sedrickkeh
commited on
Commit
•
7a2abdf
1
Parent(s):
7ddd5c9
End of training
Browse files- README.md +2 -1
- all_results.json +12 -0
- eval_results.json +7 -0
- train_results.json +8 -0
- trainer_state.json +948 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
@@ -4,6 +4,7 @@ license: llama3
|
|
4 |
base_model: meta-llama/Meta-Llama-3-8B
|
5 |
tags:
|
6 |
- llama-factory
|
|
|
7 |
- generated_from_trainer
|
8 |
model-index:
|
9 |
- name: OH_DCFT_V3_wo_unnatural_instructions
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# OH_DCFT_V3_wo_unnatural_instructions
|
17 |
|
18 |
-
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on
|
19 |
It achieves the following results on the evaluation set:
|
20 |
- Loss: 0.6487
|
21 |
|
|
|
4 |
base_model: meta-llama/Meta-Llama-3-8B
|
5 |
tags:
|
6 |
- llama-factory
|
7 |
+
- full
|
8 |
- generated_from_trainer
|
9 |
model-index:
|
10 |
- name: OH_DCFT_V3_wo_unnatural_instructions
|
|
|
16 |
|
17 |
# OH_DCFT_V3_wo_unnatural_instructions
|
18 |
|
19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the mlfoundations-dev/OH_DCFT_V3_wo_unnatural_instructions dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
- Loss: 0.6487
|
22 |
|
all_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.9946777054997042,
|
3 |
+
"eval_loss": 0.648719847202301,
|
4 |
+
"eval_runtime": 224.9555,
|
5 |
+
"eval_samples_per_second": 50.619,
|
6 |
+
"eval_steps_per_second": 0.396,
|
7 |
+
"total_flos": 2120178393415680.0,
|
8 |
+
"train_loss": 0.6180764295478568,
|
9 |
+
"train_runtime": 37891.5513,
|
10 |
+
"train_samples_per_second": 17.129,
|
11 |
+
"train_steps_per_second": 0.033
|
12 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.9946777054997042,
|
3 |
+
"eval_loss": 0.648719847202301,
|
4 |
+
"eval_runtime": 224.9555,
|
5 |
+
"eval_samples_per_second": 50.619,
|
6 |
+
"eval_steps_per_second": 0.396
|
7 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.9946777054997042,
|
3 |
+
"total_flos": 2120178393415680.0,
|
4 |
+
"train_loss": 0.6180764295478568,
|
5 |
+
"train_runtime": 37891.5513,
|
6 |
+
"train_samples_per_second": 17.129,
|
7 |
+
"train_steps_per_second": 0.033
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,948 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.9946777054997042,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1266,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.02365464222353637,
|
13 |
+
"grad_norm": 39.04922181795541,
|
14 |
+
"learning_rate": 5e-06,
|
15 |
+
"loss": 0.9233,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.04730928444707274,
|
20 |
+
"grad_norm": 8.275301054500245,
|
21 |
+
"learning_rate": 5e-06,
|
22 |
+
"loss": 0.8198,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.0709639266706091,
|
27 |
+
"grad_norm": 16.91349063149131,
|
28 |
+
"learning_rate": 5e-06,
|
29 |
+
"loss": 0.8094,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.09461856889414548,
|
34 |
+
"grad_norm": 14.148988171179118,
|
35 |
+
"learning_rate": 5e-06,
|
36 |
+
"loss": 0.7679,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.11827321111768184,
|
41 |
+
"grad_norm": 1.026404466612184,
|
42 |
+
"learning_rate": 5e-06,
|
43 |
+
"loss": 0.7523,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.1419278533412182,
|
48 |
+
"grad_norm": 0.8542225183892468,
|
49 |
+
"learning_rate": 5e-06,
|
50 |
+
"loss": 0.725,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.16558249556475457,
|
55 |
+
"grad_norm": 0.7426518873227826,
|
56 |
+
"learning_rate": 5e-06,
|
57 |
+
"loss": 0.7185,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.18923713778829096,
