497206703912,
500
+ "loss": 2.1828,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.46,
505
+ "learning_rate": 0.00017681564245810056,
506
+ "loss": 2.0562,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.47,
511
+ "learning_rate": 0.000176536312849162,
512
+ "loss": 2.1334,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.47,
517
+ "learning_rate": 0.00017625698324022347,
518
+ "loss": 2.1225,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.48,
523
+ "learning_rate": 0.00017597765363128493,
524
+ "loss": 2.2098,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.49,
529
+ "learning_rate": 0.00017569832402234637,
530
+ "loss": 2.1519,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.49,
535
+ "learning_rate": 0.00017541899441340784,
536
+ "loss": 2.1132,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.5,
541
+ "learning_rate": 0.00017513966480446928,
542
+ "loss": 2.0333,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.5,
547
+ "learning_rate": 0.00017486033519553075,
548
+ "loss": 2.2764,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.51,
553
+ "learning_rate": 0.00017458100558659218,
554
+ "loss": 2.1838,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.51,
559
+ "learning_rate": 0.00017430167597765362,
560
+ "loss": 2.1386,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.52,
565
+ "learning_rate": 0.0001740223463687151,
566
+ "loss": 2.1034,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.53,
571
+ "learning_rate": 0.00017374301675977656,
572
+ "loss": 2.0346,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.53,
577
+ "learning_rate": 0.000173463687150838,
578
+ "loss": 2.0274,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.54,
583
+ "learning_rate": 0.00017318435754189946,
584
+ "loss": 2.1036,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.54,
589
+ "learning_rate": 0.0001729050279329609,
590
+ "loss": 2.1208,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.55,
595
+ "learning_rate": 0.00017262569832402237,
596
+ "loss": 2.0572,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.55,
601
+ "learning_rate": 0.0001723463687150838,
602
+ "loss": 2.1702,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.56,
607
+ "learning_rate": 0.00017206703910614525,
608
+ "loss": 2.1302,
609
+ "step": 100
610
+ }
611
+ ],
612
+ "logging_steps": 1,
613
+ "max_steps": 716,
614
+ "num_train_epochs": 4,
615
+ "save_steps": 100,
616
+ "total_flos": 5.117136720224256e+16,
617
+ "trial_name": null,
618
+ "trial_params": null
619
+ }
checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:188ae1c421cc0c6435d1f71d8d3423ac4abc7dba0e6fc2efcbc4dbe77c741317
3
+ size 4027
checkpoint-200/README.md ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: True
10
+ - load_in_4bit: False
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: fp4
16
+ - bnb_4bit_use_double_quant: False
17
+ - bnb_4bit_compute_dtype: float32
18
+
19
+ The following `bitsandbytes` quantization config was used during training:
20
+ - quant_method: bitsandbytes
21
+ - load_in_8bit: True
22
+ - load_in_4bit: False
23
+ - llm_int8_threshold: 6.0
24
+ - llm_int8_skip_modules: None
25
+ - llm_int8_enable_fp32_cpu_offload: False
26
+ - llm_int8_has_fp16_weight: False
27
+ - bnb_4bit_quant_type: fp4
28
+ - bnb_4bit_use_double_quant: False
29
+ - bnb_4bit_compute_dtype: float32
30
+
31
+ The following `bitsandbytes` quantization config was used during training:
32
+ - quant_method: bitsandbytes
33
+ - load_in_8bit: True
34
+ - load_in_4bit: False
35
+ - llm_int8_threshold: 6.0
36
+ - llm_int8_skip_modules: None
37
+ - llm_int8_enable_fp32_cpu_offload: False
38
+ - llm_int8_has_fp16_weight: False
39
+ - bnb_4bit_quant_type: fp4
40
+ - bnb_4bit_use_double_quant: False
41
+ - bnb_4bit_compute_dtype: float32
42
+
43
+ The following `bitsandbytes` quantization config was used during training:
44
+ - quant_method: bitsandbytes
45
+ - load_in_8bit: True
46
+ - load_in_4bit: False
47
+ - llm_int8_threshold: 6.0
48
+ - llm_int8_skip_modules: None
49
+ - llm_int8_enable_fp32_cpu_offload: False
50
+ - llm_int8_has_fp16_weight: False
51
+ - bnb_4bit_quant_type: fp4
52
+ - bnb_4bit_use_double_quant: False
53
+ - bnb_4bit_compute_dtype: float32
54
+ ### Framework versions
55
+
56
+ - PEFT 0.6.0.dev0
57
+ - PEFT 0.6.0.dev0
58
+ - PEFT 0.6.0.dev0
59
+
60
+ - PEFT 0.6.0.dev0
checkpoint-200/adapter_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "bigscience/bloomz-3b",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "lora_alpha": 16,
12
+ "lora_dropout": 0.0,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 8,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "dense_4h_to_h",
20
+ "dense",
21
+ "dense_h_to_4h",
22
+ "query_key_value"
23
+ ],
24
+ "task_type": "CAUSAL_LM"
25
+ }
checkpoint-200/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5d07783590970cc01440af02efb30baf84be013f42d6e324dbec3f1211d5743
3
+ size 39409357
checkpoint-200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bb4e74f21744cbd194fc93b7a41891675165b22a0068ad1db19aeac49015587
3
+ size 78844421
checkpoint-200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:972139d83957a9cf2600cb6eeca17287d7a5377c33a53500ae7e13fe830ad36b
3
+ size 14575
checkpoint-200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49d3e390b4500e3448050a2123ac7e837c199dcd6015f166fda34e0372e32849
3
+ size 627
checkpoint-200/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
checkpoint-200/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85b00d7db4df5df2e3f01cacc3feda246002a672f3356eec7f4b04a22eb0dfbe
3
+ size 14500570
checkpoint-200/tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "<pad>",
8
+ "tokenizer_class": "BloomTokenizer",
9
+ "unk_token": "<unk>"
10
+ }
checkpoint-200/trainer_state.json ADDED
@@ -0,0 +1,1219 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.1173184357541899,
5
+ "eval_steps": 500,
6
+ "global_step": 200,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 0.00019972067039106145,
14
+ "loss": 2.6443,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 0.00019944134078212292,
20
+ "loss": 2.4104,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.02,
25
+ "learning_rate": 0.00019916201117318435,
26
+ "loss": 2.4975,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.02,
31
+ "learning_rate": 0.00019888268156424582,
32
+ "loss": 2.3513,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.03,
37
+ "learning_rate": 0.0001986033519553073,
38
+ "loss": 2.4274,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.03,
43
+ "learning_rate": 0.00019832402234636873,
44
+ "loss": 2.3628,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.04,
49
+ "learning_rate": 0.0001980446927374302,
50
+ "loss": 2.3567,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.04,
55
+ "learning_rate": 0.00019776536312849163,
56
+ "loss": 2.4121,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.05,
61
+ "learning_rate": 0.00019748603351955307,
62
+ "loss": 2.4033,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.06,
67
+ "learning_rate": 0.00019720670391061454,
68
+ "loss": 2.2805,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.06,
73
+ "learning_rate": 0.00019692737430167598,
74
+ "loss": 2.2639,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.07,
79
+ "learning_rate": 0.00019664804469273744,
80
+ "loss": 2.2724,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.07,
85
+ "learning_rate": 0.00019636871508379888,
86
+ "loss": 2.332,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.08,
91
+ "learning_rate": 0.00019608938547486035,
92
+ "loss": 2.2261,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.08,
97
+ "learning_rate": 0.00019581005586592182,
98
+ "loss": 2.2208,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.09,
103
+ "learning_rate": 0.00019553072625698326,
104
+ "loss": 2.3351,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.09,
109
+ "learning_rate": 0.0001952513966480447,
110
+ "loss": 2.2475,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.1,
115
+ "learning_rate": 0.00019497206703910616,
116
+ "loss": 2.3283,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.11,
121
+ "learning_rate": 0.0001946927374301676,
122
+ "loss": 2.1346,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.11,
127
+ "learning_rate": 0.00019441340782122907,
128
+ "loss": 2.131,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.12,
133
+ "learning_rate": 0.0001941340782122905,
134
+ "loss": 2.1718,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.12,
139
+ "learning_rate": 0.00019385474860335195,
140
+ "loss": 2.2446,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.13,
145
+ "learning_rate": 0.0001935754189944134,
146
+ "loss": 2.306,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.13,
151
+ "learning_rate": 0.00019329608938547488,
152
+ "loss": 2.1908,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.14,
157
+ "learning_rate": 0.00019301675977653632,
158
+ "loss": 2.2844,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.15,
163
+ "learning_rate": 0.00019273743016759779,
164
+ "loss": 2.2235,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.15,
169
+ "learning_rate": 0.00019245810055865922,
170
+ "loss": 2.1842,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.16,
175
+ "learning_rate": 0.00019217877094972066,
176
+ "loss": 2.2675,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.16,
181
+ "learning_rate": 0.00019189944134078213,
182
+ "loss": 2.2532,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.17,
187
+ "learning_rate": 0.00019162011173184357,
188
+ "loss": 2.1788,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.17,
193
+ "learning_rate": 0.00019134078212290504,
194
+ "loss": 2.2494,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.18,
199
+ "learning_rate": 0.0001910614525139665,
200
+ "loss": 2.1995,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.18,
205
+ "learning_rate": 0.00019078212290502794,
206
+ "loss": 2.1451,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.19,
211
+ "learning_rate": 0.0001905027932960894,
212
+ "loss": 2.223,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.2,
217
+ "learning_rate": 0.00019022346368715085,
218
+ "loss": 2.2854,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.2,
223
+ "learning_rate": 0.0001899441340782123,
224
+ "loss": 2.2265,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.21,
229
+ "learning_rate": 0.00018966480446927375,
230
+ "loss": 2.1214,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.21,
235
+ "learning_rate": 0.0001893854748603352,
236
+ "loss": 2.1898,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.22,
241
+ "learning_rate": 0.00018910614525139666,
242
+ "loss": 2.1974,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.22,
247
+ "learning_rate": 0.0001888268156424581,
248
+ "loss": 2.2259,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.23,
253
+ "learning_rate": 0.00018854748603351957,
254
+ "loss": 2.2094,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.23,
259
+ "learning_rate": 0.00018826815642458103,
260
+ "loss": 2.1731,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.24,
265
+ "learning_rate": 0.00018798882681564247,
266
+ "loss": 2.2373,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.25,
271
+ "learning_rate": 0.0001877094972067039,
272
+ "loss": 2.2295,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.25,
277
+ "learning_rate": 0.00018743016759776538,
278
+ "loss": 2.1947,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.26,
283
+ "learning_rate": 0.00018715083798882682,
284
+ "loss": 2.2115,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.26,
289
+ "learning_rate": 0.00018687150837988828,
290
+ "loss": 2.1224,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.27,
295
+ "learning_rate": 0.00018659217877094972,
296
+ "loss": 2.2137,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.27,
301
+ "learning_rate": 0.00018631284916201116,
302
+ "loss": 2.2338,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.28,
307
+ "learning_rate": 0.00018603351955307266,
308
+ "loss": 2.1298,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.28,
313
+ "learning_rate": 0.0001857541899441341,
314
+ "loss": 2.0883,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.29,
319
+ "learning_rate": 0.00018547486033519553,
320
+ "loss": 2.1216,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.3,
325
+ "learning_rate": 0.000185195530726257,
326
+ "loss": 2.2112,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.3,
331
+ "learning_rate": 0.00018491620111731844,
332
+ "loss": 2.1224,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.31,
337
+ "learning_rate": 0.0001846368715083799,
338
+ "loss": 2.2375,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.31,
343
+ "learning_rate": 0.00018435754189944135,
344
+ "loss": 2.2235,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.32,
349
+ "learning_rate": 0.00018407821229050279,
350
+ "loss": 2.1682,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.32,
355
+ "learning_rate": 0.00018379888268156425,
356
+ "loss": 2.2077,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.33,
361
+ "learning_rate": 0.00018351955307262572,
362
+ "loss": 2.1596,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.34,
367
+ "learning_rate": 0.00018324022346368716,
368
+ "loss": 2.1311,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.34,
373
+ "learning_rate": 0.00018296089385474862,
374
+ "loss": 2.1333,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.35,
379
+ "learning_rate": 0.00018268156424581006,
380
+ "loss": 2.0901,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.35,
385
+ "learning_rate": 0.00018240223463687153,
386
+ "loss": 2.1971,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.36,
391
+ "learning_rate": 0.00018212290502793297,
392
+ "loss": 2.2602,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.36,
397
+ "learning_rate": 0.0001818435754189944,
398
+ "loss": 2.2194,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.37,
403
+ "learning_rate": 0.00018156424581005588,
404
+ "loss": 2.1218,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.37,
409
+ "learning_rate": 0.00018128491620111731,
410
+ "loss": 2.2049,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.38,
415
+ "learning_rate": 0.00018100558659217878,
416
+ "loss": 2.1521,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.39,
421
+ "learning_rate": 0.00018072625698324025,
422
+ "loss": 2.112,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.39,
427
+ "learning_rate": 0.0001804469273743017,
428
+ "loss": 2.1906,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.4,
433
+ "learning_rate": 0.00018016759776536313,
434
+ "loss": 2.1717,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.4,
439
+ "learning_rate": 0.0001798882681564246,
440
+ "loss": 2.0712,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.41,
445
+ "learning_rate": 0.00017960893854748603,
446
+ "loss": 2.141,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.41,
451
+ "learning_rate": 0.0001793296089385475,
452
+ "loss": 2.0656,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.42,
457
+ "learning_rate": 0.00017905027932960894,
458
+ "loss": 2.1125,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.42,
463
+ "learning_rate": 0.00017877094972067038,
464
+ "loss": 2.0869,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.43,
469
+ "learning_rate": 0.00017849162011173187,
470
+ "loss": 2.2478,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.44,
475
+ "learning_rate": 0.0001782122905027933,
476
+ "loss": 2.1535,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.44,
481
+ "learning_rate": 0.00017793296089385475,
482
+ "loss": 2.1927,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.45,
487
+ "learning_rate": 0.00017765363128491622,
488
+ "loss": 2.1213,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.45,
493
+ "learning_rate": 0.00017737430167597766,
494
+ "loss": 2.0981,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.46,
499
+ "learning_rate": 0.00017709497206703912,
500
+ "loss": 2.1828,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.46,
505
+ "learning_rate": 0.00017681564245810056,
506
+ "loss": 2.0562,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.47,
511
+ "learning_rate": 0.000176536312849162,
512