|
62 |
+
"grad_norm": 0.6764382829611749,
|
63 |
+
"learning_rate": 5e-06,
|
64 |
+
"loss": 0.6999,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.21289178001182732,
|
69 |
+
"grad_norm": 0.5663920137594394,
|
70 |
+
"learning_rate": 5e-06,
|
71 |
+
"loss": 0.7,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.23654642223536368,
|
76 |
+
"grad_norm": 0.6218835377066562,
|
77 |
+
"learning_rate": 5e-06,
|
78 |
+
"loss": 0.6968,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.26020106445890007,
|
83 |
+
"grad_norm": 0.601497886261039,
|
84 |
+
"learning_rate": 5e-06,
|
85 |
+
"loss": 0.6885,
|
86 |
+
"step": 110
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.2838557066824364,
|
90 |
+
"grad_norm": 0.8786039473525534,
|
91 |
+
"learning_rate": 5e-06,
|
92 |
+
"loss": 0.6863,
|
93 |
+
"step": 120
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.3075103489059728,
|
97 |
+
"grad_norm": 0.5373447312315734,
|
98 |
+
"learning_rate": 5e-06,
|
99 |
+
"loss": 0.6792,
|
100 |
+
"step": 130
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.33116499112950915,
|
104 |
+
"grad_norm": 0.5195473153997355,
|
105 |
+
"learning_rate": 5e-06,
|
106 |
+
"loss": 0.6746,
|
107 |
+
"step": 140
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.35481963335304556,
|
111 |
+
"grad_norm": 0.5999120946052041,
|
112 |
+
"learning_rate": 5e-06,
|
113 |
+
"loss": 0.68,
|
114 |
+
"step": 150
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.3784742755765819,
|
118 |
+
"grad_norm": 0.5351205582865509,
|
119 |
+
"learning_rate": 5e-06,
|
120 |
+
"loss": 0.6766,
|
121 |
+
"step": 160
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.4021289178001183,
|
125 |
+
"grad_norm": 0.5425010920017291,
|
126 |
+
"learning_rate": 5e-06,
|
127 |
+
"loss": 0.6839,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.42578356002365464,
|
132 |
+
"grad_norm": 0.702582958286065,
|
133 |
+
"learning_rate": 5e-06,
|
134 |
+
"loss": 0.6711,
|
135 |
+
"step": 180
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.449438202247191,
|
139 |
+
"grad_norm": 1.2564450479675764,
|
140 |
+
"learning_rate": 5e-06,
|
141 |
+
"loss": 0.6776,
|
142 |
+
"step": 190
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.47309284447072736,
|
146 |
+
"grad_norm": 0.6226292820244915,
|
147 |
+
"learning_rate": 5e-06,
|
148 |
+
"loss": 0.6695,
|
149 |
+
"step": 200
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.4967474866942638,
|
153 |
+
"grad_norm": 0.6729451633589562,
|
154 |
+
"learning_rate": 5e-06,
|
155 |
+
"loss": 0.6656,
|
156 |
+
"step": 210
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.5204021289178001,
|
160 |
+
"grad_norm": 0.72360498041814,
|
161 |
+
"learning_rate": 5e-06,
|
162 |
+
"loss": 0.6699,
|
163 |
+
"step": 220
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.5440567711413364,
|
167 |
+
"grad_norm": 0.5730443009789895,
|
168 |
+
"learning_rate": 5e-06,
|
169 |
+
"loss": 0.6693,
|
170 |
+
"step": 230
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.5677114133648729,
|
174 |
+
"grad_norm": 0.6304204873609028,
|
175 |
+
"learning_rate": 5e-06,
|
176 |
+
"loss": 0.6564,
|
177 |
+
"step": 240
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.5913660555884093,
|
181 |
+
"grad_norm": 0.6327686473365169,
|
182 |
+
"learning_rate": 5e-06,
|
183 |
+
"loss": 0.6707,
|
184 |
+
"step": 250
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.6150206978119456,
|
188 |
+
"grad_norm": 0.5640335014419563,
|
189 |
+
"learning_rate": 5e-06,
|
190 |
+
"loss": 0.6617,
|
191 |
+
"step": 260