+ "loss": 2.1334,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.47,
517
+ "learning_rate": 0.00017625698324022347,
518
+ "loss": 2.1225,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.48,
523
+ "learning_rate": 0.00017597765363128493,
524
+ "loss": 2.2098,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.49,
529
+ "learning_rate": 0.00017569832402234637,
530
+ "loss": 2.1519,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.49,
535
+ "learning_rate": 0.00017541899441340784,
536
+ "loss": 2.1132,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.5,
541
+ "learning_rate": 0.00017513966480446928,
542
+ "loss": 2.0333,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.5,
547
+ "learning_rate": 0.00017486033519553075,
548
+ "loss": 2.2764,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.51,
553
+ "learning_rate": 0.00017458100558659218,
554
+ "loss": 2.1838,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.51,
559
+ "learning_rate": 0.00017430167597765362,
560
+ "loss": 2.1386,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.52,
565
+ "learning_rate": 0.0001740223463687151,
566
+ "loss": 2.1034,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.53,
571
+ "learning_rate": 0.00017374301675977656,
572
+ "loss": 2.0346,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.53,
577
+ "learning_rate": 0.000173463687150838,
578
+ "loss": 2.0274,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.54,
583
+ "learning_rate": 0.00017318435754189946,
584
+ "loss": 2.1036,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.54,
589
+ "learning_rate": 0.0001729050279329609,
590
+ "loss": 2.1208,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.55,
595
+ "learning_rate": 0.00017262569832402237,
596
+ "loss": 2.0572,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.55,
601
+ "learning_rate": 0.0001723463687150838,
602
+ "loss": 2.1702,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.56,
607
+ "learning_rate": 0.00017206703910614525,
608
+ "loss": 2.1302,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 0.56,
613
+ "learning_rate": 0.0001717877094972067,
614
+ "loss": 2.0175,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 0.57,
619
+ "learning_rate": 0.00017150837988826815,
620
+ "loss": 2.1006,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 0.58,
625
+ "learning_rate": 0.00017122905027932962,
626
+ "loss": 2.0662,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 0.58,
631
+ "learning_rate": 0.00017094972067039109,
632
+ "loss": 1.988,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 0.59,
637
+ "learning_rate": 0.00017067039106145253,
638
+ "loss": 2.1008,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 0.59,
643
+ "learning_rate": 0.00017039106145251396,
644
+ "loss": 2.1482,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 0.6,
649
+ "learning_rate": 0.00017011173184357543,
650
+ "loss": 2.1052,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 0.6,
655
+ "learning_rate": 0.00016983240223463687,
656
+ "loss": 2.0978,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 0.61,
661
+ "learning_rate": 0.00016955307262569834,
662
+ "loss": 2.1303,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 0.61,
667
+ "learning_rate": 0.00016927374301675978,
668
+ "loss": 2.0794,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 0.62,
673
+ "learning_rate": 0.00016899441340782122,
674
+ "loss": 2.1059,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 0.63,
679
+ "learning_rate": 0.0001687150837988827,
680
+ "loss": 1.9642,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 0.63,
685
+ "learning_rate": 0.00016843575418994415,
686
+ "loss": 2.0415,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 0.64,
691
+ "learning_rate": 0.0001681564245810056,
692
+ "loss": 2.0795,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 0.64,
697
+ "learning_rate": 0.00016787709497206705,
698
+ "loss": 2.0238,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 0.65,
703
+ "learning_rate": 0.0001675977653631285,
704
+ "loss": 2.078,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 0.65,
709
+ "learning_rate": 0.00016731843575418996,
710
+ "loss": 2.1362,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 0.66,
715
+ "learning_rate": 0.0001670391061452514,
716
+ "loss": 2.0552,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 0.66,
721
+ "learning_rate": 0.00016675977653631284,
722
+ "loss": 2.213,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 0.67,
727
+ "learning_rate": 0.0001664804469273743,
728
+ "loss": 1.9999,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 0.68,
733
+ "learning_rate": 0.00016620111731843577,
734
+ "loss": 2.06,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 0.68,
739
+ "learning_rate": 0.0001659217877094972,
740
+ "loss": 2.0177,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 0.69,
745
+ "learning_rate": 0.00016564245810055868,
746
+ "loss": 2.0504,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 0.69,
751
+ "learning_rate": 0.00016536312849162012,
752
+ "loss": 2.0585,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 0.7,
757
+ "learning_rate": 0.00016508379888268158,
758
+ "loss": 2.0273,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 0.7,
763
+ "learning_rate": 0.00016480446927374302,
764
+ "loss": 2.0549,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 0.71,
769
+ "learning_rate": 0.00016452513966480446,
770
+ "loss": 2.044,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 0.72,
775
+ "learning_rate": 0.00016424581005586593,
776
+ "loss": 2.0731,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 0.72,
781
+ "learning_rate": 0.00016396648044692737,
782
+ "loss": 2.0568,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 0.73,
787
+ "learning_rate": 0.00016368715083798883,
788
+ "loss": 2.007,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 0.73,
793
+ "learning_rate": 0.0001634078212290503,
794
+ "loss": 2.0707,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 0.74,
799
+ "learning_rate": 0.00016312849162011174,
800
+ "loss": 1.9793,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 0.74,
805
+ "learning_rate": 0.0001628491620111732,
806
+ "loss": 2.1311,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 0.75,
811
+ "learning_rate": 0.00016256983240223465,
812
+ "loss": 2.0016,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 0.75,
817
+ "learning_rate": 0.00016229050279329609,
818
+ "loss": 1.9945,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 0.76,
823
+ "learning_rate": 0.00016201117318435755,
824
+ "loss": 2.0186,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 0.77,
829
+ "learning_rate": 0.000161731843575419,
830
+ "loss": 2.0971,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 0.77,
835
+ "learning_rate": 0.00016145251396648046,
836
+ "loss": 2.0883,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 0.78,
841
+ "learning_rate": 0.00016117318435754192,
842
+ "loss": 2.0803,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 0.78,
847
+ "learning_rate": 0.00016089385474860336,
848
+ "loss": 2.0617,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.79,
853
+ "learning_rate": 0.00016061452513966483,
854
+ "loss": 2.1265,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.79,
859
+ "learning_rate": 0.00016033519553072627,
860
+ "loss": 2.0151,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.8,
865
+ "learning_rate": 0.0001600558659217877,
866
+ "loss": 1.996,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.8,
871
+ "learning_rate": 0.00015977653631284918,
872
+ "loss": 2.0164,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.81,
877
+ "learning_rate": 0.00015949720670391061,
878
+ "loss": 2.0314,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 0.82,
883
+ "learning_rate": 0.00015921787709497208,
884
+ "loss": 1.9501,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 0.82,
889
+ "learning_rate": 0.00015893854748603352,
890
+ "loss": 2.087,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 0.83,
895
+ "learning_rate": 0.000158659217877095,
896
+ "loss": 2.0262,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 0.83,
901
+ "learning_rate": 0.00015837988826815643,
902
+ "loss": 2.0765,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 0.84,
907
+ "learning_rate": 0.0001581005586592179,
908
+ "loss": 2.105,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 0.84,
913
+ "learning_rate": 0.00015782122905027933,
914
+ "loss": 1.9863,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 0.85,
919
+ "learning_rate": 0.0001575418994413408,
920
+ "loss": 1.9873,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 0.85,
925
+ "learning_rate": 0.00015726256983240224,
926
+ "loss": 2.0094,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 0.86,
931
+ "learning_rate": 0.00015698324022346368,
932
+ "loss": 1.9141,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 0.87,
937
+ "learning_rate": 0.00015670391061452514,
938
+ "loss": 1.917,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 0.87,
943
+ "learning_rate": 0.00015642458100558658,
944
+ "loss": 2.109,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 0.88,
949
+ "learning_rate": 0.00015614525139664805,
950
+ "loss": 1.9799,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 0.88,
955
+ "learning_rate": 0.00015586592178770952,
956
+ "loss": 1.9571,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 0.89,
961
+ "learning_rate": 0.00015558659217877096,
962
+ "loss": 1.9931,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 0.89,
967
+ "learning_rate": 0.00015530726256983242,
968
+ "loss": 2.1004,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 0.9,
973
+ "learning_rate": 0.00015502793296089386,
974
+ "loss": 2.0385,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 0.91,
979
+ "learning_rate": 0.0001547486033519553,
980
+ "loss": 1.9751,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 0.91,
985
+ "learning_rate": 0.00015446927374301677,
986
+ "loss": 2.0544,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 0.92,
991
+ "learning_rate": 0.0001541899441340782,
992
+ "loss": 2.0069,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 0.92,
997
+ "learning_rate": 0.00015391061452513967,
998
+ "loss": 1.9576,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 0.93,
1003
+ "learning_rate": 0.00015363128491620114,
1004
+ "loss": 1.8991,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 0.93,
1009
+ "learning_rate": 0.00015335195530726258,
1010
+ "loss": 1.9336,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 0.94,
1015
+ "learning_rate": 0.00015307262569832405,
1016
+ "loss": 1.9736,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 0.94,
1021
+ "learning_rate": 0.00015279329608938548,
1022
+ "loss": 1.9702,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 0.95,
1027
+ "learning_rate": 0.00015251396648044692,
1028
+ "loss": 1.9055,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 0.96,
1033
+ "learning_rate": 0.0001522346368715084,
1034
+ "loss": 2.0503,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 0.96,
1039
+ "learning_rate": 0.00015195530726256983,
1040
+ "loss": 2.0039,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 0.97,
1045
+ "learning_rate": 0.0001516759776536313,
1046
+ "loss": 1.9406,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 0.97,
1051
+ "learning_rate": 0.00015139664804469274,
1052
+ "loss": 2.0525,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 0.98,
1057
+ "learning_rate": 0.0001511173184357542,
1058
+ "loss": 1.9234,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 0.98,
1063
+ "learning_rate": 0.00015083798882681567,
1064
+ "loss": 1.8614,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 0.99,
1069
+ "learning_rate": 0.0001505586592178771,
1070
+ "loss": 1.9616,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 0.99,
1075
+ "learning_rate": 0.00015027932960893855,
1076
+ "loss": 1.9509,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 1.0,
1081
+ "learning_rate": 0.00015000000000000001,
1082
+ "loss": 1.9592,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 1.01,
1087
+ "learning_rate": 0.00014972067039106145,
1088
+ "loss": 1.8991,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 1.01,
1093
+ "learning_rate": 0.00014944134078212292,
1094
+ "loss": 1.9127,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 1.02,
1099
+ "learning_rate": 0.00014916201117318436,
1100
+ "loss": 1.8982,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 1.02,
1105
+ "learning_rate": 0.0001488826815642458,
1106
+ "loss": 1.9534,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 1.03,
1111
+ "learning_rate": 0.0001486033519553073,
1112
+ "loss": 1.7794,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 1.03,
1117
+ "learning_rate": 0.00014832402234636873,
1118
+ "loss": 1.7958,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 1.04,
1123
+ "learning_rate": 0.00014804469273743017,
1124
+ "loss": 1.8282,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 1.04,
1129
+ "learning_rate": 0.00014776536312849164,
1130
+ "loss": 2.0423,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 1.05,
1135
+ "learning_rate": 0.00014748603351955308,
1136
+ "loss": 1.9282,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 1.06,
1141
+ "learning_rate": 0.00014720670391061454,
1142
+ "loss": 1.9072,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 1.06,
1147
+ "learning_rate": 0.00014692737430167598,
1148
+ "loss": 1.8665,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 1.07,
1153
+ "learning_rate": 0.00014664804469273742,
1154
+ "loss": 1.9021,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 1.07,
1159
+ "learning_rate": 0.0001463687150837989,
1160
+ "loss": 1.7308,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 1.08,
1165
+ "learning_rate": 0.00014608938547486035,
1166
+ "loss": 1.9165,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 1.08,
1171
+ "learning_rate": 0.0001458100558659218,
1172
+ "loss": 1.842,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 1.09,
1177
+ "learning_rate": 0.00014553072625698326,
1178
+ "loss": 1.9128,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 1.09,
1183
+ "learning_rate": 0.0001452513966480447,
1184
+ "loss": 1.8005,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 1.1,
1189
+ "learning_rate": 0.00014497206703910614,
1190
+ "loss": 1.8547,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 1.11,
1195
+ "learning_rate": 0.0001446927374301676,
1196
+ "loss": 1.9042,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 1.11,
1201
+ "learning_rate": 0.00014441340782122905,
1202
+ "loss": 1.8609,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 1.12,
1207
+ "learning_rate": 0.0001441340782122905,
1208
+ "loss": 1.9591,
1209
+ "step": 200
1210
+ }
1211
+ ],
1212
+ "logging_steps": 1,
1213
+ "max_steps": 716,
1214
+ "num_train_epochs": 4,
1215
+ "save_steps": 100,
1216
+ "total_flos": 1.0290223796256768e+17,
1217
+ "trial_name": null,
1218
+ "trial_params": null
1219
+ }
checkpoint-200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:188ae1c421cc0c6435d1f71d8d3423ac4abc7dba0e6fc2efcbc4dbe77c741317
3
+ size 4027
checkpoint-300/README.md ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: True
10
+ - load_in_4bit: False
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: fp4
16
+ - bnb_4bit_use_double_quant: False
17
+ - bnb_4bit_compute_dtype: float32
18
+
19
+ The following `bitsandbytes` quantization config was used during training:
20
+ - quant_method: bitsandbytes
21
+ - load_in_8bit: True
22
+ - load_in_4bit: False
23
+ - llm_int8_threshold: 6.0
24
+ - llm_int8_skip_modules: None
25
+ - llm_int8_enable_fp32_cpu_offload: False
26
+ - llm_int8_has_fp16_weight: False
27
+ - bnb_4bit_quant_type: fp4
28
+ - bnb_4bit_use_double_quant: False
29
+ - bnb_4bit_compute_dtype: float32
30
+
31
+ The following `bitsandbytes` quantization config was used during training:
32
+ - quant_method: bitsandbytes
33
+ - load_in_8bit: True
34
+ - load_in_4bit: False
35
+ - llm_int8_threshold: 6.0
36
+ - llm_int8_skip_modules: None
37
+ - llm_int8_enable_fp32_cpu_offload: False
38
+ - llm_int8_has_fp16_weight: False
39
+ - bnb_4bit_quant_type: fp4
40
+ - bnb_4bit_use_double_quant: False
41
+ - bnb_4bit_compute_dtype: float32
42
+
43
+ The following `bitsandbytes` quantization config was used during training:
44
+ - quant_method: bitsandbytes
45
+ - load_in_8bit: True
46
+ - load_in_4bit: False
47
+ - llm_int8_threshold: 6.0
48
+ - llm_int8_skip_modules: None
49
+ - llm_int8_enable_fp32_cpu_offload: False
50
+ - llm_int8_has_fp16_weight: False
51
+ - bnb_4bit_quant_type: fp4
52
+ - bnb_4bit_use_double_quant: False
53
+ - bnb_4bit_compute_dtype: float32
54
+ ### Framework versions
55
+
56
+ - PEFT 0.6.0.dev0
57
+ - PEFT 0.6.0.dev0
58
+ - PEFT 0.6.0.dev0
59
+
60
+ - PEFT 0.6.0.dev0
checkpoint-300/adapter_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "bigscience/bloomz-3b",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "lora_alpha": 16,
12
+ "lora_dropout": 0.0,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 8,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "dense_4h_to_h",
20
+ "dense",
21
+ "dense_h_to_4h",
22
+ "query_key_value"
23
+ ],
24
+ "task_type": "CAUSAL_LM"
25
+ }
checkpoint-300/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b39b2ac3c3f75772f547048fda7ecb323076b9689db7d79915bba156dc508f2f
3
+ size 39409357
checkpoint-300/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c734ecaa394370ee4bcd94cc0b2ae016a26765122f3f76327b28c23f96a22732
3
+ size 78844421
checkpoint-300/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:972139d83957a9cf2600cb6eeca17287d7a5377c33a53500ae7e13fe830ad36b
3
+ size 14575
checkpoint-300/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d8dcaf05375bb59f736a94e8f8b03d33cdc87bc02411e6527a29996e0a68b3b
3
+ size 627
checkpoint-300/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
checkpoint-300/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85b00d7db4df5df2e3f01cacc3feda246002a672f3356eec7f4b04a22eb0dfbe
3
+ size 14500570
checkpoint-300/tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "<pad>",
8
+ "tokenizer_class": "BloomTokenizer",
9
+ "unk_token": "<unk>"
10
+ }
checkpoint-300/trainer_state.json ADDED
@@ -0,0 +1,1819 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.675977653631285,
5
+ "eval_steps": 500,
6
+ "global_step": 300,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 0.00019972067039106145,
14
+ "loss": 2.6443,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 0.00019944134078212292,
20
+ "loss": 2.4104,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.02,
25
+ "learning_rate": 0.00019916201117318435,
26
+ "loss": 2.4975,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.02,
31
+ "learning_rate": 0.00019888268156424582,
32
+ "loss": 2.3513,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.03,
37
+ "learning_rate": 0.0001986033519553073,
38
+ "loss": 2.4274,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.03,
43
+ "learning_rate": 0.00019832402234636873,
44
+ "loss": 2.3628,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.04,
49
+ "learning_rate": 0.0001980446927374302,
50
+ "loss": 2.3567,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.04,
55
+ "learning_rate": 0.00019776536312849163,
56
+ "loss": 2.4121,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.05,
61
+ "learning_rate": 0.00019748603351955307,
62
+ "loss": 2.4033,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.06,
67
+ "learning_rate": 0.00019720670391061454,
68
+ "loss": 2.2805,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.06,
73
+ "learning_rate": 0.00019692737430167598,
74
+ "loss": 2.2639,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.07,
79
+ "learning_rate": 0.00019664804469273744,
80
+ "loss": 2.2724,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.07,
85
+ "learning_rate": 0.00019636871508379888,
86
+ "loss": 2.332,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.08,
91
+ "learning_rate": 0.00019608938547486035,
92
+ "loss": 2.2261,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.08,
97
+ "learning_rate": 0.00019581005586592182,
98
+ "loss": 2.2208,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.09,
103
+ "learning_rate": 0.00019553072625698326,
104
+ "loss": 2.3351,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.09,
109
+ "learning_rate": 0.0001952513966480447,
110
+ "loss": 2.2475,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.1,
115
+ "learning_rate": 0.00019497206703910616,
116
+ "loss": 2.3283,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.11,
121
+ "learning_rate": 0.0001946927374301676,
122
+ "loss": 2.1346,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.11,
127
+ "learning_rate": 0.00019441340782122907,
128
+ "loss": 2.131,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.12,
133
+ "learning_rate": 0.0001941340782122905,
134
+ "loss": 2.1718,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.12,
139
+ "learning_rate": 0.00019385474860335195,
140
+ "loss": 2.2446,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.13,
145
+ "learning_rate": 0.0001935754189944134,
146
+ "loss": 2.306,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.13,
151
+ "learning_rate": 0.00019329608938547488,
152
+ "loss": 2.1908,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.14,
157
+ "learning_rate": 0.00019301675977653632,
158
+ "loss": 2.2844,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.15,
163
+ "learning_rate": 0.00019273743016759779,
164
+ "loss": 2.2235,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.15,
169
+ "learning_rate": 0.00019245810055865922,
170
+ "loss": 2.1842,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.16,
175
+ "learning_rate": 0.00019217877094972066,
176
+ "loss": 2.2675,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.16,
181
+ "learning_rate": 0.00019189944134078213,
182
+ "loss": 2.2532,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.17,
187
+ "learning_rate": 0.00019162011173184357,
188
+ "loss": 2.1788,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.17,
193
+ "learning_rate": 0.00019134078212290504,
194
+ "loss": 2.2494,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.18,
199
+ "learning_rate": 0.0001910614525139665,
200
+ "loss": 2.1995,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.18,
205
+ "learning_rate": 0.00019078212290502794,
206
+ "loss": 2.1451,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.19,
211
+ "learning_rate": 0.0001905027932960894,
212
+ "loss": 2.223,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.2,
217
+ "learning_rate": 0.00019022346368715085,
218
+ "loss": 2.2854,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.2,
223
+ "learning_rate": 0.0001899441340782123,
224
+ "loss": 2.2265,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.21,
229
+ "learning_rate": 0.00018966480446927375,
230
+ "loss": 2.1214,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.21,
235
+ "learning_rate": 0.0001893854748603352,
236
+ "loss": 2.1898,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.22,
241
+ "learning_rate": 0.00018910614525139666,
242
+ "loss": 2.1974,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.22,
247
+ "learning_rate": 0.0001888268156424581,
248
+ "loss": 2.2259,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.23,
253
+ "learning_rate": 0.00018854748603351957,
254
+ "loss": 2.2094,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.23,
259
+ "learning_rate": 0.00018826815642458103,
260
+ "loss": 2.1731,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.24,
265
+ "learning_rate": 0.00018798882681564247,
266
+ "loss": 2.2373,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.25,
271
+ "learning_rate": 0.0001877094972067039,
272
+ "loss": 2.2295,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.25,
277
+ "learning_rate": 0.00018743016759776538,
278
+ "loss": 2.1947,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.26,
283
+ "learning_rate": 0.00018715083798882682,
284
+ "loss": 2.2115,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.26,
289
+ "learning_rate": 0.00018687150837988828,
290
+ "loss": 2.1224,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.27,
295
+ "learning_rate": 0.00018659217877094972,
296
+ "loss": 2.2137,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.27,
301
+ "learning_rate": 0.00018631284916201116,
302
+ "loss": 2.2338,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.28,
307
+ "learning_rate": 0.00018603351955307266,
308
+ "loss": 2.1298,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.28,
313
+ "learning_rate": 0.0001857541899441341,
314
+ "loss": 2.0883,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.29,
319
+ "learning_rate": 0.00018547486033519553,
320
+ "loss": 2.1216,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.3,
325
+ "learning_rate": 0.000185195530726257,
326
+ "loss": 2.2112,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.3,
331
+ "learning_rate": 0.00018491620111731844,
332
+ "loss": 2.1224,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.31,
337
+ "learning_rate": 0.0001846368715083799,
338
+ "loss": 2.2375,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.31,
343
+ "learning_rate": 0.00018435754189944135,
344
+ "loss": 2.2235,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.32,
349
+ "learning_rate": 0.00018407821229050279,
350
+ "loss": 2.1682,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.32,
355
+ "learning_rate": 0.00018379888268156425,
356
+ "loss": 2.2077,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.33,
361
+ "learning_rate": 0.00018351955307262572,
362
+ "loss": 2.1596,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.34,
367
+ "learning_rate": 0.00018324022346368716,
368
+ "loss": 2.1311,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.34,
373
+ "learning_rate": 0.00018296089385474862,
374
+ "loss": 2.1333,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.35,
379
+ "learning_rate": 0.00018268156424581006,
380
+ "loss": 2.0901,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.35,
385
+ "learning_rate": 0.00018240223463687153,
386
+ "loss": 2.1971,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.36,
391
+ "learning_rate": 0.00018212290502793297,
392
+ "loss": 2.2602,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.36,
397
+ "learning_rate": 0.0001818435754189944,
398
+ "loss": 2.2194,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.37,
403
+ "learning_rate": 0.00018156424581005588,
404
+ "loss": 2.1218,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.37,
409
+ "learning_rate": 0.00018128491620111731,
410
+ "loss": 2.2049,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.38,
415
+ "learning_rate": 0.00018100558659217878,
416
+ "loss": 2.1521,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.39,
421
+ "learning_rate": 0.00018072625698324025,
422
+ "loss": 2.112,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.39,
427
+ "learning_rate": 0.0001804469273743017,
428
+ "loss": 2.1906,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.4,
433
+ "learning_rate": 0.00018016759776536313,
434
+ "loss": 2.1717,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.4,
439
+ "learning_rate": 0.0001798882681564246,
440
+ "loss": 2.0712,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.41,
445
+ "learning_rate": 0.00017960893854748603,
446
+ "loss": 2.141,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.41,
451
+ "learning_rate": 0.0001793296089385475,
452
+ "loss": 2.0656,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.42,
457
+ "learning_rate": 0.00017905027932960894,
458
+ "loss": 2.1125,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.42,
463
+ "learning_rate": 0.00017877094972067038,
464
+ "loss": 2.0869,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.43,
469
+ "learning_rate": 0.00017849162011173187,
470
+ "loss": 2.2478,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.44,
475
+ "learning_rate": 0.0001782122905027933,
476
+ "loss": 2.1535,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.44,
481
+ "learning_rate": 0.00017793296089385475,
482
+ "loss": 2.1927,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.45,
487
+ "learning_rate": 0.00017765363128491622,
488
+ "loss": 2.1213,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.45,
493
+ "learning_rate": 0.00017737430167597766,
494
+ "loss": 2.0981,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.46,
499
+ "learning_rate": 0.00017709497206703912,
500
+ "loss": 2.1828,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.46,
505
+ "learning_rate": 0.00017681564245810056,
506
+ "loss": 2.0562,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.47,
511
+ "learning_rate": 0.000176536312849162,
512
+ "loss": 2.1334,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.47,
517
+ "learning_rate": 0.00017625698324022347,
518
+ "loss": 2.1225,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.48,
523
+ "learning_rate": 0.00017597765363128493,
524
+ "loss": 2.2098,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.49,
529
+ "learning_rate": 0.00017569832402234637,
530
+ "loss": 2.1519,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.49,
535
+ "learning_rate": 0.00017541899441340784,
536
+ "loss": 2.1132,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.5,
541
+ "learning_rate": 0.00017513966480446928,
542
+ "loss": 2.0333,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.5,
547
+ "learning_rate": 0.00017486033519553075,
548
+ "loss": 2.2764,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.51,
553
+ "learning_rate": 0.00017458100558659218,
554
+ "loss": 2.1838,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.51,
559
+ "learning_rate": 0.00017430167597765362,
560
+ "loss": 2.1386,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.52,
565
+ "learning_rate": 0.0001740223463687151,
566
+ "loss": 2.1034,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.53,
571
+ "learning_rate": 0.00017374301675977656,
572
+ "loss": 2.0346,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.53,
577
+ "learning_rate": 0.000173463687150838,
578
+ "loss": 2.0274,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.54,
583
+ "learning_rate": 0.00017318435754189946,
584
+ "loss": 2.1036,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.54,
589
+ "learning_rate": 0.0001729050279329609,
590
+ "loss": 2.1208,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.55,
595
+ "learning_rate": 0.00017262569832402237,
596
+ "loss": 2.0572,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.55,
601
+ "learning_rate": 0.0001723463687150838,
602
+ "loss": 2.1702,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.56,
607
+ "learning_rate": 0.00017206703910614525,
608
+ "loss": 2.1302,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 0.56,
613
+ "learning_rate": 0.0001717877094972067,
614
+ "loss": 2.0175,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 0.57,
619
+ "learning_rate": 0.00017150837988826815,
620
+ "loss": 2.1006,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 0.58,
625
+ "learning_rate": 0.00017122905027932962,
626
+ "loss": 2.0662,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 0.58,
631
+ "learning_rate": 0.00017094972067039109,
632
+ "loss": 1.988,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 0.59,
637
+ "learning_rate": 0.00017067039106145253,
638
+ "loss": 2.1008,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 0.59,
643
+ "learning_rate": 0.00017039106145251396,
644
+ "loss": 2.1482,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 0.6,
649
+ "learning_rate": 0.00017011173184357543,
650
+ "loss": 2.1052,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 0.6,
655
+ "learning_rate": 0.00016983240223463687,
656
+ "loss": 2.0978,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 0.61,
661
+ "learning_rate": 0.00016955307262569834,
662
+ "loss": 2.1303,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 0.61,
667
+ "learning_rate": 0.00016927374301675978,
668
+ "loss": 2.0794,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 0.62,
673
+ "learning_rate": 0.00016899441340782122,
674
+ "loss": 2.1059,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 0.63,
679
+ "learning_rate": 0.0001687150837988827,
680
+ "loss": 1.9642,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 0.63,
685
+ "learning_rate": 0.00016843575418994415,
686
+ "loss": 2.0415,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 0.64,
691
+ "learning_rate": 0.0001681564245810056,
692
+ "loss": 2.0795,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 0.64,