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.638675340035482,
|
195 |
+
"grad_norm": 0.6026872513783592,
|
196 |
+
"learning_rate": 5e-06,
|
197 |
+
"loss": 0.6711,
|
198 |
+
"step": 270
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.6623299822590183,
|
202 |
+
"grad_norm": 0.5194797310260643,
|
203 |
+
"learning_rate": 5e-06,
|
204 |
+
"loss": 0.6561,
|
205 |
+
"step": 280
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.6859846244825547,
|
209 |
+
"grad_norm": 0.6658270095766984,
|
210 |
+
"learning_rate": 5e-06,
|
211 |
+
"loss": 0.663,
|
212 |
+
"step": 290
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.7096392667060911,
|
216 |
+
"grad_norm": 0.5259962549449988,
|
217 |
+
"learning_rate": 5e-06,
|
218 |
+
"loss": 0.6511,
|
219 |
+
"step": 300
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.7332939089296274,
|
223 |
+
"grad_norm": 0.5776532705758929,
|
224 |
+
"learning_rate": 5e-06,
|
225 |
+
"loss": 0.6649,
|
226 |
+
"step": 310
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.7569485511531638,
|
230 |
+
"grad_norm": 0.5249892835904177,
|
231 |
+
"learning_rate": 5e-06,
|
232 |
+
"loss": 0.6648,
|
233 |
+
"step": 320
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.7806031933767001,
|
237 |
+
"grad_norm": 0.5092145613062358,
|
238 |
+
"learning_rate": 5e-06,
|
239 |
+
"loss": 0.6614,
|
240 |
+
"step": 330
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.8042578356002366,
|
244 |
+
"grad_norm": 0.5273167065626364,
|
245 |
+
"learning_rate": 5e-06,
|
246 |
+
"loss": 0.6468,
|
247 |
+
"step": 340
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.8279124778237729,
|
251 |
+
"grad_norm": 0.5666036582386984,
|
252 |
+
"learning_rate": 5e-06,
|
253 |
+
"loss": 0.6562,
|
254 |
+
"step": 350
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.8515671200473093,
|
258 |
+
"grad_norm": 0.6164474600239763,
|
259 |
+
"learning_rate": 5e-06,
|
260 |
+
"loss": 0.6544,
|
261 |
+
"step": 360
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.8752217622708457,
|
265 |
+
"grad_norm": 0.5854672267431167,
|
266 |
+
"learning_rate": 5e-06,
|
267 |
+
"loss": 0.6547,
|
268 |
+
"step": 370
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.898876404494382,
|
272 |
+
"grad_norm": 0.5313196039449892,
|
273 |
+
"learning_rate": 5e-06,
|
274 |
+
"loss": 0.6584,
|
275 |
+
"step": 380
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.9225310467179184,
|
279 |
+
"grad_norm": 0.5598019500152581,
|
280 |
+
"learning_rate": 5e-06,
|
281 |
+
"loss": 0.6533,
|
282 |
+
"step": 390
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.9461856889414547,
|
286 |
+
"grad_norm": 0.6003027055491813,
|
287 |
+
"learning_rate": 5e-06,
|
288 |
+
"loss": 0.6458,
|
289 |
+
"step": 400
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.9698403311649911,
|
293 |
+
"grad_norm": 0.6341763962447327,
|
294 |
+
"learning_rate": 5e-06,
|
295 |
+
"loss": 0.656,
|
296 |
+
"step": 410
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.9934949733885275,
|
300 |
+
"grad_norm": 0.6083507877729101,
|
301 |
+
"learning_rate": 5e-06,
|
302 |
+
"loss": 0.6538,
|
303 |
+
"step": 420
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.9982259018332348,
|
307 |
+
"eval_loss": 0.6558582186698914,
|
308 |
+
"eval_runtime": 224.885,
|
309 |
+
"eval_samples_per_second": 50.635,
|
310 |
+
"eval_steps_per_second": 0.396,
|
311 |
+
"step": 422
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 1.0171496156120639,
|
315 |
+
"grad_norm": 0.9361782463296332,
|
316 |
+
"learning_rate": 5e-06,
|
317 |
+
"loss": 0.6157,
|
318 |
+