697
+ "learning_rate": 0.00016787709497206705,
698
+ "loss": 2.0238,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 0.65,
703
+ "learning_rate": 0.0001675977653631285,
704
+ "loss": 2.078,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 0.65,
709
+ "learning_rate": 0.00016731843575418996,
710
+ "loss": 2.1362,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 0.66,
715
+ "learning_rate": 0.0001670391061452514,
716
+ "loss": 2.0552,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 0.66,
721
+ "learning_rate": 0.00016675977653631284,
722
+ "loss": 2.213,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 0.67,
727
+ "learning_rate": 0.0001664804469273743,
728
+ "loss": 1.9999,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 0.68,
733
+ "learning_rate": 0.00016620111731843577,
734
+ "loss": 2.06,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 0.68,
739
+ "learning_rate": 0.0001659217877094972,
740
+ "loss": 2.0177,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 0.69,
745
+ "learning_rate": 0.00016564245810055868,
746
+ "loss": 2.0504,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 0.69,
751
+ "learning_rate": 0.00016536312849162012,
752
+ "loss": 2.0585,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 0.7,
757
+ "learning_rate": 0.00016508379888268158,
758
+ "loss": 2.0273,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 0.7,
763
+ "learning_rate": 0.00016480446927374302,
764
+ "loss": 2.0549,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 0.71,
769
+ "learning_rate": 0.00016452513966480446,
770
+ "loss": 2.044,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 0.72,
775
+ "learning_rate": 0.00016424581005586593,
776
+ "loss": 2.0731,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 0.72,
781
+ "learning_rate": 0.00016396648044692737,
782
+ "loss": 2.0568,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 0.73,
787
+ "learning_rate": 0.00016368715083798883,
788
+ "loss": 2.007,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 0.73,
793
+ "learning_rate": 0.0001634078212290503,
794
+ "loss": 2.0707,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 0.74,
799
+ "learning_rate": 0.00016312849162011174,
800
+ "loss": 1.9793,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 0.74,
805
+ "learning_rate": 0.0001628491620111732,
806
+ "loss": 2.1311,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 0.75,
811
+ "learning_rate": 0.00016256983240223465,
812
+ "loss": 2.0016,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 0.75,
817
+ "learning_rate": 0.00016229050279329609,
818
+ "loss": 1.9945,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 0.76,
823
+ "learning_rate": 0.00016201117318435755,
824
+ "loss": 2.0186,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 0.77,
829
+ "learning_rate": 0.000161731843575419,
830
+ "loss": 2.0971,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 0.77,
835
+ "learning_rate": 0.00016145251396648046,
836
+ "loss": 2.0883,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 0.78,
841
+ "learning_rate": 0.00016117318435754192,
842
+ "loss": 2.0803,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 0.78,
847
+ "learning_rate": 0.00016089385474860336,
848
+ "loss": 2.0617,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.79,
853
+ "learning_rate": 0.00016061452513966483,
854
+ "loss": 2.1265,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.79,
859
+ "learning_rate": 0.00016033519553072627,
860
+ "loss": 2.0151,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.8,
865
+ "learning_rate": 0.0001600558659217877,
866
+ "loss": 1.996,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.8,
871
+ "learning_rate": 0.00015977653631284918,
872
+ "loss": 2.0164,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.81,
877
+ "learning_rate": 0.00015949720670391061,
878
+ "loss": 2.0314,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 0.82,
883
+ "learning_rate": 0.00015921787709497208,
884
+ "loss": 1.9501,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 0.82,
889
+ "learning_rate": 0.00015893854748603352,
890
+ "loss": 2.087,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 0.83,
895
+ "learning_rate": 0.000158659217877095,
896
+ "loss": 2.0262,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 0.83,
901
+ "learning_rate": 0.00015837988826815643,
902
+ "loss": 2.0765,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 0.84,
907
+ "learning_rate": 0.0001581005586592179,
908
+ "loss": 2.105,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 0.84,
913
+ "learning_rate": 0.00015782122905027933,
914
+ "loss": 1.9863,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 0.85,
919
+ "learning_rate": 0.0001575418994413408,
920
+ "loss": 1.9873,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 0.85,
925
+ "learning_rate": 0.00015726256983240224,
926
+ "loss": 2.0094,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 0.86,
931
+ "learning_rate": 0.00015698324022346368,
932
+ "loss": 1.9141,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 0.87,
937
+ "learning_rate": 0.00015670391061452514,
938
+ "loss": 1.917,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 0.87,
943
+ "learning_rate": 0.00015642458100558658,
944
+ "loss": 2.109,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 0.88,
949
+ "learning_rate": 0.00015614525139664805,
950
+ "loss": 1.9799,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 0.88,
955
+ "learning_rate": 0.00015586592178770952,
956
+ "loss": 1.9571,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 0.89,
961
+ "learning_rate": 0.00015558659217877096,
962
+ "loss": 1.9931,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 0.89,
967
+ "learning_rate": 0.00015530726256983242,
968
+ "loss": 2.1004,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 0.9,
973
+ "learning_rate": 0.00015502793296089386,
974
+ "loss": 2.0385,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 0.91,
979
+ "learning_rate": 0.0001547486033519553,
980
+ "loss": 1.9751,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 0.91,
985
+ "learning_rate": 0.00015446927374301677,
986
+ "loss": 2.0544,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 0.92,
991
+ "learning_rate": 0.0001541899441340782,
992
+ "loss": 2.0069,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 0.92,
997
+ "learning_rate": 0.00015391061452513967,
998
+ "loss": 1.9576,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 0.93,
1003
+ "learning_rate": 0.00015363128491620114,
1004
+ "loss": 1.8991,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 0.93,
1009
+ "learning_rate": 0.00015335195530726258,
1010
+ "loss": 1.9336,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 0.94,
1015
+ "learning_rate": 0.00015307262569832405,
1016
+ "loss": 1.9736,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 0.94,
1021
+ "learning_rate": 0.00015279329608938548,
1022
+ "loss": 1.9702,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 0.95,
1027
+ "learning_rate": 0.00015251396648044692,
1028
+ "loss": 1.9055,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 0.96,
1033
+ "learning_rate": 0.0001522346368715084,
1034
+ "loss": 2.0503,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 0.96,
1039
+ "learning_rate": 0.00015195530726256983,
1040
+ "loss": 2.0039,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 0.97,
1045
+ "learning_rate": 0.0001516759776536313,
1046
+ "loss": 1.9406,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 0.97,
1051
+ "learning_rate": 0.00015139664804469274,
1052
+ "loss": 2.0525,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 0.98,
1057
+ "learning_rate": 0.0001511173184357542,
1058
+ "loss": 1.9234,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 0.98,
1063
+ "learning_rate": 0.00015083798882681567,
1064
+ "loss": 1.8614,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 0.99,
1069
+ "learning_rate": 0.0001505586592178771,
1070
+ "loss": 1.9616,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 0.99,
1075
+ "learning_rate": 0.00015027932960893855,
1076
+ "loss": 1.9509,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 1.0,
1081
+ "learning_rate": 0.00015000000000000001,
1082
+ "loss": 1.9592,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 1.01,
1087
+ "learning_rate": 0.00014972067039106145,
1088
+ "loss": 1.8991,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 1.01,
1093
+ "learning_rate": 0.00014944134078212292,
1094
+ "loss": 1.9127,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 1.02,
1099
+ "learning_rate": 0.00014916201117318436,
1100
+ "loss": 1.8982,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 1.02,
1105
+ "learning_rate": 0.0001488826815642458,
1106
+ "loss": 1.9534,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 1.03,
1111
+ "learning_rate": 0.0001486033519553073,
1112
+ "loss": 1.7794,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 1.03,
1117
+ "learning_rate": 0.00014832402234636873,
1118
+ "loss": 1.7958,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 1.04,
1123
+ "learning_rate": 0.00014804469273743017,
1124
+ "loss": 1.8282,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 1.04,
1129
+ "learning_rate": 0.00014776536312849164,
1130
+ "loss": 2.0423,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 1.05,
1135
+ "learning_rate": 0.00014748603351955308,
1136
+ "loss": 1.9282,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 1.06,
1141
+ "learning_rate": 0.00014720670391061454,
1142
+ "loss": 1.9072,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 1.06,
1147
+ "learning_rate": 0.00014692737430167598,
1148
+ "loss": 1.8665,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 1.07,
1153
+ "learning_rate": 0.00014664804469273742,
1154
+ "loss": 1.9021,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 1.07,
1159
+ "learning_rate": 0.0001463687150837989,
1160
+ "loss": 1.7308,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 1.08,
1165
+ "learning_rate": 0.00014608938547486035,
1166
+ "loss": 1.9165,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 1.08,
1171
+ "learning_rate": 0.0001458100558659218,
1172
+ "loss": 1.842,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 1.09,
1177
+ "learning_rate": 0.00014553072625698326,
1178
+ "loss": 1.9128,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 1.09,
1183
+ "learning_rate": 0.0001452513966480447,
1184
+ "loss": 1.8005,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 1.1,
1189
+ "learning_rate": 0.00014497206703910614,
1190
+ "loss": 1.8547,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 1.11,
1195
+ "learning_rate": 0.0001446927374301676,
1196
+ "loss": 1.9042,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 1.11,
1201
+ "learning_rate": 0.00014441340782122905,
1202
+ "loss": 1.8609,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 1.12,
1207
+ "learning_rate": 0.0001441340782122905,
1208
+ "loss": 1.9591,
1209
+ "step": 200
1210
+ },
1211
+ {
1212
+ "epoch": 1.12,
1213
+ "learning_rate": 0.00014385474860335195,
1214
+ "loss": 1.8722,
1215
+ "step": 201
1216
+ },
1217
+ {
1218
+ "epoch": 1.13,
1219
+ "learning_rate": 0.00014357541899441342,
1220
+ "loss": 1.8535,
1221
+ "step": 202
1222
+ },
1223
+ {
1224
+ "epoch": 1.13,
1225
+ "learning_rate": 0.00014329608938547488,
1226
+ "loss": 1.8676,
1227
+ "step": 203
1228
+ },
1229
+ {
1230
+ "epoch": 1.14,
1231
+ "learning_rate": 0.00014301675977653632,
1232
+ "loss": 1.8976,
1233
+ "step": 204
1234
+ },
1235
+ {
1236
+ "epoch": 1.15,
1237
+ "learning_rate": 0.00014273743016759776,
1238
+ "loss": 1.7723,
1239
+ "step": 205
1240
+ },
1241
+ {
1242
+ "epoch": 1.15,
1243
+ "learning_rate": 0.00014245810055865923,
1244
+ "loss": 1.8165,
1245
+ "step": 206
1246
+ },
1247
+ {
1248
+ "epoch": 1.16,
1249
+ "learning_rate": 0.00014217877094972067,
1250
+ "loss": 1.7811,
1251
+ "step": 207
1252
+ },
1253
+ {
1254
+ "epoch": 1.16,
1255
+ "learning_rate": 0.00014189944134078214,
1256
+ "loss": 1.908,
1257
+ "step": 208
1258
+ },
1259
+ {
1260
+ "epoch": 1.17,
1261
+ "learning_rate": 0.00014162011173184357,
1262
+ "loss": 1.7663,
1263
+ "step": 209
1264
+ },
1265
+ {
1266
+ "epoch": 1.17,
1267
+ "learning_rate": 0.00014134078212290501,
1268
+ "loss": 1.6779,
1269
+ "step": 210
1270
+ },
1271
+ {
1272
+ "epoch": 1.18,
1273
+ "learning_rate": 0.0001410614525139665,
1274
+ "loss": 1.9039,
1275
+ "step": 211
1276
+ },
1277
+ {
1278
+ "epoch": 1.18,
1279
+ "learning_rate": 0.00014078212290502795,
1280
+ "loss": 1.8033,
1281
+ "step": 212
1282
+ },
1283
+ {
1284
+ "epoch": 1.19,
1285
+ "learning_rate": 0.00014050279329608939,
1286
+ "loss": 1.8251,
1287
+ "step": 213
1288
+ },
1289
+ {
1290
+ "epoch": 1.2,
1291
+ "learning_rate": 0.00014022346368715085,
1292
+ "loss": 1.8505,
1293
+ "step": 214
1294
+ },
1295
+ {
1296
+ "epoch": 1.2,
1297
+ "learning_rate": 0.0001399441340782123,
1298
+ "loss": 1.8147,
1299
+ "step": 215
1300
+ },
1301
+ {
1302
+ "epoch": 1.21,
1303
+ "learning_rate": 0.00013966480446927376,
1304
+ "loss": 1.8419,
1305
+ "step": 216
1306
+ },
1307
+ {
1308
+ "epoch": 1.21,
1309
+ "learning_rate": 0.0001393854748603352,
1310
+ "loss": 1.8401,
1311
+ "step": 217
1312
+ },
1313
+ {
1314
+ "epoch": 1.22,
1315
+ "learning_rate": 0.00013910614525139664,
1316
+ "loss": 1.8912,
1317
+ "step": 218
1318
+ },
1319
+ {
1320
+ "epoch": 1.22,
1321
+ "learning_rate": 0.0001388268156424581,
1322
+ "loss": 1.7548,
1323
+ "step": 219
1324
+ },
1325
+ {
1326
+ "epoch": 1.23,
1327
+ "learning_rate": 0.00013854748603351957,
1328
+ "loss": 1.8741,
1329
+ "step": 220
1330
+ },
1331
+ {
1332
+ "epoch": 1.23,
1333
+ "learning_rate": 0.000138268156424581,
1334
+ "loss": 1.9549,
1335
+ "step": 221
1336
+ },
1337
+ {
1338
+ "epoch": 1.24,
1339
+ "learning_rate": 0.00013798882681564248,
1340
+ "loss": 1.9093,
1341
+ "step": 222
1342
+ },
1343
+ {
1344
+ "epoch": 1.25,
1345
+ "learning_rate": 0.00013770949720670392,
1346
+ "loss": 1.7896,
1347
+ "step": 223
1348
+ },
1349
+ {
1350
+ "epoch": 1.25,
1351
+ "learning_rate": 0.00013743016759776538,
1352
+ "loss": 1.8491,
1353
+ "step": 224
1354
+ },
1355
+ {
1356
+ "epoch": 1.26,
1357
+ "learning_rate": 0.00013715083798882682,
1358
+ "loss": 1.7851,
1359
+ "step": 225
1360
+ },
1361
+ {
1362
+ "epoch": 1.26,
1363
+ "learning_rate": 0.00013687150837988826,
1364
+ "loss": 1.6992,
1365
+ "step": 226
1366
+ },
1367
+ {
1368
+ "epoch": 1.27,
1369
+ "learning_rate": 0.00013659217877094973,
1370
+ "loss": 1.9765,
1371
+ "step": 227
1372
+ },
1373
+ {
1374
+ "epoch": 1.27,
1375
+ "learning_rate": 0.00013631284916201117,
1376
+ "loss": 1.8179,
1377
+ "step": 228
1378
+ },
1379
+ {
1380
+ "epoch": 1.28,
1381
+ "learning_rate": 0.00013603351955307263,
1382
+ "loss": 1.8548,
1383
+ "step": 229
1384
+ },
1385
+ {
1386
+ "epoch": 1.28,
1387
+ "learning_rate": 0.0001357541899441341,
1388
+ "loss": 1.8843,
1389
+ "step": 230
1390
+ },
1391
+ {
1392
+ "epoch": 1.29,
1393
+ "learning_rate": 0.00013547486033519554,
1394
+ "loss": 1.9105,
1395
+ "step": 231
1396
+ },
1397
+ {
1398
+ "epoch": 1.3,
1399
+ "learning_rate": 0.00013519553072625698,
1400
+ "loss": 1.8748,
1401
+ "step": 232
1402
+ },
1403
+ {
1404
+ "epoch": 1.3,
1405
+ "learning_rate": 0.00013491620111731844,
1406
+ "loss": 1.7976,
1407
+ "step": 233
1408
+ },
1409
+ {
1410
+ "epoch": 1.31,
1411
+ "learning_rate": 0.00013463687150837988,
1412
+ "loss": 1.7369,
1413
+ "step": 234
1414
+ },
1415
+ {
1416
+ "epoch": 1.31,
1417
+ "learning_rate": 0.00013435754189944135,
1418
+ "loss": 1.7808,
1419
+ "step": 235
1420
+ },
1421
+ {
1422
+ "epoch": 1.32,
1423
+ "learning_rate": 0.0001340782122905028,
1424
+ "loss": 1.8385,
1425
+ "step": 236
1426
+ },
1427
+ {
1428
+ "epoch": 1.32,
1429
+ "learning_rate": 0.00013379888268156423,
1430
+ "loss": 1.8295,
1431
+ "step": 237
1432
+ },
1433
+ {
1434
+ "epoch": 1.33,
1435
+ "learning_rate": 0.00013351955307262572,
1436
+ "loss": 1.757,
1437
+ "step": 238
1438
+ },
1439
+ {
1440
+ "epoch": 1.34,
1441
+ "learning_rate": 0.00013324022346368716,
1442
+ "loss": 1.7904,
1443
+ "step": 239
1444
+ },
1445
+ {
1446
+ "epoch": 1.34,
1447
+ "learning_rate": 0.0001329608938547486,
1448
+ "loss": 1.7632,
1449
+ "step": 240
1450
+ },
1451
+ {
1452
+ "epoch": 1.35,
1453
+ "learning_rate": 0.00013268156424581007,
1454
+ "loss": 1.7867,
1455
+ "step": 241
1456
+ },
1457
+ {
1458
+ "epoch": 1.35,
1459
+ "learning_rate": 0.0001324022346368715,
1460
+ "loss": 1.8259,
1461
+ "step": 242
1462
+ },
1463
+ {
1464
+ "epoch": 1.36,
1465
+ "learning_rate": 0.00013212290502793297,
1466
+ "loss": 1.6655,
1467
+ "step": 243
1468
+ },
1469
+ {
1470
+ "epoch": 1.36,
1471
+ "learning_rate": 0.0001318435754189944,
1472
+ "loss": 1.6848,
1473
+ "step": 244
1474
+ },
1475
+ {
1476
+ "epoch": 1.37,
1477
+ "learning_rate": 0.00013156424581005585,
1478
+ "loss": 1.7931,
1479
+ "step": 245
1480
+ },
1481
+ {
1482
+ "epoch": 1.37,
1483
+ "learning_rate": 0.00013128491620111732,
1484
+ "loss": 1.7868,
1485
+ "step": 246
1486
+ },
1487
+ {
1488
+ "epoch": 1.38,
1489
+ "learning_rate": 0.00013100558659217879,
1490
+ "loss": 1.7732,
1491
+ "step": 247
1492
+ },
1493
+ {
1494
+ "epoch": 1.39,
1495
+ "learning_rate": 0.00013072625698324022,
1496
+ "loss": 1.7851,
1497
+ "step": 248
1498
+ },
1499
+ {
1500
+ "epoch": 1.39,
1501
+ "learning_rate": 0.0001304469273743017,
1502
+ "loss": 1.7406,
1503
+ "step": 249
1504
+ },
1505
+ {
1506
+ "epoch": 1.4,
1507
+ "learning_rate": 0.00013016759776536313,
1508
+ "loss": 1.5853,
1509
+ "step": 250
1510
+ },
1511
+ {
1512
+ "epoch": 1.4,
1513
+ "learning_rate": 0.0001298882681564246,
1514
+ "loss": 1.8271,
1515
+ "step": 251
1516
+ },
1517
+ {
1518
+ "epoch": 1.41,
1519
+ "learning_rate": 0.00012960893854748604,
1520
+ "loss": 1.6054,
1521
+ "step": 252
1522
+ },
1523
+ {
1524
+ "epoch": 1.41,
1525
+ "learning_rate": 0.00012932960893854748,
1526
+ "loss": 1.6884,
1527
+ "step": 253
1528
+ },
1529
+ {
1530
+ "epoch": 1.42,
1531
+ "learning_rate": 0.00012905027932960894,
1532
+ "loss": 1.7333,
1533
+ "step": 254
1534
+ },
1535
+ {
1536
+ "epoch": 1.42,
1537
+ "learning_rate": 0.00012877094972067038,
1538
+ "loss": 1.803,
1539
+ "step": 255
1540
+ },
1541
+ {
1542
+ "epoch": 1.43,
1543
+ "learning_rate": 0.00012849162011173185,
1544
+ "loss": 1.63,
1545
+ "step": 256
1546
+ },
1547
+ {
1548
+ "epoch": 1.44,
1549
+ "learning_rate": 0.00012821229050279331,
1550
+ "loss": 1.8023,
1551
+ "step": 257
1552
+ },
1553
+ {
1554
+ "epoch": 1.44,
1555
+ "learning_rate": 0.00012793296089385475,
1556
+ "loss": 1.762,
1557
+ "step": 258
1558
+ },
1559
+ {
1560
+ "epoch": 1.45,
1561
+ "learning_rate": 0.00012765363128491622,
1562
+ "loss": 1.7565,
1563
+ "step": 259
1564
+ },
1565
+ {
1566
+ "epoch": 1.45,
1567
+ "learning_rate": 0.00012737430167597766,
1568
+ "loss": 1.5937,
1569
+ "step": 260
1570
+ },
1571
+ {
1572
+ "epoch": 1.46,
1573
+ "learning_rate": 0.0001270949720670391,
1574
+ "loss": 1.7208,
1575
+ "step": 261
1576
+ },
1577
+ {
1578
+ "epoch": 1.46,
1579
+ "learning_rate": 0.00012681564245810057,
1580
+ "loss": 1.8097,
1581
+ "step": 262
1582
+ },
1583
+ {
1584
+ "epoch": 1.47,
1585
+ "learning_rate": 0.000126536312849162,
1586
+ "loss": 1.7042,
1587
+ "step": 263
1588
+ },
1589
+ {
1590
+ "epoch": 1.47,
1591
+ "learning_rate": 0.00012625698324022347,
1592
+ "loss": 1.7892,
1593
+ "step": 264
1594
+ },
1595
+ {
1596
+ "epoch": 1.48,
1597
+ "learning_rate": 0.00012597765363128494,
1598
+ "loss": 1.752,
1599
+ "step": 265
1600
+ },
1601
+ {
1602
+ "epoch": 1.49,
1603
+ "learning_rate": 0.00012569832402234638,
1604
+ "loss": 1.7333,
1605
+ "step": 266
1606
+ },
1607
+ {
1608
+ "epoch": 1.49,
1609
+ "learning_rate": 0.00012541899441340784,
1610
+ "loss": 1.7492,
1611
+ "step": 267
1612
+ },
1613
+ {
1614
+ "epoch": 1.5,
1615
+ "learning_rate": 0.00012513966480446928,
1616
+ "loss": 1.818,
1617
+ "step": 268
1618
+ },
1619
+ {
1620
+ "epoch": 1.5,
1621
+ "learning_rate": 0.00012486033519553072,
1622
+ "loss": 1.7146,
1623
+ "step": 269
1624
+ },
1625
+ {
1626
+ "epoch": 1.51,
1627
+ "learning_rate": 0.0001245810055865922,
1628
+ "loss": 1.7958,
1629
+ "step": 270
1630
+ },
1631
+ {
1632
+ "epoch": 1.51,
1633
+ "learning_rate": 0.00012430167597765363,
1634
+ "loss": 1.7212,
1635
+ "step": 271
1636
+ },
1637
+ {
1638
+ "epoch": 1.52,
1639
+ "learning_rate": 0.0001240223463687151,
1640
+ "loss": 1.8835,
1641
+ "step": 272
1642
+ },
1643
+ {
1644
+ "epoch": 1.53,
1645
+ "learning_rate": 0.00012374301675977656,
1646
+ "loss": 1.7486,
1647
+ "step": 273
1648
+ },
1649
+ {
1650
+ "epoch": 1.53,
1651
+ "learning_rate": 0.000123463687150838,
1652
+ "loss": 1.8103,
1653
+ "step": 274
1654
+ },
1655
+ {
1656
+ "epoch": 1.54,
1657
+ "learning_rate": 0.00012318435754189944,
1658
+ "loss": 1.7557,
1659
+ "step": 275
1660
+ },
1661
+ {
1662
+ "epoch": 1.54,
1663
+ "learning_rate": 0.0001229050279329609,
1664
+ "loss": 1.6198,
1665
+ "step": 276
1666
+ },
1667
+ {
1668
+ "epoch": 1.55,
1669
+ "learning_rate": 0.00012262569832402235,
1670
+ "loss": 1.6971,
1671
+ "step": 277
1672
+ },
1673
+ {
1674
+ "epoch": 1.55,
1675
+ "learning_rate": 0.0001223463687150838,
1676
+ "loss": 1.668,
1677
+ "step": 278
1678
+ },
1679
+ {
1680
+ "epoch": 1.56,
1681
+ "learning_rate": 0.00012206703910614525,
1682
+ "loss": 1.8795,
1683
+ "step": 279
1684
+ },
1685
+ {
1686
+ "epoch": 1.56,
1687
+ "learning_rate": 0.0001217877094972067,
1688
+ "loss": 1.6412,
1689
+ "step": 280
1690
+ },
1691
+ {
1692
+ "epoch": 1.57,
1693
+ "learning_rate": 0.00012150837988826816,
1694
+ "loss": 1.7497,
1695
+ "step": 281
1696
+ },
1697
+ {
1698
+ "epoch": 1.58,
1699
+ "learning_rate": 0.00012122905027932962,
1700
+ "loss": 1.5577,
1701
+ "step": 282
1702
+ },
1703
+ {
1704
+ "epoch": 1.58,
1705
+ "learning_rate": 0.00012094972067039108,
1706
+ "loss": 1.8049,
1707
+ "step": 283
1708
+ },
1709
+ {
1710
+ "epoch": 1.59,
1711
+ "learning_rate": 0.00012067039106145253,
1712
+ "loss": 1.6834,
1713
+ "step": 284
1714
+ },
1715
+ {
1716
+ "epoch": 1.59,
1717
+ "learning_rate": 0.00012039106145251397,
1718
+ "loss": 1.7978,
1719
+ "step": 285
1720
+ },
1721
+ {
1722
+ "epoch": 1.6,
1723
+ "learning_rate": 0.00012011173184357542,
1724
+ "loss": 1.6558,
1725
+ "step": 286
1726
+ },
1727
+ {
1728
+ "epoch": 1.6,
1729
+ "learning_rate": 0.00011983240223463687,
1730
+ "loss": 1.7561,
1731
+ "step": 287
1732
+ },
1733
+ {
1734
+ "epoch": 1.61,
1735
+ "learning_rate": 0.00011955307262569833,
1736
+ "loss": 1.6807,
1737
+ "step": 288
1738
+ },
1739
+ {
1740
+ "epoch": 1.61,
1741
+ "learning_rate": 0.00011927374301675978,
1742
+ "loss": 1.6937,
1743
+ "step": 289
1744
+ },
1745
+ {
1746
+ "epoch": 1.62,
1747
+ "learning_rate": 0.00011899441340782122,
1748
+ "loss": 1.6591,
1749
+ "step": 290
1750
+ },
1751
+ {
1752
+ "epoch": 1.63,
1753
+ "learning_rate": 0.0001187150837988827,
1754
+ "loss": 1.6771,
1755
+ "step": 291
1756
+ },
1757
+ {
1758
+ "epoch": 1.63,
1759
+ "learning_rate": 0.00011843575418994415,
1760
+ "loss": 1.7743,
1761
+ "step": 292
1762
+ },
1763
+ {
1764
+ "epoch": 1.64,
1765
+ "learning_rate": 0.00011815642458100559,
1766
+ "loss": 1.5857,
1767
+ "step": 293
1768
+ },
1769
+ {
1770
+ "epoch": 1.64,
1771
+ "learning_rate": 0.00011787709497206705,
1772
+ "loss": 1.6999,
1773
+ "step": 294
1774
+ },
1775
+ {
1776
+ "epoch": 1.65,
1777
+ "learning_rate": 0.0001175977653631285,
1778
+ "loss": 1.5661,
1779
+ "step": 295
1780
+ },
1781
+ {
1782
+ "epoch": 1.65,
1783
+ "learning_rate": 0.00011731843575418995,
1784
+ "loss": 1.7235,
1785
+ "step": 296
1786
+ },
1787
+ {
1788
+ "epoch": 1.66,
1789
+ "learning_rate": 0.0001170391061452514,
1790
+ "loss": 1.607,
1791
+ "step": 297
1792
+ },
1793
+ {
1794
+ "epoch": 1.66,
1795
+ "learning_rate": 0.00011675977653631284,
1796
+ "loss": 1.68,
1797
+ "step": 298
1798
+ },
1799
+ {
1800
+ "epoch": 1.67,
1801
+ "learning_rate": 0.0001164804469273743,
1802
+ "loss": 1.6938,
1803
+ "step": 299
1804
+ },
1805
+ {
1806
+ "epoch": 1.68,
1807
+ "learning_rate": 0.00011620111731843578,
1808
+ "loss": 1.6315,
1809
+ "step": 300
1810
+ }
1811
+ ],
1812
+ "logging_steps": 1,
1813
+ "max_steps": 716,
1814
+ "num_train_epochs": 4,
1815
+ "save_steps": 100,
1816
+ "total_flos": 1.5369996759656448e+17,
1817
+ "trial_name": null,
1818
+ "trial_params": null
1819
+ }
checkpoint-300/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:188ae1c421cc0c6435d1f71d8d3423ac4abc7dba0e6fc2efcbc4dbe77c741317
3
+ size 4027
checkpoint-400/README.md ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: True
10
+ - load_in_4bit: False
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: fp4
16
+ - bnb_4bit_use_double_quant: False
17
+ - bnb_4bit_compute_dtype: float32
18
+
19
+ The following `bitsandbytes` quantization config was used during training:
20
+ - quant_method: bitsandbytes
21
+ - load_in_8bit: True
22
+ - load_in_4bit: False
23
+ - llm_int8_threshold: 6.0
24
+ - llm_int8_skip_modules: None
25
+ - llm_int8_enable_fp32_cpu_offload: False
26
+ - llm_int8_has_fp16_weight: False
27
+ - bnb_4bit_quant_type: fp4
28
+ - bnb_4bit_use_double_quant: False
29
+ - bnb_4bit_compute_dtype: float32
30
+
31
+ The following `bitsandbytes` quantization config was used during training:
32
+ - quant_method: bitsandbytes
33
+ - load_in_8bit: True
34
+ - load_in_4bit: False
35
+ - llm_int8_threshold: 6.0
36
+ - llm_int8_skip_modules: None
37
+ - llm_int8_enable_fp32_cpu_offload: False
38
+ - llm_int8_has_fp16_weight: False
39
+ - bnb_4bit_quant_type: fp4
40
+ - bnb_4bit_use_double_quant: False
41
+ - bnb_4bit_compute_dtype: float32
42
+
43
+ The following `bitsandbytes` quantization config was used during training:
44
+ - quant_method: bitsandbytes
45
+ - load_in_8bit: True
46
+ - load_in_4bit: False
47
+ - llm_int8_threshold: 6.0
48
+ - llm_int8_skip_modules: None
49
+ - llm_int8_enable_fp32_cpu_offload: False
50
+ - llm_int8_has_fp16_weight: False
51
+ - bnb_4bit_quant_type: fp4
52
+ - bnb_4bit_use_double_quant: False
53
+ - bnb_4bit_compute_dtype: float32
54
+ ### Framework versions
55
+
56
+ - PEFT 0.6.0.dev0
57
+ - PEFT 0.6.0.dev0
58
+ - PEFT 0.6.0.dev0
59
+
60
+ - PEFT 0.6.0.dev0
checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "bigscience/bloomz-3b",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "lora_alpha": 16,
12
+ "lora_dropout": 0.0,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 8,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "dense_4h_to_h",
20
+ "dense",
21
+ "dense_h_to_4h",
22
+ "query_key_value"
23
+ ],
24
+ "task_type": "CAUSAL_LM"
25
+ }
checkpoint-400/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7b701342ea311c1e25f0f6953505f048df3f56027dc5c764b95df4491bfde1c
3
+ size 39409357
checkpoint-400/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da79792a601e6737b980ff24e453353405dce9a807a0964433ac96d5a97b84aa
3
+ size 78844421
checkpoint-400/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7508d4b8dd267de5cc58e972da25236687927651336a28f292c92f7f23951475
3
+ size 14575
checkpoint-400/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04fdaf305b17644f9d215d28be45b77e6d0f8e4b5adc1c7045c50a61bd8f3c5b
3
+ size 627
checkpoint-400/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
checkpoint-400/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85b00d7db4df5df2e3f01cacc3feda246002a672f3356eec7f4b04a22eb0dfbe
3
+ size 14500570
checkpoint-400/tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "<pad>",
8
+ "tokenizer_class": "BloomTokenizer",
9
+ "unk_token": "<unk>"
10
+ }
checkpoint-400/trainer_state.json ADDED
@@ -0,0 +1,2419 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.2346368715083798,
5
+ "eval_steps": 500,
6
+ "global_step": 400,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 0.00019972067039106145,
14
+ "loss": 2.6443,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 0.00019944134078212292,
20
+ "loss": 2.4104,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.02,
25
+ "learning_rate": 0.00019916201117318435,
26
+ "loss": 2.4975,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.02,
31
+ "learning_rate": 0.00019888268156424582,
32
+ "loss": 2.3513,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.03,
37
+ "learning_rate": 0.0001986033519553073,
38
+ "loss": 2.4274,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.03,
43
+ "learning_rate": 0.00019832402234636873,
44
+ "loss": 2.3628,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.04,
49
+ "learning_rate": 0.0001980446927374302,
50
+ "loss": 2.3567,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.04,
55
+ "learning_rate": 0.00019776536312849163,
56
+ "loss": 2.4121,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.05,
61
+ "learning_rate": 0.00019748603351955307,
62
+ "loss": 2.4033,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.06,
67
+ "learning_rate": 0.00019720670391061454,
68
+ "loss": 2.2805,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.06,
73
+ "learning_rate": 0.00019692737430167598,
74
+ "loss": 2.2639,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.07,
79
+ "learning_rate": 0.00019664804469273744,
80
+ "loss": 2.2724,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.07,
85
+ "learning_rate": 0.00019636871508379888,
86
+ "loss": 2.332,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.08,
91
+ "learning_rate": 0.00019608938547486035,
92
+ "loss": 2.2261,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.08,
97
+ "learning_rate": 0.00019581005586592182,
98
+ "loss": 2.2208,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.09,
103
+ "learning_rate": 0.00019553072625698326,
104
+ "loss": 2.3351,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.09,
109
+ "learning_rate": 0.0001952513966480447,
110
+ "loss": 2.2475,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.1,
115
+ "learning_rate": 0.00019497206703910616,
116
+ "loss": 2.3283,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.11,
121
+ "learning_rate": 0.0001946927374301676,
122
+ "loss": 2.1346,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.11,
127
+ "learning_rate": 0.00019441340782122907,
128
+ "loss": 2.131,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.12,
133
+ "learning_rate": 0.0001941340782122905,
134
+ "loss": 2.1718,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.12,
139
+ "learning_rate": 0.00019385474860335195,
140
+ "loss": 2.2446,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.13,
145
+ "learning_rate": 0.0001935754189944134,
146
+ "loss": 2.306,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.13,
151
+ "learning_rate": 0.00019329608938547488,
152
+ "loss": 2.1908,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.14,
157
+ "learning_rate": 0.00019301675977653632,
158
+ "loss": 2.2844,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.15,
163
+ "learning_rate": 0.00019273743016759779,
164
+ "loss": 2.2235,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.15,
169
+ "learning_rate": 0.00019245810055865922,
170
+ "loss": 2.1842,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.16,
175
+ "learning_rate": 0.00019217877094972066,
176
+ "loss": 2.2675,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.16,
181
+ "learning_rate": 0.00019189944134078213,
182
+ "loss": 2.2532,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.17,
187
+ "learning_rate": 0.00019162011173184357,
188
+ "loss": 2.1788,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.17,
193
+ "learning_rate": 0.00019134078212290504,
194
+ "loss": 2.2494,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.18,
199
+ "learning_rate": 0.0001910614525139665,
200
+ "loss": 2.1995,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.18,
205
+ "learning_rate": 0.00019078212290502794,
206
+ "loss": 2.1451,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.19,
211
+ "learning_rate": 0.0001905027932960894,
212
+ "loss": 2.223,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.2,
217
+ "learning_rate": 0.00019022346368715085,
218
+ "loss": 2.2854,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.2,
223
+ "learning_rate": 0.0001899441340782123,
224
+ "loss": 2.2265,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.21,
229
+ "learning_rate": 0.00018966480446927375,
230
+ "loss": 2.1214,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.21,
235
+ "learning_rate": 0.0001893854748603352,
236
+ "loss": 2.1898,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.22,
241
+ "learning_rate": 0.00018910614525139666,
242
+ "loss": 2.1974,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.22,
247
+ "learning_rate": 0.0001888268156424581,
248
+ "loss": 2.2259,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.23,
253
+ "learning_rate": 0.00018854748603351957,
254
+ "loss": 2.2094,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.23,