"step": 430
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 1.0408042578356003,
|
322 |
+
"grad_norm": 0.6204113010596938,
|
323 |
+
"learning_rate": 5e-06,
|
324 |
+
"loss": 0.6065,
|
325 |
+
"step": 440
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 1.0644589000591367,
|
329 |
+
"grad_norm": 0.6564336264095381,
|
330 |
+
"learning_rate": 5e-06,
|
331 |
+
"loss": 0.6048,
|
332 |
+
"step": 450
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 1.0881135422826729,
|
336 |
+
"grad_norm": 0.5555833545533679,
|
337 |
+
"learning_rate": 5e-06,
|
338 |
+
"loss": 0.6072,
|
339 |
+
"step": 460
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 1.1117681845062093,
|
343 |
+
"grad_norm": 0.568736434370096,
|
344 |
+
"learning_rate": 5e-06,
|
345 |
+
"loss": 0.6026,
|
346 |
+
"step": 470
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 1.1354228267297457,
|
350 |
+
"grad_norm": 0.5963174527245159,
|
351 |
+
"learning_rate": 5e-06,
|
352 |
+
"loss": 0.6041,
|
353 |
+
"step": 480
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 1.1590774689532821,
|
357 |
+
"grad_norm": 0.6296624775692966,
|
358 |
+
"learning_rate": 5e-06,
|
359 |
+
"loss": 0.6036,
|
360 |
+
"step": 490
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 1.1827321111768185,
|
364 |
+
"grad_norm": 0.7667349314546962,
|
365 |
+
"learning_rate": 5e-06,
|
366 |
+
"loss": 0.6068,
|
367 |
+
"step": 500
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 1.2063867534003547,
|
371 |
+
"grad_norm": 0.6034621980970892,
|
372 |
+
"learning_rate": 5e-06,
|
373 |
+
"loss": 0.6104,
|
374 |
+
"step": 510
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 1.2300413956238911,
|
378 |
+
"grad_norm": 0.5825117431703367,
|
379 |
+
"learning_rate": 5e-06,
|
380 |
+
"loss": 0.6026,
|
381 |
+
"step": 520
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 1.2536960378474276,
|
385 |
+
"grad_norm": 0.5671081402783421,
|
386 |
+
"learning_rate": 5e-06,
|
387 |
+
"loss": 0.604,
|
388 |
+
"step": 530
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 1.277350680070964,
|
392 |
+
"grad_norm": 0.5309591912112671,
|
393 |
+
"learning_rate": 5e-06,
|
394 |
+
"loss": 0.6132,
|
395 |
+
"step": 540
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 1.3010053222945004,
|
399 |
+
"grad_norm": 0.5636046858771947,
|
400 |
+
"learning_rate": 5e-06,
|
401 |
+
"loss": 0.605,
|
402 |
+
"step": 550
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 1.3246599645180366,
|
406 |
+
"grad_norm": 0.6623955102141809,
|
407 |
+
"learning_rate": 5e-06,
|
408 |
+
"loss": 0.6082,
|
409 |
+
"step": 560
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 1.348314606741573,
|
413 |
+
"grad_norm": 0.5742305096790601,
|
414 |
+
"learning_rate": 5e-06,
|
415 |
+
"loss": 0.605,
|
416 |
+
"step": 570
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 1.3719692489651094,
|
420 |
+
"grad_norm": 0.5167065988140831,
|
421 |
+
"learning_rate": 5e-06,
|
422 |
+
"loss": 0.6091,
|
423 |
+
"step": 580
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 1.3956238911886458,
|
427 |
+
"grad_norm": 0.5112713876137833,
|
428 |
+
"learning_rate": 5e-06,
|
429 |
+
"loss": 0.6049,
|
430 |
+
"step": 590
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 1.4192785334121822,
|
434 |
+
"grad_norm": 0.515536375353522,
|
435 |
+
"learning_rate": 5e-06,
|
436 |
+
"loss": 0.6079,
|
437 |
+
"step": 600
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 1.4429331756357184,
|
441 |
+
"grad_norm": 0.5943800369847494,
|
442 |
+
"learning_rate": 5e-06,
|
443 |
+
"loss": 0.602,
|
444 |
+
"step": 610
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 1.4665878178592548,
|
448 |
+
"grad_norm": 0.5570413849081146,
|
449 |
+
"learning_rate": 5e-06,
|
450 |
+
"loss": 0.6074,
|
451 |
+
"step": 620
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 1.4902424600827913,
|
455 |
+
"grad_norm": 0.5383074416990815,
|
456 |
+
"learning_rate": 5e-06,
|
457 |
+
"loss": 0.6055,
|
458 |
+
"step": 630
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 1.5138971023063275,
|
462 |
+
"grad_norm": 0.6221748842819845,
|
463 |
+
"learning_rate": 5e-06,
|
464 |
+
"loss": 0.6048,
|
465 |
+
"step": 640
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 1.537551744529864,
|
469 |
+
"grad_norm": 0.623130737085543,
|
470 |
+
"learning_rate": 5e-06,
|
471 |
+
"loss": 0.6124,
|
472 |
+
"step": 650
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 1.5612063867534003,
|
476 |
+
"grad_norm": 0.7728758992657894,
|
477 |
+
"learning_rate": 5e-06,
|
478 |
+
"loss": 0.6073,
|
479 |
+
"step": 660
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 1.5848610289769367,
|
483 |
+
"grad_norm": 0.5531126954202661,
|
484 |
+
"learning_rate": 5e-06,
|
485 |
+
"loss": 0.6023,
|
486 |
+
"step": 670
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 1.6085156712004731,
|
490 |
+
"grad_norm": 0.8207249388527519,
|
491 |
+
"learning_rate": 5e-06,
|
492 |
+
"loss": 0.6041,
|
493 |
+
"step": 680
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 1.6321703134240093,
|
497 |
+
"grad_norm": 0.7382668830128054,
|
498 |
+
"learning_rate": 5e-06,
|
499 |
+
"loss": 0.6027,
|
500 |
+
"step": 690
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 1.655824955647546,
|
504 |
+
"grad_norm": 0.8181634349883082,
|
505 |
+
"learning_rate": 5e-06,
|
506 |
+
"loss": 0.6077,
|
507 |
+
"step": 700
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 1.6794795978710821,
|
511 |
+
"grad_norm": 0.5715750112816181,
|
512 |
+
"learning_rate": 5e-06,
|
513 |
+
"loss": 0.603,
|
514 |
+
"step": 710
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 1.7031342400946186,
|
518 |
+
"grad_norm": 0.564060422032355,
|
519 |
+
"learning_rate": 5e-06,
|
520 |
+
"loss": 0.6137,
|
521 |
+
"step": 720
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 1.726788882318155,
|
525 |
+
"grad_norm": 0.5112934215435977,
|
526 |
+
"learning_rate": 5e-06,
|
527 |
+
"loss": 0.6041,
|
528 |
+
"step": 730
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 1.7504435245416912,
|
532 |
+
"grad_norm": 0.6498040890743698,
|
533 |
+
"learning_rate": 5e-06,
|
534 |
+
"loss": 0.6038,
|
535 |
+
"step": 740
|
536 |
+
},
|
537 |
+
{
|
538 |
+
"epoch": 1.7740981667652278,
|
539 |
+
"grad_norm": 0.6625174306160165,
|
540 |
+
"learning_rate": 5e-06,
|
541 |
+
"loss": 0.604,
|
542 |
+
"step": 750
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 1.797752808988764,
|
546 |
+
"grad_norm": 0.5200239654238437,
|
547 |
+
"learning_rate": 5e-06,
|
548 |
+
"loss": 0.604,
|
549 |
+
"step": 760
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 1.8214074512123004,
|
553 |
+
"grad_norm": 0.5056250667365105,
|
554 |
+
"learning_rate": 5e-06,
|
555 |
+
"loss": 0.601,
|
556 |
+
"step": 770
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 1.8450620934358368,
|
560 |
+
"grad_norm": 0.5465224841554837,
|
561 |
+
"learning_rate": 5e-06,
|
562 |
+
"loss": 0.6043,
|
563 |
+
"step": 780
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 1.868716735659373,
|
567 |
+
"grad_norm": 0.5173445168820222,
|
568 |
+
"learning_rate": 5e-06,
|
569 |
+
"loss": 0.6051,
|
570 |
+
"step": 790