259
+ "learning_rate": 0.00018826815642458103,
260
+ "loss": 2.1731,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.24,
265
+ "learning_rate": 0.00018798882681564247,
266
+ "loss": 2.2373,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.25,
271
+ "learning_rate": 0.0001877094972067039,
272
+ "loss": 2.2295,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.25,
277
+ "learning_rate": 0.00018743016759776538,
278
+ "loss": 2.1947,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.26,
283
+ "learning_rate": 0.00018715083798882682,
284
+ "loss": 2.2115,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.26,
289
+ "learning_rate": 0.00018687150837988828,
290
+ "loss": 2.1224,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.27,
295
+ "learning_rate": 0.00018659217877094972,
296
+ "loss": 2.2137,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.27,
301
+ "learning_rate": 0.00018631284916201116,
302
+ "loss": 2.2338,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.28,
307
+ "learning_rate": 0.00018603351955307266,
308
+ "loss": 2.1298,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.28,
313
+ "learning_rate": 0.0001857541899441341,
314
+ "loss": 2.0883,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.29,
319
+ "learning_rate": 0.00018547486033519553,
320
+ "loss": 2.1216,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.3,
325
+ "learning_rate": 0.000185195530726257,
326
+ "loss": 2.2112,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.3,
331
+ "learning_rate": 0.00018491620111731844,
332
+ "loss": 2.1224,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.31,
337
+ "learning_rate": 0.0001846368715083799,
338
+ "loss": 2.2375,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.31,
343
+ "learning_rate": 0.00018435754189944135,
344
+ "loss": 2.2235,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.32,
349
+ "learning_rate": 0.00018407821229050279,
350
+ "loss": 2.1682,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.32,
355
+ "learning_rate": 0.00018379888268156425,
356
+ "loss": 2.2077,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.33,
361
+ "learning_rate": 0.00018351955307262572,
362
+ "loss": 2.1596,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.34,
367
+ "learning_rate": 0.00018324022346368716,
368
+ "loss": 2.1311,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.34,
373
+ "learning_rate": 0.00018296089385474862,
374
+ "loss": 2.1333,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.35,
379
+ "learning_rate": 0.00018268156424581006,
380
+ "loss": 2.0901,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.35,
385
+ "learning_rate": 0.00018240223463687153,
386
+ "loss": 2.1971,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.36,
391
+ "learning_rate": 0.00018212290502793297,
392
+ "loss": 2.2602,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.36,
397
+ "learning_rate": 0.0001818435754189944,
398
+ "loss": 2.2194,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.37,
403
+ "learning_rate": 0.00018156424581005588,
404
+ "loss": 2.1218,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.37,
409
+ "learning_rate": 0.00018128491620111731,
410
+ "loss": 2.2049,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.38,
415
+ "learning_rate": 0.00018100558659217878,
416
+ "loss": 2.1521,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.39,
421
+ "learning_rate": 0.00018072625698324025,
422
+ "loss": 2.112,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.39,
427
+ "learning_rate": 0.0001804469273743017,
428
+ "loss": 2.1906,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.4,
433
+ "learning_rate": 0.00018016759776536313,
434
+ "loss": 2.1717,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.4,
439
+ "learning_rate": 0.0001798882681564246,
440
+ "loss": 2.0712,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.41,
445
+ "learning_rate": 0.00017960893854748603,
446
+ "loss": 2.141,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.41,
451
+ "learning_rate": 0.0001793296089385475,
452
+ "loss": 2.0656,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.42,
457
+ "learning_rate": 0.00017905027932960894,
458
+ "loss": 2.1125,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.42,
463
+ "learning_rate": 0.00017877094972067038,
464
+ "loss": 2.0869,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.43,
469
+ "learning_rate": 0.00017849162011173187,
470
+ "loss": 2.2478,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.44,
475
+ "learning_rate": 0.0001782122905027933,
476
+ "loss": 2.1535,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.44,
481
+ "learning_rate": 0.00017793296089385475,
482
+ "loss": 2.1927,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.45,
487
+ "learning_rate": 0.00017765363128491622,
488
+ "loss": 2.1213,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.45,
493
+ "learning_rate": 0.00017737430167597766,
494
+ "loss": 2.0981,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.46,
499
+ "learning_rate": 0.00017709497206703912,
500
+ "loss": 2.1828,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.46,
505
+ "learning_rate": 0.00017681564245810056,
506
+ "loss": 2.0562,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.47,
511
+ "learning_rate": 0.000176536312849162,
512
+ "loss": 2.1334,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.47,
517
+ "learning_rate": 0.00017625698324022347,
518
+ "loss": 2.1225,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.48,
523
+ "learning_rate": 0.00017597765363128493,
524
+ "loss": 2.2098,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.49,
529
+ "learning_rate": 0.00017569832402234637,
530
+ "loss": 2.1519,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.49,
535
+ "learning_rate": 0.00017541899441340784,
536
+ "loss": 2.1132,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.5,
541
+ "learning_rate": 0.00017513966480446928,
542
+ "loss": 2.0333,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.5,
547
+ "learning_rate": 0.00017486033519553075,
548
+ "loss": 2.2764,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.51,
553
+ "learning_rate": 0.00017458100558659218,
554
+ "loss": 2.1838,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.51,
559
+ "learning_rate": 0.00017430167597765362,
560
+ "loss": 2.1386,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.52,
565
+ "learning_rate": 0.0001740223463687151,
566
+ "loss": 2.1034,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.53,
571
+ "learning_rate": 0.00017374301675977656,
572
+ "loss": 2.0346,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.53,
577
+ "learning_rate": 0.000173463687150838,
578
+ "loss": 2.0274,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.54,
583
+ "learning_rate": 0.00017318435754189946,
584
+ "loss": 2.1036,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.54,
589
+ "learning_rate": 0.0001729050279329609,
590
+ "loss": 2.1208,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.55,
595
+ "learning_rate": 0.00017262569832402237,
596
+ "loss": 2.0572,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.55,
601
+ "learning_rate": 0.0001723463687150838,
602
+ "loss": 2.1702,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.56,
607
+ "learning_rate": 0.00017206703910614525,
608
+ "loss": 2.1302,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 0.56,
613
+ "learning_rate": 0.0001717877094972067,
614
+ "loss": 2.0175,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 0.57,
619
+ "learning_rate": 0.00017150837988826815,
620
+ "loss": 2.1006,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 0.58,
625
+ "learning_rate": 0.00017122905027932962,
626
+ "loss": 2.0662,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 0.58,
631
+ "learning_rate": 0.00017094972067039109,
632
+ "loss": 1.988,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 0.59,
637
+ "learning_rate": 0.00017067039106145253,
638
+ "loss": 2.1008,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 0.59,
643
+ "learning_rate": 0.00017039106145251396,
644
+ "loss": 2.1482,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 0.6,
649
+ "learning_rate": 0.00017011173184357543,
650
+ "loss": 2.1052,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 0.6,
655
+ "learning_rate": 0.00016983240223463687,
656
+ "loss": 2.0978,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 0.61,
661
+ "learning_rate": 0.00016955307262569834,
662
+ "loss": 2.1303,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 0.61,
667
+ "learning_rate": 0.00016927374301675978,
668
+ "loss": 2.0794,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 0.62,
673
+ "learning_rate": 0.00016899441340782122,
674
+ "loss": 2.1059,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 0.63,
679
+ "learning_rate": 0.0001687150837988827,
680
+ "loss": 1.9642,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 0.63,
685
+ "learning_rate": 0.00016843575418994415,
686
+ "loss": 2.0415,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 0.64,
691
+ "learning_rate": 0.0001681564245810056,
692
+ "loss": 2.0795,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 0.64,
697
+ "learning_rate": 0.00016787709497206705,
698
+ "loss": 2.0238,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 0.65,
703
+ "learning_rate": 0.0001675977653631285,
704
+ "loss": 2.078,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 0.65,
709
+ "learning_rate": 0.00016731843575418996,
710
+ "loss": 2.1362,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 0.66,
715
+ "learning_rate": 0.0001670391061452514,
716
+ "loss": 2.0552,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 0.66,
721
+ "learning_rate": 0.00016675977653631284,
722
+ "loss": 2.213,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 0.67,
727
+ "learning_rate": 0.0001664804469273743,
728
+ "loss": 1.9999,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 0.68,
733
+ "learning_rate": 0.00016620111731843577,
734
+ "loss": 2.06,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 0.68,
739
+ "learning_rate": 0.0001659217877094972,
740
+ "loss": 2.0177,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 0.69,
745
+ "learning_rate": 0.00016564245810055868,
746
+ "loss": 2.0504,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 0.69,
751
+ "learning_rate": 0.00016536312849162012,
752
+ "loss": 2.0585,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 0.7,
757
+ "learning_rate": 0.00016508379888268158,
758
+ "loss": 2.0273,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 0.7,
763
+ "learning_rate": 0.00016480446927374302,
764
+ "loss": 2.0549,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 0.71,
769
+ "learning_rate": 0.00016452513966480446,
770
+ "loss": 2.044,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 0.72,
775
+ "learning_rate": 0.00016424581005586593,
776
+ "loss": 2.0731,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 0.72,
781
+ "learning_rate": 0.00016396648044692737,
782
+ "loss": 2.0568,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 0.73,
787
+ "learning_rate": 0.00016368715083798883,
788
+ "loss": 2.007,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 0.73,
793
+ "learning_rate": 0.0001634078212290503,
794
+ "loss": 2.0707,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 0.74,
799
+ "learning_rate": 0.00016312849162011174,
800
+ "loss": 1.9793,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 0.74,
805
+ "learning_rate": 0.0001628491620111732,
806
+ "loss": 2.1311,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 0.75,
811
+ "learning_rate": 0.00016256983240223465,
812
+ "loss": 2.0016,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 0.75,
817
+ "learning_rate": 0.00016229050279329609,
818
+ "loss": 1.9945,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 0.76,
823
+ "learning_rate": 0.00016201117318435755,
824
+ "loss": 2.0186,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 0.77,
829
+ "learning_rate": 0.000161731843575419,
830
+ "loss": 2.0971,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 0.77,
835
+ "learning_rate": 0.00016145251396648046,
836
+ "loss": 2.0883,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 0.78,
841
+ "learning_rate": 0.00016117318435754192,
842
+ "loss": 2.0803,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 0.78,
847
+ "learning_rate": 0.00016089385474860336,
848
+ "loss": 2.0617,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.79,
853
+ "learning_rate": 0.00016061452513966483,
854
+ "loss": 2.1265,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.79,
859
+ "learning_rate": 0.00016033519553072627,
860
+ "loss": 2.0151,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.8,
865
+ "learning_rate": 0.0001600558659217877,
866
+ "loss": 1.996,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.8,
871
+ "learning_rate": 0.00015977653631284918,
872
+ "loss": 2.0164,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.81,
877
+ "learning_rate": 0.00015949720670391061,
878
+ "loss": 2.0314,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 0.82,
883
+ "learning_rate": 0.00015921787709497208,
884
+ "loss": 1.9501,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 0.82,
889
+ "learning_rate": 0.00015893854748603352,
890
+ "loss": 2.087,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 0.83,
895
+ "learning_rate": 0.000158659217877095,
896
+ "loss": 2.0262,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 0.83,
901
+ "learning_rate": 0.00015837988826815643,
902
+ "loss": 2.0765,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 0.84,
907
+ "learning_rate": 0.0001581005586592179,
908
+ "loss": 2.105,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 0.84,
913
+ "learning_rate": 0.00015782122905027933,
914
+ "loss": 1.9863,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 0.85,
919
+ "learning_rate": 0.0001575418994413408,
920
+ "loss": 1.9873,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 0.85,
925
+ "learning_rate": 0.00015726256983240224,
926
+ "loss": 2.0094,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 0.86,
931
+ "learning_rate": 0.00015698324022346368,
932
+ "loss": 1.9141,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 0.87,
937
+ "learning_rate": 0.00015670391061452514,
938
+ "loss": 1.917,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 0.87,
943
+ "learning_rate": 0.00015642458100558658,
944
+ "loss": 2.109,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 0.88,
949
+ "learning_rate": 0.00015614525139664805,
950
+ "loss": 1.9799,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 0.88,
955
+ "learning_rate": 0.00015586592178770952,
956
+ "loss": 1.9571,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 0.89,
961
+ "learning_rate": 0.00015558659217877096,
962
+ "loss": 1.9931,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 0.89,
967
+ "learning_rate": 0.00015530726256983242,
968
+ "loss": 2.1004,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 0.9,
973
+ "learning_rate": 0.00015502793296089386,
974
+ "loss": 2.0385,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 0.91,
979
+ "learning_rate": 0.0001547486033519553,
980
+ "loss": 1.9751,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 0.91,
985
+ "learning_rate": 0.00015446927374301677,
986
+ "loss": 2.0544,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 0.92,
991
+ "learning_rate": 0.0001541899441340782,
992
+ "loss": 2.0069,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 0.92,
997
+ "learning_rate": 0.00015391061452513967,
998
+ "loss": 1.9576,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 0.93,
1003
+ "learning_rate": 0.00015363128491620114,
1004
+ "loss": 1.8991,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 0.93,
1009
+ "learning_rate": 0.00015335195530726258,
1010
+ "loss": 1.9336,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 0.94,
1015
+ "learning_rate": 0.00015307262569832405,
1016
+ "loss": 1.9736,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 0.94,
1021
+ "learning_rate": 0.00015279329608938548,
1022
+ "loss": 1.9702,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 0.95,
1027
+ "learning_rate": 0.00015251396648044692,
1028
+ "loss": 1.9055,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 0.96,
1033
+ "learning_rate": 0.0001522346368715084,