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 1.8923713778829097,
|
574 |
+
"grad_norm": 0.5037163086029489,
|
575 |
+
"learning_rate": 5e-06,
|
576 |
+
"loss": 0.6071,
|
577 |
+
"step": 800
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"epoch": 1.9160260201064458,
|
581 |
+
"grad_norm": 0.5032092904194995,
|
582 |
+
"learning_rate": 5e-06,
|
583 |
+
"loss": 0.6097,
|
584 |
+
"step": 810
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 1.9396806623299823,
|
588 |
+
"grad_norm": 0.5153373413177225,
|
589 |
+
"learning_rate": 5e-06,
|
590 |
+
"loss": 0.6017,
|
591 |
+
"step": 820
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 1.9633353045535187,
|
595 |
+
"grad_norm": 0.48445434626456924,
|
596 |
+
"learning_rate": 5e-06,
|
597 |
+
"loss": 0.6097,
|
598 |
+
"step": 830
|
599 |
+
},
|
600 |
+
{
|
601 |
+
"epoch": 1.9869899467770549,
|
602 |
+
"grad_norm": 0.5493690840998718,
|
603 |
+
"learning_rate": 5e-06,
|
604 |
+
"loss": 0.5996,
|
605 |
+
"step": 840
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 1.9988172678888232,
|
609 |
+
"eval_loss": 0.6458428502082825,
|
610 |
+
"eval_runtime": 226.2611,
|
611 |
+
"eval_samples_per_second": 50.327,
|
612 |
+
"eval_steps_per_second": 0.393,
|
613 |
+
"step": 845
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 2.0106445890005915,
|
617 |
+
"grad_norm": 0.6225484532666892,
|
618 |
+
"learning_rate": 5e-06,
|
619 |
+
"loss": 0.5795,
|
620 |
+
"step": 850
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 2.0342992312241277,
|
624 |
+
"grad_norm": 0.5819857678964343,
|
625 |
+
"learning_rate": 5e-06,
|
626 |
+
"loss": 0.5553,
|
627 |
+
"step": 860
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 2.057953873447664,
|
631 |
+
"grad_norm": 0.7185360534865078,
|
632 |
+
"learning_rate": 5e-06,
|
633 |
+
"loss": 0.5506,
|
634 |
+
"step": 870
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 2.0816085156712005,
|
638 |
+
"grad_norm": 0.5134284842767335,
|
639 |
+
"learning_rate": 5e-06,
|
640 |
+
"loss": 0.5539,
|
641 |
+
"step": 880
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 2.1052631578947367,
|
645 |
+
"grad_norm": 0.5986326239884353,
|
646 |
+
"learning_rate": 5e-06,
|
647 |
+
"loss": 0.5609,
|
648 |
+
"step": 890
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 2.1289178001182734,
|
652 |
+
"grad_norm": 0.579714763513885,
|
653 |
+
"learning_rate": 5e-06,
|
654 |
+
"loss": 0.5546,
|
655 |
+
"step": 900
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 2.1525724423418096,
|
659 |
+
"grad_norm": 0.570292196409214,
|
660 |
+
"learning_rate": 5e-06,
|
661 |
+
"loss": 0.5586,
|
662 |
+
"step": 910
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 2.1762270845653457,
|
666 |
+
"grad_norm": 0.5811117001743673,
|
667 |
+
"learning_rate": 5e-06,
|
668 |
+
"loss": 0.5585,
|
669 |
+
"step": 920
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 2.1998817267888824,
|
673 |
+
"grad_norm": 0.554144816987719,
|
674 |
+
"learning_rate": 5e-06,
|
675 |
+
"loss": 0.5562,
|
676 |
+
"step": 930
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 2.2235363690124186,
|
680 |
+
"grad_norm": 0.6493826388527278,
|
681 |
+
"learning_rate": 5e-06,
|
682 |
+
"loss": 0.5565,
|
683 |
+
"step": 940
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 2.247191011235955,
|
687 |
+
"grad_norm": 0.5220557856218626,
|
688 |
+
"learning_rate": 5e-06,
|
689 |
+
"loss": 0.5694,
|
690 |
+
"step": 950
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 2.2708456534594914,
|
694 |
+
"grad_norm": 0.6378102281048501,
|
695 |
+
"learning_rate": 5e-06,
|
696 |
+
"loss": 0.5602,
|
697 |
+
"step": 960
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 2.2945002956830276,
|
701 |
+
"grad_norm": 0.5497371876386185,
|
702 |
+
"learning_rate": 5e-06,
|
703 |
+
"loss": 0.5628,
|
704 |
+
"step": 970
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 2.3181549379065642,
|
708 |
+
"grad_norm": 0.6521682175920844,
|
709 |
+
"learning_rate": 5e-06,
|
710 |
+
"loss": 0.5565,
|
711 |
+
"step": 980
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 2.3418095801301004,
|
715 |
+
"grad_norm": 0.5734936169662879,
|
716 |
+
"learning_rate": 5e-06,
|
717 |
+
"loss": 0.5674,
|
718 |
+
"step": 990
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 2.365464222353637,
|
722 |
+
"grad_norm": 0.5394258314592499,
|
723 |
+
"learning_rate": 5e-06,
|
724 |
+
"loss": 0.5569,
|
725 |
+
"step": 1000
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 2.3891188645771733,
|
729 |
+
"grad_norm": 0.5306593171364488,
|
730 |
+
"learning_rate": 5e-06,
|
731 |
+
"loss": 0.5502,
|
732 |
+
"step": 1010
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 2.4127735068007095,
|
736 |
+
"grad_norm": 0.5344199954837688,
|
737 |
+
"learning_rate": 5e-06,
|
738 |
+
"loss": 0.5549,
|
739 |
+
"step": 1020
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 2.436428149024246,
|
743 |
+
"grad_norm": 0.5892751227456119,
|
744 |
+
"learning_rate": 5e-06,
|
745 |
+
"loss": 0.5533,
|
746 |
+
"step": 1030
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 2.4600827912477823,
|
750 |
+
"grad_norm": 0.6529042003930223,
|
751 |
+
"learning_rate": 5e-06,
|
752 |
+
"loss": 0.5613,
|
753 |
+
"step": 1040
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 2.483737433471319,
|
757 |
+
"grad_norm": 0.5765438425321338,
|
758 |
+
"learning_rate": 5e-06,
|
759 |
+
"loss": 0.5646,
|
760 |
+
"step": 1050
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 2.507392075694855,
|
764 |
+
"grad_norm": 0.6764490044193554,
|
765 |
+
"learning_rate": 5e-06,
|
766 |
+
"loss": 0.567,
|
767 |
+
"step": 1060
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 2.5310467179183913,
|
771 |
+
"grad_norm": 0.5365218264481744,
|
772 |
+
"learning_rate": 5e-06,
|
773 |
+
"loss": 0.5532,
|
774 |
+
"step": 1070
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 2.554701360141928,
|
778 |
+
"grad_norm": 0.6033785399498255,
|
779 |
+
"learning_rate": 5e-06,
|
780 |
+
"loss": 0.5622,
|
781 |
+
"step": 1080
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 2.578356002365464,
|
785 |
+
"grad_norm": 0.8004909937255467,
|
786 |
+
"learning_rate": 5e-06,
|
787 |
+
"loss": 0.5661,
|
788 |
+
"step": 1090
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 2.6020106445890008,
|
792 |
+
"grad_norm": 0.5819582134735406,
|
793 |
+
"learning_rate": 5e-06,
|
794 |
+
"loss": 0.5616,
|
795 |
+
"step": 1100
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 2.625665286812537,
|
799 |
+
"grad_norm": 0.5537773395049099,
|
800 |
+
"learning_rate": 5e-06,
|
801 |
+
"loss": 0.5628,
|
802 |
+
"step": 1110
|
803 |
+
},
|
804 |
+
{
|
805 |
+
"epoch": 2.649319929036073,
|
806 |
+
"grad_norm": 0.5539615560141525,
|
807 |
+
"learning_rate": 5e-06,
|
808 |
+
"loss": 0.5648,
|
809 |
+
"step": 1120
|
810 |
+
},
|
811 |
+
{
|
812 |
+
"epoch": 2.67297457125961,
|
813 |
+
"grad_norm": 0.6206027218523953,
|
814 |
+
"learning_rate": 5e-06,
|
815 |
+
"loss": 0.5643,
|
816 |
+
"step": 1130
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 2.696629213483146,
|
820 |
+
"grad_norm": 0.5108322877934205,
|
821 |
+
"learning_rate": 5e-06,
|
822 |
+
"loss": 0.5586,
|
823 |
+
"step": 1140
|