1034
+ "loss": 2.0503,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 0.96,
1039
+ "learning_rate": 0.00015195530726256983,
1040
+ "loss": 2.0039,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 0.97,
1045
+ "learning_rate": 0.0001516759776536313,
1046
+ "loss": 1.9406,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 0.97,
1051
+ "learning_rate": 0.00015139664804469274,
1052
+ "loss": 2.0525,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 0.98,
1057
+ "learning_rate": 0.0001511173184357542,
1058
+ "loss": 1.9234,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 0.98,
1063
+ "learning_rate": 0.00015083798882681567,
1064
+ "loss": 1.8614,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 0.99,
1069
+ "learning_rate": 0.0001505586592178771,
1070
+ "loss": 1.9616,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 0.99,
1075
+ "learning_rate": 0.00015027932960893855,
1076
+ "loss": 1.9509,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 1.0,
1081
+ "learning_rate": 0.00015000000000000001,
1082
+ "loss": 1.9592,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 1.01,
1087
+ "learning_rate": 0.00014972067039106145,
1088
+ "loss": 1.8991,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 1.01,
1093
+ "learning_rate": 0.00014944134078212292,
1094
+ "loss": 1.9127,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 1.02,
1099
+ "learning_rate": 0.00014916201117318436,
1100
+ "loss": 1.8982,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 1.02,
1105
+ "learning_rate": 0.0001488826815642458,
1106
+ "loss": 1.9534,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 1.03,
1111
+ "learning_rate": 0.0001486033519553073,
1112
+ "loss": 1.7794,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 1.03,
1117
+ "learning_rate": 0.00014832402234636873,
1118
+ "loss": 1.7958,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 1.04,
1123
+ "learning_rate": 0.00014804469273743017,
1124
+ "loss": 1.8282,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 1.04,
1129
+ "learning_rate": 0.00014776536312849164,
1130
+ "loss": 2.0423,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 1.05,
1135
+ "learning_rate": 0.00014748603351955308,
1136
+ "loss": 1.9282,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 1.06,
1141
+ "learning_rate": 0.00014720670391061454,
1142
+ "loss": 1.9072,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 1.06,
1147
+ "learning_rate": 0.00014692737430167598,
1148
+ "loss": 1.8665,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 1.07,
1153
+ "learning_rate": 0.00014664804469273742,
1154
+ "loss": 1.9021,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 1.07,
1159
+ "learning_rate": 0.0001463687150837989,
1160
+ "loss": 1.7308,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 1.08,
1165
+ "learning_rate": 0.00014608938547486035,
1166
+ "loss": 1.9165,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 1.08,
1171
+ "learning_rate": 0.0001458100558659218,
1172
+ "loss": 1.842,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 1.09,
1177
+ "learning_rate": 0.00014553072625698326,
1178
+ "loss": 1.9128,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 1.09,
1183
+ "learning_rate": 0.0001452513966480447,
1184
+ "loss": 1.8005,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 1.1,
1189
+ "learning_rate": 0.00014497206703910614,
1190
+ "loss": 1.8547,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 1.11,
1195
+ "learning_rate": 0.0001446927374301676,
1196
+ "loss": 1.9042,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 1.11,
1201
+ "learning_rate": 0.00014441340782122905,
1202
+ "loss": 1.8609,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 1.12,
1207
+ "learning_rate": 0.0001441340782122905,
1208
+ "loss": 1.9591,
1209
+ "step": 200
1210
+ },
1211
+ {
1212
+ "epoch": 1.12,
1213
+ "learning_rate": 0.00014385474860335195,
1214
+ "loss": 1.8722,
1215
+ "step": 201
1216
+ },
1217
+ {
1218
+ "epoch": 1.13,
1219
+ "learning_rate": 0.00014357541899441342,
1220
+ "loss": 1.8535,
1221
+ "step": 202
1222
+ },
1223
+ {
1224
+ "epoch": 1.13,
1225
+ "learning_rate": 0.00014329608938547488,
1226
+ "loss": 1.8676,
1227
+ "step": 203
1228
+ },
1229
+ {
1230
+ "epoch": 1.14,
1231
+ "learning_rate": 0.00014301675977653632,
1232
+ "loss": 1.8976,
1233
+ "step": 204
1234
+ },
1235
+ {
1236
+ "epoch": 1.15,
1237
+ "learning_rate": 0.00014273743016759776,
1238
+ "loss": 1.7723,
1239
+ "step": 205
1240
+ },
1241
+ {
1242
+ "epoch": 1.15,
1243
+ "learning_rate": 0.00014245810055865923,
1244
+ "loss": 1.8165,
1245
+ "step": 206
1246
+ },
1247
+ {
1248
+ "epoch": 1.16,
1249
+ "learning_rate": 0.00014217877094972067,
1250
+ "loss": 1.7811,
1251
+ "step": 207
1252
+ },
1253
+ {
1254
+ "epoch": 1.16,
1255
+ "learning_rate": 0.00014189944134078214,
1256
+ "loss": 1.908,
1257
+ "step": 208
1258
+ },
1259
+ {
1260
+ "epoch": 1.17,
1261
+ "learning_rate": 0.00014162011173184357,
1262
+ "loss": 1.7663,
1263
+ "step": 209
1264
+ },
1265
+ {
1266
+ "epoch": 1.17,
1267
+ "learning_rate": 0.00014134078212290501,
1268
+ "loss": 1.6779,
1269
+ "step": 210
1270
+ },
1271
+ {
1272
+ "epoch": 1.18,
1273
+ "learning_rate": 0.0001410614525139665,
1274
+ "loss": 1.9039,
1275
+ "step": 211
1276
+ },
1277
+ {
1278
+ "epoch": 1.18,
1279
+ "learning_rate": 0.00014078212290502795,
1280
+ "loss": 1.8033,
1281
+ "step": 212
1282
+ },
1283
+ {
1284
+ "epoch": 1.19,
1285
+ "learning_rate": 0.00014050279329608939,
1286
+ "loss": 1.8251,
1287
+ "step": 213
1288
+ },
1289
+ {
1290
+ "epoch": 1.2,
1291
+ "learning_rate": 0.00014022346368715085,
1292
+ "loss": 1.8505,
1293
+ "step": 214
1294
+ },
1295
+ {
1296
+ "epoch": 1.2,
1297
+ "learning_rate": 0.0001399441340782123,
1298
+ "loss": 1.8147,
1299
+ "step": 215
1300
+ },
1301
+ {
1302
+ "epoch": 1.21,
1303
+ "learning_rate": 0.00013966480446927376,
1304
+ "loss": 1.8419,
1305
+ "step": 216
1306
+ },
1307
+ {
1308
+ "epoch": 1.21,
1309
+ "learning_rate": 0.0001393854748603352,
1310
+ "loss": 1.8401,
1311
+ "step": 217
1312
+ },
1313
+ {
1314
+ "epoch": 1.22,
1315
+ "learning_rate": 0.00013910614525139664,
1316
+ "loss": 1.8912,
1317
+ "step": 218
1318
+ },
1319
+ {
1320
+ "epoch": 1.22,
1321
+ "learning_rate": 0.0001388268156424581,
1322
+ "loss": 1.7548,
1323
+ "step": 219
1324
+ },
1325
+ {
1326
+ "epoch": 1.23,
1327
+ "learning_rate": 0.00013854748603351957,
1328
+ "loss": 1.8741,
1329
+ "step": 220
1330
+ },
1331
+ {
1332
+ "epoch": 1.23,
1333
+ "learning_rate": 0.000138268156424581,
1334
+ "loss": 1.9549,
1335
+ "step": 221
1336
+ },
1337
+ {
1338
+ "epoch": 1.24,
1339
+ "learning_rate": 0.00013798882681564248,
1340
+ "loss": 1.9093,
1341
+ "step": 222
1342
+ },
1343
+ {
1344
+ "epoch": 1.25,
1345
+ "learning_rate": 0.00013770949720670392,
1346
+ "loss": 1.7896,
1347
+ "step": 223
1348
+ },
1349
+ {
1350
+ "epoch": 1.25,
1351
+ "learning_rate": 0.00013743016759776538,
1352
+ "loss": 1.8491,
1353
+ "step": 224
1354
+ },
1355
+ {
1356
+ "epoch": 1.26,
1357
+ "learning_rate": 0.00013715083798882682,
1358
+ "loss": 1.7851,
1359
+ "step": 225
1360
+ },
1361
+ {
1362
+ "epoch": 1.26,
1363
+ "learning_rate": 0.00013687150837988826,
1364
+ "loss": 1.6992,
1365
+ "step": 226
1366
+ },
1367
+ {
1368
+ "epoch": 1.27,
1369
+ "learning_rate": 0.00013659217877094973,
1370
+ "loss": 1.9765,
1371
+ "step": 227
1372
+ },
1373
+ {
1374
+ "epoch": 1.27,
1375
+ "learning_rate": 0.00013631284916201117,
1376
+ "loss": 1.8179,
1377
+ "step": 228
1378
+ },
1379
+ {
1380
+ "epoch": 1.28,
1381
+ "learning_rate": 0.00013603351955307263,
1382
+ "loss": 1.8548,
1383
+ "step": 229
1384
+ },
1385
+ {
1386
+ "epoch": 1.28,
1387
+ "learning_rate": 0.0001357541899441341,
1388
+ "loss": 1.8843,
1389
+ "step": 230
1390
+ },
1391
+ {
1392
+ "epoch": 1.29,
1393
+ "learning_rate": 0.00013547486033519554,
1394
+ "loss": 1.9105,
1395
+ "step": 231
1396
+ },
1397
+ {
1398
+ "epoch": 1.3,
1399
+ "learning_rate": 0.00013519553072625698,
1400
+ "loss": 1.8748,
1401
+ "step": 232
1402
+ },
1403
+ {
1404
+ "epoch": 1.3,
1405
+ "learning_rate": 0.00013491620111731844,
1406
+ "loss": 1.7976,
1407
+ "step": 233
1408
+ },
1409
+ {
1410
+ "epoch": 1.31,
1411
+ "learning_rate": 0.00013463687150837988,
1412
+ "loss": 1.7369,
1413
+ "step": 234
1414
+ },
1415
+ {
1416
+ "epoch": 1.31,
1417
+ "learning_rate": 0.00013435754189944135,
1418
+ "loss": 1.7808,
1419
+ "step": 235
1420
+ },
1421
+ {
1422
+ "epoch": 1.32,
1423
+ "learning_rate": 0.0001340782122905028,
1424
+ "loss": 1.8385,
1425
+ "step": 236
1426
+ },
1427
+ {
1428
+ "epoch": 1.32,
1429
+ "learning_rate": 0.00013379888268156423,
1430
+ "loss": 1.8295,
1431
+ "step": 237
1432
+ },
1433
+ {
1434
+ "epoch": 1.33,
1435
+ "learning_rate": 0.00013351955307262572,
1436
+ "loss": 1.757,
1437
+ "step": 238
1438
+ },
1439
+ {
1440
+ "epoch": 1.34,
1441
+ "learning_rate": 0.00013324022346368716,
1442
+ "loss": 1.7904,
1443
+ "step": 239
1444
+ },
1445
+ {
1446
+ "epoch": 1.34,
1447
+ "learning_rate": 0.0001329608938547486,
1448
+ "loss": 1.7632,
1449
+ "step": 240
1450
+ },
1451
+ {
1452
+ "epoch": 1.35,
1453
+ "learning_rate": 0.00013268156424581007,
1454
+ "loss": 1.7867,
1455
+ "step": 241
1456
+ },
1457
+ {
1458
+ "epoch": 1.35,
1459
+ "learning_rate": 0.0001324022346368715,
1460
+ "loss": 1.8259,
1461
+ "step": 242
1462
+ },
1463
+ {
1464
+ "epoch": 1.36,
1465
+ "learning_rate": 0.00013212290502793297,
1466
+ "loss": 1.6655,
1467
+ "step": 243
1468
+ },
1469
+ {
1470
+ "epoch": 1.36,
1471
+ "learning_rate": 0.0001318435754189944,
1472
+ "loss": 1.6848,
1473
+ "step": 244
1474
+ },
1475
+ {
1476
+ "epoch": 1.37,
1477
+ "learning_rate": 0.00013156424581005585,
1478
+ "loss": 1.7931,
1479
+ "step": 245
1480
+ },
1481
+ {
1482
+ "epoch": 1.37,
1483
+ "learning_rate": 0.00013128491620111732,
1484
+ "loss": 1.7868,
1485
+ "step": 246
1486
+ },
1487
+ {
1488
+ "epoch": 1.38,
1489
+ "learning_rate": 0.00013100558659217879,
1490
+ "loss": 1.7732,
1491
+ "step": 247
1492
+ },
1493
+ {
1494
+ "epoch": 1.39,
1495
+ "learning_rate": 0.00013072625698324022,
1496
+ "loss": 1.7851,
1497
+ "step": 248
1498
+ },
1499
+ {
1500
+ "epoch": 1.39,
1501
+ "learning_rate": 0.0001304469273743017,
1502
+ "loss": 1.7406,
1503
+ "step": 249
1504
+ },
1505
+ {
1506
+ "epoch": 1.4,
1507
+ "learning_rate": 0.00013016759776536313,
1508
+ "loss": 1.5853,
1509
+ "step": 250
1510
+ },
1511
+ {
1512
+ "epoch": 1.4,
1513
+ "learning_rate": 0.0001298882681564246,
1514
+ "loss": 1.8271,
1515
+ "step": 251
1516
+ },
1517
+ {
1518
+ "epoch": 1.41,
1519
+ "learning_rate": 0.00012960893854748604,
1520
+ "loss": 1.6054,
1521
+ "step": 252
1522
+ },
1523
+ {
1524
+ "epoch": 1.41,
1525
+ "learning_rate": 0.00012932960893854748,
1526
+ "loss": 1.6884,
1527
+ "step": 253
1528
+ },
1529
+ {
1530
+ "epoch": 1.42,
1531
+ "learning_rate": 0.00012905027932960894,
1532
+ "loss": 1.7333,
1533
+ "step": 254
1534
+ },
1535
+ {
1536
+ "epoch": 1.42,
1537
+ "learning_rate": 0.00012877094972067038,
1538
+ "loss": 1.803,
1539
+ "step": 255
1540
+ },
1541
+ {
1542
+ "epoch": 1.43,
1543
+ "learning_rate": 0.00012849162011173185,
1544
+ "loss": 1.63,
1545
+ "step": 256
1546
+ },
1547
+ {
1548
+ "epoch": 1.44,
1549
+ "learning_rate": 0.00012821229050279331,
1550
+ "loss": 1.8023,
1551
+ "step": 257
1552
+ },
1553
+ {
1554
+ "epoch": 1.44,
1555
+ "learning_rate": 0.00012793296089385475,
1556
+ "loss": 1.762,
1557
+ "step": 258
1558
+ },
1559
+ {
1560
+ "epoch": 1.45,
1561
+ "learning_rate": 0.00012765363128491622,
1562
+ "loss": 1.7565,
1563
+ "step": 259
1564
+ },
1565
+ {
1566
+ "epoch": 1.45,
1567
+ "learning_rate": 0.00012737430167597766,
1568
+ "loss": 1.5937,
1569
+ "step": 260
1570
+ },
1571
+ {
1572
+ "epoch": 1.46,
1573
+ "learning_rate": 0.0001270949720670391,
1574
+ "loss": 1.7208,
1575
+ "step": 261
1576
+ },
1577
+ {
1578
+ "epoch": 1.46,
1579
+ "learning_rate": 0.00012681564245810057,
1580
+ "loss": 1.8097,
1581
+ "step": 262
1582
+ },
1583
+ {
1584
+ "epoch": 1.47,
1585
+ "learning_rate": 0.000126536312849162,
1586
+ "loss": 1.7042,
1587
+ "step": 263
1588
+ },
1589
+ {
1590
+ "epoch": 1.47,
1591
+ "learning_rate": 0.00012625698324022347,
1592
+ "loss": 1.7892,
1593
+ "step": 264
1594
+ },
1595
+ {
1596
+ "epoch": 1.48,
1597
+ "learning_rate": 0.00012597765363128494,
1598
+ "loss": 1.752,
1599
+ "step": 265
1600
+ },
1601
+ {
1602
+ "epoch": 1.49,
1603
+ "learning_rate": 0.00012569832402234638,
1604
+ "loss": 1.7333,
1605
+ "step": 266
1606
+ },
1607
+ {
1608
+ "epoch": 1.49,
1609
+ "learning_rate": 0.00012541899441340784,
1610
+ "loss": 1.7492,
1611
+ "step": 267
1612
+ },
1613
+ {
1614
+ "epoch": 1.5,
1615
+ "learning_rate": 0.00012513966480446928,
1616
+ "loss": 1.818,
1617
+ "step": 268
1618
+ },
1619
+ {
1620
+ "epoch": 1.5,
1621
+ "learning_rate": 0.00012486033519553072,
1622
+ "loss": 1.7146,
1623
+ "step": 269
1624
+ },
1625
+ {
1626
+ "epoch": 1.51,
1627
+ "learning_rate": 0.0001245810055865922,
1628
+ "loss": 1.7958,
1629
+ "step": 270
1630
+ },
1631
+ {
1632
+ "epoch": 1.51,
1633
+ "learning_rate": 0.00012430167597765363,
1634
+ "loss": 1.7212,
1635
+ "step": 271
1636
+ },
1637
+ {
1638
+ "epoch": 1.52,
1639
+ "learning_rate": 0.0001240223463687151,
1640
+ "loss": 1.8835,
1641
+ "step": 272
1642
+ },
1643
+ {
1644
+ "epoch": 1.53,
1645
+ "learning_rate": 0.00012374301675977656,
1646
+ "loss": 1.7486,
1647
+ "step": 273
1648
+ },
1649
+ {
1650
+ "epoch": 1.53,
1651
+ "learning_rate": 0.000123463687150838,
1652
+ "loss": 1.8103,
1653
+ "step": 274
1654
+ },
1655
+ {
1656
+ "epoch": 1.54,
1657
+ "learning_rate": 0.00012318435754189944,
1658
+ "loss": 1.7557,
1659
+ "step": 275
1660
+ },
1661
+ {
1662
+ "epoch": 1.54,
1663
+ "learning_rate": 0.0001229050279329609,
1664
+ "loss": 1.6198,
1665
+ "step": 276
1666
+ },
1667
+ {
1668
+ "epoch": 1.55,
1669
+ "learning_rate": 0.00012262569832402235,
1670
+ "loss": 1.6971,
1671
+ "step": 277
1672
+ },
1673
+ {
1674
+ "epoch": 1.55,
1675
+ "learning_rate": 0.0001223463687150838,
1676
+ "loss": 1.668,
1677
+ "step": 278
1678
+ },
1679
+ {
1680
+ "epoch": 1.56,
1681
+ "learning_rate": 0.00012206703910614525,
1682
+ "loss": 1.8795,
1683
+ "step": 279
1684
+ },
1685
+ {
1686
+ "epoch": 1.56,
1687
+ "learning_rate": 0.0001217877094972067,
1688
+ "loss": 1.6412,
1689
+ "step": 280
1690
+ },
1691
+ {
1692
+ "epoch": 1.57,
1693
+ "learning_rate": 0.00012150837988826816,
1694
+ "loss": 1.7497,
1695
+ "step": 281
1696
+ },
1697
+ {
1698
+ "epoch": 1.58,
1699
+ "learning_rate": 0.00012122905027932962,
1700
+ "loss": 1.5577,
1701
+ "step": 282
1702
+ },
1703
+ {
1704
+ "epoch": 1.58,
1705
+ "learning_rate": 0.00012094972067039108,
1706
+ "loss": 1.8049,
1707
+ "step": 283
1708
+ },
1709
+ {
1710
+ "epoch": 1.59,
1711
+ "learning_rate": 0.00012067039106145253,
1712
+ "loss": 1.6834,
1713
+ "step": 284
1714
+ },
1715
+ {
1716
+ "epoch": 1.59,
1717
+ "learning_rate": 0.00012039106145251397,
1718
+ "loss": 1.7978,
1719
+ "step": 285
1720
+ },
1721
+ {
1722
+ "epoch": 1.6,
1723
+ "learning_rate": 0.00012011173184357542,
1724
+ "loss": 1.6558,
1725
+ "step": 286
1726
+ },
1727
+ {
1728
+ "epoch": 1.6,
1729
+ "learning_rate": 0.00011983240223463687,
1730
+ "loss": 1.7561,
1731
+ "step": 287
1732
+ },
1733
+ {
1734
+ "epoch": 1.61,
1735
+ "learning_rate": 0.00011955307262569833,
1736
+ "loss": 1.6807,
1737
+ "step": 288
1738
+ },
1739
+ {
1740
+ "epoch": 1.61,
1741
+ "learning_rate": 0.00011927374301675978,
1742
+ "loss": 1.6937,
1743
+ "step": 289
1744
+ },
1745
+ {
1746
+ "epoch": 1.62,
1747
+ "learning_rate": 0.00011899441340782122,
1748
+ "loss": 1.6591,
1749
+ "step": 290
1750
+ },
1751
+ {
1752
+ "epoch": 1.63,
1753
+ "learning_rate": 0.0001187150837988827,
1754
+ "loss": 1.6771,
1755
+ "step": 291
1756
+ },
1757
+ {
1758
+ "epoch": 1.63,
1759
+ "learning_rate": 0.00011843575418994415,
1760
+ "loss": 1.7743,
1761
+ "step": 292
1762
+ },
1763
+ {
1764
+ "epoch": 1.64,
1765
+ "learning_rate": 0.00011815642458100559,
1766
+ "loss": 1.5857,
1767
+ "step": 293
1768
+ },
1769
+ {
1770
+ "epoch": 1.64,
1771
+ "learning_rate": 0.00011787709497206705,
1772
+ "loss": 1.6999,
1773
+ "step": 294
1774
+ },
1775
+ {
1776
+ "epoch": 1.65,
1777
+ "learning_rate": 0.0001175977653631285,
1778
+ "loss": 1.5661,
1779
+ "step": 295
1780
+ },
1781
+ {
1782
+ "epoch": 1.65,
1783
+ "learning_rate": 0.00011731843575418995,
1784
+ "loss": 1.7235,
1785
+ "step": 296
1786
+ },
1787
+ {
1788
+ "epoch": 1.66,
1789
+ "learning_rate": 0.0001170391061452514,
1790
+ "loss": 1.607,
1791
+ "step": 297
1792
+ },
1793
+ {
1794
+ "epoch": 1.66,
1795
+ "learning_rate": 0.00011675977653631284,
1796
+ "loss": 1.68,
1797
+ "step": 298
1798
+ },
1799
+ {
1800
+ "epoch": 1.67,
1801
+ "learning_rate": 0.0001164804469273743,
1802
+ "loss": 1.6938,
1803
+ "step": 299
1804
+ },
1805
+ {
1806
+ "epoch": 1.68,
1807
+ "learning_rate": 0.00011620111731843578,
1808
+ "loss": 1.6315,
1809
+ "step": 300
1810
+ },
1811
+ {
1812
+ "epoch": 1.68,
1813
+ "learning_rate": 0.00011592178770949722,
1814
+ "loss": 1.6802,
1815
+ "step": 301
1816
+ },
1817
+ {
1818
+ "epoch": 1.69,
1819
+ "learning_rate": 0.00011564245810055867,
1820
+ "loss": 1.7174,
1821
+ "step": 302
1822
+ },
1823
+ {
1824
+ "epoch": 1.69,
1825
+ "learning_rate": 0.00011536312849162012,
1826
+ "loss": 1.5212,
1827
+ "step": 303
1828
+ },
1829
+ {
1830
+ "epoch": 1.7,
1831
+ "learning_rate": 0.00011508379888268157,
1832
+ "loss": 1.5808,
1833
+ "step": 304
1834
+ },
1835
+ {
1836
+ "epoch": 1.7,
1837
+ "learning_rate": 0.00011480446927374303,
1838
+ "loss": 1.6152,
1839
+ "step": 305
1840
+ },
1841
+ {
1842
+ "epoch": 1.71,
1843
+ "learning_rate": 0.00011452513966480447,
1844
+ "loss": 1.5435,
1845
+ "step": 306
1846
+ },
1847
+ {
1848
+ "epoch": 1.72,
1849
+ "learning_rate": 0.00011424581005586592,
1850
+ "loss": 1.6603,
1851
+ "step": 307
1852
+ },
1853
+ {
1854
+ "epoch": 1.72,
1855
+ "learning_rate": 0.00011396648044692737,
1856
+ "loss": 1.685,
1857
+ "step": 308
1858
+ },
1859
+ {
1860
+ "epoch": 1.73,
1861
+ "learning_rate": 0.00011368715083798884,
1862
+ "loss": 1.6002,
1863
+ "step": 309
1864
+ },
1865
+ {
1866
+ "epoch": 1.73,
1867
+ "learning_rate": 0.00011340782122905029,
1868
+ "loss": 1.6046,
1869
+ "step": 310
1870
+ },
1871
+ {
1872
+ "epoch": 1.74,
1873
+ "learning_rate": 0.00011312849162011174,
1874
+ "loss": 1.5969,
1875
+ "step": 311
1876
+ },
1877
+ {
1878
+ "epoch": 1.74,
1879
+ "learning_rate": 0.0001128491620111732,
1880
+ "loss": 1.5845,
1881
+ "step": 312
1882
+ },
1883
+ {
1884
+ "epoch": 1.75,
1885
+ "learning_rate": 0.00011256983240223464,
1886
+ "loss": 1.8183,
1887
+ "step": 313
1888
+ },
1889
+ {
1890
+ "epoch": 1.75,
1891
+ "learning_rate": 0.00011229050279329609,
1892
+ "loss": 1.6953,
1893
+ "step": 314
1894
+ },
1895
+ {
1896
+ "epoch": 1.76,
1897
+ "learning_rate": 0.00011201117318435754,
1898
+ "loss": 1.7787,
1899
+ "step": 315
1900
+ },
1901
+ {
1902
+ "epoch": 1.77,
1903
+ "learning_rate": 0.000111731843575419,
1904
+ "loss": 1.6422,
1905
+ "step": 316
1906
+ },
1907
+ {
1908
+ "epoch": 1.77,
1909
+ "learning_rate": 0.00011145251396648045,
1910
+ "loss": 1.7034,
1911
+ "step": 317
1912
+ },
1913
+ {
1914
+ "epoch": 1.78,
1915
+ "learning_rate": 0.00011117318435754192,
1916
+ "loss": 1.7301,
1917
+ "step": 318
1918
+ },
1919
+ {
1920
+ "epoch": 1.78,
1921
+ "learning_rate": 0.00011089385474860337,
1922
+ "loss": 1.7084,
1923
+ "step": 319
1924
+ },
1925
+ {
1926
+ "epoch": 1.79,
1927
+ "learning_rate": 0.00011061452513966482,
1928
+ "loss": 1.772,
1929
+ "step": 320
1930
+ },
1931
+ {
1932
+ "epoch": 1.79,
1933
+ "learning_rate": 0.00011033519553072626,
1934
+ "loss": 1.5733,
1935
+ "step": 321
1936
+ },
1937
+ {
1938
+ "epoch": 1.8,
1939
+ "learning_rate": 0.00011005586592178771,
1940
+ "loss": 1.6423,
1941
+ "step": 322
1942
+ },
1943
+ {
1944
+ "epoch": 1.8,
1945
+ "learning_rate": 0.00010977653631284917,
1946
+ "loss": 1.5809,
1947
+ "step": 323
1948
+ },
1949
+ {
1950
+ "epoch": 1.81,
1951
+ "learning_rate": 0.00010949720670391062,
1952
+ "loss": 1.6781,
1953
+ "step": 324
1954
+ },
1955
+ {
1956
+ "epoch": 1.82,
1957
+ "learning_rate": 0.00010921787709497207,
1958
+ "loss": 1.6788,
1959
+ "step": 325
1960
+ },
1961
+ {
1962
+ "epoch": 1.82,
1963
+ "learning_rate": 0.00010893854748603351,
1964
+ "loss": 1.6346,
1965
+ "step": 326
1966
+ },
1967
+ {
1968
+ "epoch": 1.83,
1969
+ "learning_rate": 0.00010865921787709499,
1970
+ "loss": 1.6634,
1971
+ "step": 327
1972
+ },
1973
+ {
1974
+ "epoch": 1.83,
1975
+ "learning_rate": 0.00010837988826815643,
1976
+ "loss": 1.7561,
1977
+ "step": 328
1978
+ },
1979
+ {
1980
+ "epoch": 1.84,
1981
+ "learning_rate": 0.00010810055865921788,
1982
+ "loss": 1.66,
1983
+ "step": 329
1984
+ },
1985
+ {
1986
+ "epoch": 1.84,
1987
+ "learning_rate": 0.00010782122905027934,
1988
+ "loss": 1.7298,
1989
+ "step": 330
1990
+ },
1991
+ {
1992
+ "epoch": 1.85,
1993
+ "learning_rate": 0.00010754189944134079,
1994
+ "loss": 1.6893,
1995
+ "step": 331
1996
+ },
1997
+ {
1998
+ "epoch": 1.85,
1999
+ "learning_rate": 0.00010726256983240224,
2000
+ "loss": 1.7631,
2001
+ "step": 332
2002
+ },
2003
+ {
2004
+ "epoch": 1.86,
2005
+ "learning_rate": 0.00010698324022346368,
2006
+ "loss": 1.6633,
2007
+ "step": 333
2008
+ },
2009
+ {
2010
+ "epoch": 1.87,
2011
+ "learning_rate": 0.00010670391061452513,
2012
+ "loss": 1.5388,
2013
+ "step": 334
2014
+ },
2015
+ {
2016
+ "epoch": 1.87,
2017
+ "learning_rate": 0.00010642458100558659,
2018
+ "loss": 1.6718,
2019
+ "step": 335
2020
+ },
2021
+ {
2022
+ "epoch": 1.88,
2023
+ "learning_rate": 0.00010614525139664805,
2024
+ "loss": 1.5536,
2025
+ "step": 336
2026
+ },
2027
+ {
2028
+ "epoch": 1.88,
2029
+ "learning_rate": 0.00010586592178770951,
2030
+ "loss": 1.6483,
2031
+ "step": 337
2032
+ },
2033
+ {
2034
+ "epoch": 1.89,
2035
+ "learning_rate": 0.00010558659217877096,
2036
+ "loss": 1.5774,
2037
+ "step": 338
2038
+ },
2039
+ {
2040
+ "epoch": 1.89,
2041
+ "learning_rate": 0.00010530726256983241,
2042
+ "loss": 1.6366,
2043
+ "step": 339
2044
+ },
2045
+ {
2046
+ "epoch": 1.9,
2047
+ "learning_rate": 0.00010502793296089387,
2048
+ "loss": 1.5567,
2049
+ "step": 340
2050
+ },
2051
+ {
2052
+ "epoch": 1.91,
2053
+ "learning_rate": 0.0001047486033519553,
2054
+ "loss": 1.5323,
2055
+ "step": 341
2056
+ },
2057
+ {
2058
+ "epoch": 1.91,
2059
+ "learning_rate": 0.00010446927374301676,
2060
+ "loss": 1.4608,
2061
+ "step": 342
2062
+ },
2063
+ {
2064
+ "epoch": 1.92,
2065
+ "learning_rate": 0.00010418994413407821,
2066
+ "loss": 1.5933,
2067
+ "step": 343
2068
+ },
2069
+ {
2070
+ "epoch": 1.92,
2071
+ "learning_rate": 0.00010391061452513966,
2072
+ "loss": 1.6625,
2073
+ "step": 344
2074
+ },
2075
+ {
2076
+ "epoch": 1.93,
2077
+ "learning_rate": 0.00010363128491620113,
2078
+ "loss": 1.7236,
2079
+ "step": 345
2080
+ },
2081
+ {
2082
+ "epoch": 1.93,
2083
+ "learning_rate": 0.00010335195530726258,
2084
+ "loss": 1.759,
2085
+ "step": 346
2086
+ },
2087
+ {
2088
+ "epoch": 1.94,
2089
+ "learning_rate": 0.00010307262569832404,
2090
+ "loss": 1.7248,
2091
+ "step": 347
2092
+ },
2093
+ {
2094
+ "epoch": 1.94,
2095
+ "learning_rate": 0.00010279329608938548,
2096
+ "loss": 1.5144,
2097
+ "step": 348
2098
+ },
2099
+ {
2100
+ "epoch": 1.95,
2101
+ "learning_rate": 0.00010251396648044693,
2102
+ "loss": 1.6905,
2103
+ "step": 349
2104
+ },
2105
+ {
2106
+ "epoch": 1.96,
2107
+ "learning_rate": 0.00010223463687150838,
2108
+ "loss": 1.6119,
2109
+ "step": 350
2110
+ },
2111
+ {
2112
+ "epoch": 1.96,
2113
+ "learning_rate": 0.00010195530726256983,
2114
+ "loss": 1.5464,
2115
+ "step": 351
2116
+ },
2117
+ {
2118
+ "epoch": 1.97,
2119
+ "learning_rate": 0.00010167597765363129,
2120
+ "loss": 1.6901,
2121
+ "step": 352
2122
+ },
2123
+ {
2124
+ "epoch": 1.97,
2125
+ "learning_rate": 0.00010139664804469273,
2126
+ "loss": 1.3511,
2127
+ "step": 353
2128
+ },
2129
+ {
2130
+ "epoch": 1.98,
2131
+ "learning_rate": 0.0001011173184357542,
2132
+ "loss": 1.5434,
2133
+ "step": 354
2134
+ },
2135
+ {
2136
+ "epoch": 1.98,
2137
+ "learning_rate": 0.00010083798882681566,
2138
+ "loss": 1.5891,
2139
+ "step": 355
2140
+ },
2141
+ {
2142
+ "epoch": 1.99,
2143
+ "learning_rate": 0.0001005586592178771,
2144
+ "loss": 1.6658,
2145
+ "step": 356
2146
+ },
2147
+ {
2148
+ "epoch": 1.99,
2149
+ "learning_rate": 0.00010027932960893855,
2150
+ "loss": 1.5657,
2151
+ "step": 357
2152
+ },
2153
+ {
2154
+ "epoch": 2.0,
2155
+ "learning_rate": 0.0001,
2156
+ "loss": 1.7005,
2157
+ "step": 358
2158
+ },
2159
+ {
2160
+ "epoch": 2.01,
2161
+ "learning_rate": 9.972067039106146e-05,
2162
+ "loss": 1.4202,
2163
+ "step": 359
2164
+ },
2165
+ {
2166
+ "epoch": 2.01,
2167
+ "learning_rate": 9.944134078212291e-05,
2168
+ "loss": 1.5262,
2169
+ "step": 360
2170
+ },
2171
+ {
2172
+ "epoch": 2.02,
2173
+ "learning_rate": 9.916201117318436e-05,
2174
+ "loss": 1.6323,
2175
+ "step": 361
2176
+ },
2177
+ {
2178
+ "epoch": 2.02,
2179
+ "learning_rate": 9.888268156424582e-05,
2180
+ "loss": 1.5521,
2181
+ "step": 362
2182
+ },
2183
+ {
2184
+ "epoch": 2.03,
2185
+ "learning_rate": 9.860335195530727e-05,
2186
+ "loss": 1.5762,
2187
+ "step": 363
2188
+ },
2189
+ {
2190
+ "epoch": 2.03,
2191
+ "learning_rate": 9.832402234636872e-05,
2192
+ "loss": 1.613,
2193
+ "step": 364
2194
+ },
2195
+ {
2196
+ "epoch": 2.04,
2197
+ "learning_rate": 9.804469273743018e-05,
2198
+ "loss": 1.4231,
2199
+ "step": 365
2200
+ },
2201
+ {
2202
+ "epoch": 2.04,
2203
+ "learning_rate": 9.776536312849163e-05,
2204
+ "loss": 1.5706,
2205
+ "step": 366
2206
+ },
2207
+ {
2208
+ "epoch": 2.05,
2209
+ "learning_rate": 9.748603351955308e-05,
2210
+ "loss": 1.5245,
2211
+ "step": 367
2212
+ },
2213
+ {
2214
+ "epoch": 2.06,
2215
+ "learning_rate": 9.720670391061453e-05,
2216
+ "loss": 1.4771,
2217
+ "step": 368
2218
+ },
2219
+ {
2220
+ "epoch": 2.06,
2221
+ "learning_rate": 9.692737430167597e-05,
2222
+ "loss": 1.596,
2223
+ "step": 369
2224
+ },
2225
+ {
2226
+ "epoch": 2.07,
2227
+ "learning_rate": 9.664804469273744e-05,
2228
+ "loss": 1.537,
2229
+ "step": 370
2230
+ },
2231
+ {
2232
+ "epoch": 2.07,
2233
+ "learning_rate": 9.636871508379889e-05,
2234
+ "loss": 1.4276,
2235
+ "step": 371
2236
+ },
2237
+ {
2238
+ "epoch": 2.08,
2239
+ "learning_rate": 9.608938547486033e-05,
2240
+ "loss": 1.4746,
2241
+ "step": 372
2242
+ },
2243
+ {
2244
+ "epoch": 2.08,
2245
+ "learning_rate": 9.581005586592178e-05,
2246
+ "loss": 1.4374,
2247
+ "step": 373
2248
+ },
2249
+ {
2250
+ "epoch": 2.09,
2251
+ "learning_rate": 9.553072625698325e-05,
2252
+ "loss": 1.4704,
2253
+ "step": 374
2254
+ },
2255
+ {
2256
+ "epoch": 2.09,
2257
+ "learning_rate": 9.52513966480447e-05,
2258
+ "loss": 1.5997,
2259
+ "step": 375
2260
+ },
2261
+ {
2262
+ "epoch": 2.1,
2263
+ "learning_rate": 9.497206703910614e-05,
2264
+ "loss": 1.5034,
2265
+ "step": 376
2266
+ },
2267
+ {
2268
+ "epoch": 2.11,
2269
+ "learning_rate": 9.46927374301676e-05,
2270
+ "loss": 1.6392,
2271
+ "step": 377
2272
+ },
2273
+ {
2274
+ "epoch": 2.11,
2275
+ "learning_rate": 9.441340782122905e-05,
2276
+ "loss": 1.5611,
2277
+ "step": 378
2278
+ },
2279
+ {
2280
+ "epoch": 2.12,
2281
+ "learning_rate": 9.413407821229052e-05,
2282
+ "loss": 1.3384,
2283
+ "step": 379
2284
+ },
2285
+ {
2286
+ "epoch": 2.12,
2287
+ "learning_rate": 9.385474860335196e-05,
2288
+ "loss": 1.5732,
2289
+ "step": 380
2290
+ },
2291
+ {
2292
+ "epoch": 2.13,
2293
+ "learning_rate": 9.357541899441341e-05,
2294
+ "loss": 1.3874,
2295
+ "step": 381
2296
+ },
2297
+ {
2298
+ "epoch": 2.13,
2299
+ "learning_rate": 9.329608938547486e-05,
2300
+ "loss": 1.4139,
2301
+ "step": 382
2302
+ },
2303
+ {
2304
+ "epoch": 2.14,
2305
+ "learning_rate": 9.301675977653633e-05,
2306
+ "loss": 1.5195,
2307
+ "step": 383
2308
+ },
2309
+ {
2310
+ "epoch": 2.15,
2311
+ "learning_rate": 9.273743016759777e-05,
2312
+ "loss": 1.4371,
2313
+ "step": 384
2314
+ },
2315
+ {
2316
+ "epoch": 2.15,
2317
+ "learning_rate": 9.245810055865922e-05,
2318
+ "loss": 1.4411,
2319
+ "step": 385
2320
+ },
2321
+ {
2322
+ "epoch": 2.16,
2323
+ "learning_rate": 9.217877094972067e-05,
2324
+ "loss": 1.5214,
2325
+ "step": 386
2326
+ },
2327
+ {
2328
+ "epoch": 2.16,
2329
+ "learning_rate": 9.189944134078213e-05,
2330
+ "loss": 1.4971,
2331
+ "step": 387
2332
+ },
2333
+ {
2334
+ "epoch": 2.17,
2335
+ "learning_rate": 9.162011173184358e-05,
2336
+ "loss": 1.3453,
2337
+ "step": 388
2338
+ },
2339
+ {
2340
+ "epoch": 2.17,
2341
+ "learning_rate": 9.134078212290503e-05,
2342
+ "loss": 1.394,
2343
+ "step": 389
2344
+ },
2345
+ {
2346
+ "epoch": 2.18,
2347
+ "learning_rate": 9.106145251396648e-05,
2348
+ "loss": 1.5058,
2349
+ "step": 390
2350
+ },
2351
+ {
2352
+ "epoch": 2.18,
2353
+ "learning_rate": 9.078212290502794e-05,
2354
+ "loss": 1.4855,
2355
+ "step": 391
2356
+ },
2357
+ {
2358
+ "epoch": 2.19,
2359
+ "learning_rate": 9.050279329608939e-05,
2360
+ "loss": 1.4647,
2361
+ "step": 392
2362
+ },
2363
+ {
2364
+ "epoch": 2.2,
2365
+ "learning_rate": 9.022346368715084e-05,
2366
+ "loss": 1.3435,
2367
+ "step": 393
2368
+ },
2369
+ {
2370
+ "epoch": 2.2,
2371
+ "learning_rate": 8.99441340782123e-05,
2372
+ "loss": 1.5815,
2373
+ "step": 394
2374
+ },
2375
+ {
2376
+ "epoch": 2.21,
2377
+ "learning_rate": 8.966480446927375e-05,
2378
+ "loss": 1.4742,
2379
+ "step": 395
2380
+ },
2381
+ {
2382
+ "epoch": 2.21,
2383
+ "learning_rate": 8.938547486033519e-05,
2384
+ "loss": 1.5389,
2385
+ "step": 396
2386
+ },
2387
+ {
2388
+ "epoch": 2.22,
2389
+ "learning_rate": 8.910614525139666e-05,
2390
+ "loss": 1.384,
2391
+ "step": 397
2392
+ },
2393
+ {
2394
+ "epoch": 2.22,
2395
+ "learning_rate": 8.882681564245811e-05,
2396
+ "loss": 1.3967,
2397
+ "step": 398
2398
+ },
2399
+ {
2400
+ "epoch": 2.23,
2401
+ "learning_rate": 8.854748603351956e-05,
2402
+ "loss": 1.442,
2403
+ "step": 399
2404
+ },
2405
+ {
2406
+ "epoch": 2.23,
2407
+ "learning_rate": 8.8268156424581e-05,
2408
+ "loss": 1.396,
2409
+ "step": 400
2410
+ }
2411
+ ],
2412
+ "logging_steps": 1,
2413
+ "max_steps": 716,
2414
+ "num_train_epochs": 4,
2415
+ "save_steps": 100,
2416
+ "total_flos": 2.056923590572032e+17,
2417
+ "trial_name": null,
2418
+ "trial_params": null
2419
+ }
checkpoint-400/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:188ae1c421cc0c6435d1f71d8d3423ac4abc7dba0e6fc2efcbc4dbe77c741317
3
+ size 4027
checkpoint-500/README.md ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: True
10
+ - load_in_4bit: False
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: fp4
16
+ - bnb_4bit_use_double_quant: False
17
+ - bnb_4bit_compute_dtype: float32
18
+
19
+ The following `bitsandbytes` quantization config was used during training:
20
+ - quant_method: bitsandbytes
21
+ - load_in_8bit: True
22
+ - load_in_4bit: False
23
+ - llm_int8_threshold: 6.0
24
+ - llm_int8_skip_modules: None
25
+ - llm_int8_enable_fp32_cpu_offload: False
26
+ - llm_int8_has_fp16_weight: False
27
+ - bnb_4bit_quant_type: fp4
28
+ - bnb_4bit_use_double_quant: False
29
+ - bnb_4bit_compute_dtype: float32
30
+
31
+ The following `bitsandbytes` quantization config was used during training:
32
+ - quant_method: bitsandbytes
33
+ - load_in_8bit: True
34
+ - load_in_4bit: False
35
+ - llm_int8_threshold: 6.0
36
+ - llm_int8_skip_modules: None
37
+ - llm_int8_enable_fp32_cpu_offload: False
38
+ - llm_int8_has_fp16_weight: False
39
+ - bnb_4bit_quant_type: fp4
40
+ - bnb_4bit_use_double_quant: False
41
+ - bnb_4bit_compute_dtype: float32
42
+
43
+ The following `bitsandbytes` quantization config was used during training:
44
+ - quant_method: bitsandbytes
45
+ - load_in_8bit: True
46
+ - load_in_4bit: False
47
+ - llm_int8_threshold: 6.0
48
+ - llm_int8_skip_modules: None
49
+ - llm_int8_enable_fp32_cpu_offload: False
50
+ - llm_int8_has_fp16_weight: False
51
+ - bnb_4bit_quant_type: fp4
52
+ - bnb_4bit_use_double_quant: False
53
+ - bnb_4bit_compute_dtype: float32
54
+ ### Framework versions
55
+
56
+ - PEFT 0.6.0.dev0
57
+ - PEFT 0.6.0.dev0
58
+ - PEFT 0.6.0.dev0
59
+
60
+ - PEFT 0.6.0.dev0
checkpoint-500/adapter_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "bigscience/bloomz-3b",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "lora_alpha": 16,
12
+ "lora_dropout": 0.0,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 8,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "dense_4h_to_h",
20
+ "dense",
21
+ "dense_h_to_4h",
22
+ "query_key_value"
23
+ ],
24
+ "task_type": "CAUSAL_LM"
25
+ }
checkpoint-500/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbc5f8a93e505087cecc049ff476019df96de3cba21db5d67029ade06c844216
3
+ size 39409357
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbab141106d84467be5a7a978a93b8492dd00bcc4a497115fb4124bf8beaa046
3
+ size 78844421
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7508d4b8dd267de5cc58e972da25236687927651336a28f292c92f7f23951475
3
+ size 14575