824 |
+
},
|
825 |
+
{
|
826 |
+
"epoch": 2.7202838557066826,
|
827 |
+
"grad_norm": 0.48797735494965916,
|
828 |
+
"learning_rate": 5e-06,
|
829 |
+
"loss": 0.5563,
|
830 |
+
"step": 1150
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 2.743938497930219,
|
834 |
+
"grad_norm": 0.5823974142352172,
|
835 |
+
"learning_rate": 5e-06,
|
836 |
+
"loss": 0.5671,
|
837 |
+
"step": 1160
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 2.767593140153755,
|
841 |
+
"grad_norm": 0.8599218035136146,
|
842 |
+
"learning_rate": 5e-06,
|
843 |
+
"loss": 0.5723,
|
844 |
+
"step": 1170
|
845 |
+
},
|
846 |
+
{
|
847 |
+
"epoch": 2.7912477823772917,
|
848 |
+
"grad_norm": 0.6555716714163583,
|
849 |
+
"learning_rate": 5e-06,
|
850 |
+
"loss": 0.5633,
|
851 |
+
"step": 1180
|
852 |
+
},
|
853 |
+
{
|
854 |
+
"epoch": 2.814902424600828,
|
855 |
+
"grad_norm": 0.49879910164951613,
|
856 |
+
"learning_rate": 5e-06,
|
857 |
+
"loss": 0.5581,
|
858 |
+
"step": 1190
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 2.8385570668243645,
|
862 |
+
"grad_norm": 0.5241725506783274,
|
863 |
+
"learning_rate": 5e-06,
|
864 |
+
"loss": 0.5623,
|
865 |
+
"step": 1200
|
866 |
+
},
|
867 |
+
{
|
868 |
+
"epoch": 2.8622117090479007,
|
869 |
+
"grad_norm": 0.6173811070502804,
|
870 |
+
"learning_rate": 5e-06,
|
871 |
+
"loss": 0.569,
|
872 |
+
"step": 1210
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 2.885866351271437,
|
876 |
+
"grad_norm": 0.5397292738316359,
|
877 |
+
"learning_rate": 5e-06,
|
878 |
+
"loss": 0.5642,
|
879 |
+
"step": 1220
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 2.9095209934949735,
|
883 |
+
"grad_norm": 0.7053290870019903,
|
884 |
+
"learning_rate": 5e-06,
|
885 |
+
"loss": 0.5593,
|
886 |
+
"step": 1230
|
887 |
+
},
|
888 |
+
{
|
889 |
+
"epoch": 2.9331756357185097,
|
890 |
+
"grad_norm": 0.5500348460578961,
|
891 |
+
"learning_rate": 5e-06,
|
892 |
+
"loss": 0.5591,
|
893 |
+
"step": 1240
|
894 |
+
},
|
895 |
+
{
|
896 |
+
"epoch": 2.9568302779420463,
|
897 |
+
"grad_norm": 0.5833114667049699,
|
898 |
+
"learning_rate": 5e-06,
|
899 |
+
"loss": 0.5649,
|
900 |
+
"step": 1250
|
901 |
+
},
|
902 |
+
{
|
903 |
+
"epoch": 2.9804849201655825,
|
904 |
+
"grad_norm": 0.569413301750619,
|
905 |
+
"learning_rate": 5e-06,
|
906 |
+
"loss": 0.5577,
|
907 |
+
"step": 1260
|
908 |
+
},
|
909 |
+
{
|
910 |
+
"epoch": 2.9946777054997042,
|
911 |
+
"eval_loss": 0.648719847202301,
|
912 |
+
"eval_runtime": 225.8886,
|
913 |
+
"eval_samples_per_second": 50.41,
|
914 |
+
"eval_steps_per_second": 0.394,
|
915 |
+
"step": 1266
|
916 |
+
},
|
917 |
+
{
|
918 |
+
"epoch": 2.9946777054997042,
|
919 |
+
"step": 1266,
|
920 |
+
"total_flos": 2120178393415680.0,
|
921 |
+
"train_loss": 0.6180764295478568,
|
922 |
+
"train_runtime": 37891.5513,
|
923 |
+
"train_samples_per_second": 17.129,
|
924 |
+
"train_steps_per_second": 0.033
|
925 |
+
}
|
926 |
+
],
|
927 |
+
"logging_steps": 10,
|
928 |
+
"max_steps": 1266,
|
929 |
+
"num_input_tokens_seen": 0,
|
930 |
+
"num_train_epochs": 3,
|
931 |
+
"save_steps": 500,
|
932 |
+
"stateful_callbacks": {
|
933 |
+
"TrainerControl": {
|
934 |
+
"args": {
|
935 |
+
"should_epoch_stop": false,
|
936 |
+
"should_evaluate": false,
|
937 |
+
"should_log": false,
|
938 |
+
"should_save": true,
|
939 |
+
"should_training_stop": true
|
940 |
+
},
|
941 |
+
"attributes": {}
|
942 |
+
}
|
943 |
+
},
|
944 |
+
"total_flos": 2120178393415680.0,
|
945 |
+
"train_batch_size": 8,
|
946 |
+
"trial_name": null,
|
947 |
+
"trial_params": null
|
948 |
+
}
|
training_eval_loss.png
ADDED
training_loss.png
ADDED