sedrickkeh
commited on
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 +899 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
@@ -4,6 +4,7 @@ license: llama3.1
|
|
4 |
base_model: meta-llama/Llama-3.1-8B
|
5 |
tags:
|
6 |
- llama-factory
|
|
|
7 |
- generated_from_trainer
|
8 |
model-index:
|
9 |
- name: oh_v1_w_v3_camel_biology_gpt-4o-mini
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# oh_v1_w_v3_camel_biology_gpt-4o-mini
|
17 |
|
18 |
-
This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on
|
19 |
It achieves the following results on the evaluation set:
|
20 |
- Loss: 0.5550
|
21 |
|
|
|
4 |
base_model: meta-llama/Llama-3.1-8B
|
5 |
tags:
|
6 |
- llama-factory
|
7 |
+
- full
|
8 |
- generated_from_trainer
|
9 |
model-index:
|
10 |
- name: oh_v1_w_v3_camel_biology_gpt-4o-mini
|
|
|
16 |
|
17 |
# oh_v1_w_v3_camel_biology_gpt-4o-mini
|
18 |
|
19 |
+
This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on the mlfoundations-dev/oh_v1_w_v3_camel_biology_gpt-4o-mini dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
- Loss: 0.5550
|
22 |
|
all_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.9962358845671266,
|
3 |
+
"eval_loss": 0.555037796497345,
|
4 |
+
"eval_runtime": 213.0252,
|
5 |
+
"eval_samples_per_second": 50.388,
|
6 |
+
"eval_steps_per_second": 0.394,
|
7 |
+
"total_flos": 1999575711744000.0,
|
8 |
+
"train_loss": 0.5572832309620664,
|
9 |
+
"train_runtime": 35786.5658,
|
10 |
+
"train_samples_per_second": 17.096,
|
11 |
+
"train_steps_per_second": 0.033
|
12 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.9962358845671266,
|
3 |
+
"eval_loss": 0.555037796497345,
|
4 |
+
"eval_runtime": 213.0252,
|
5 |
+
"eval_samples_per_second": 50.388,
|
6 |
+
"eval_steps_per_second": 0.394
|
7 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.9962358845671266,
|
3 |
+
"total_flos": 1999575711744000.0,
|
4 |
+
"train_loss": 0.5572832309620664,
|
5 |
+
"train_runtime": 35786.5658,
|
6 |
+
"train_samples_per_second": 17.096,
|
7 |
+
"train_steps_per_second": 0.033
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,899 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.9962358845671266,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1194,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.025094102885821833,
|
13 |
+
"grad_norm": 11.718188698364322,
|
14 |
+
"learning_rate": 5e-06,
|
15 |
+
"loss": 0.9141,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.050188205771643665,
|
20 |
+
"grad_norm": 2.128194193417522,
|
21 |
+
"learning_rate": 5e-06,
|
22 |
+
"loss": 0.7836,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.07528230865746549,
|
27 |
+
"grad_norm": 2.3757769329973657,
|
28 |
+
"learning_rate": 5e-06,
|
29 |
+
"loss": 0.7498,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.10037641154328733,
|
34 |
+
"grad_norm": 1.103206879933866,
|
35 |
+
"learning_rate": 5e-06,
|
36 |
+
"loss": 0.7188,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.12547051442910917,
|
41 |
+
"grad_norm": 0.9274722897954563,
|
42 |
+
"learning_rate": 5e-06,
|
43 |
+
"loss": 0.7002,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.15056461731493098,
|
48 |
+
"grad_norm": 0.84713375375135,
|
49 |
+
"learning_rate": 5e-06,
|
50 |
+
"loss": 0.6765,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.17565872020075282,
|
55 |
+
"grad_norm": 0.7850634011267035,
|
56 |
+
"learning_rate": 5e-06,
|
57 |
+
"loss": 0.6679,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.20075282308657466,
|
62 |
+
"grad_norm": 0.6763495874297807,
|
63 |
+
"learning_rate": 5e-06,
|
64 |
+
"loss": 0.6554,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.2258469259723965,
|
69 |
+
"grad_norm": 0.6460889441423061,
|
70 |
+
"learning_rate": 5e-06,
|
71 |
+
"loss": 0.6537,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.25094102885821834,
|
76 |
+
"grad_norm": 0.6381839585959109,
|
77 |
+
"learning_rate": 5e-06,
|
78 |
+
"loss": 0.6469,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.27603513174404015,
|
83 |
+
"grad_norm": 0.5934854411636431,
|
84 |
+
"learning_rate": 5e-06,
|
85 |
+
"loss": 0.6408,
|
86 |
+
"step": 110
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.30112923462986196,
|
90 |
+
"grad_norm": 0.5908335131781053,
|
91 |
+
"learning_rate": 5e-06,
|
92 |
+
"loss": 0.6315,
|
93 |
+
"step": 120
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.32622333751568383,
|
97 |
+
"grad_norm": 0.6207583357857969,
|
98 |
+
"learning_rate": 5e-06,
|
99 |
+
"loss": 0.6295,
|
100 |
+
"step": 130
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.35131744040150564,
|
104 |
+
"grad_norm": 0.5777218463460926,
|
105 |
+
"learning_rate": 5e-06,
|
106 |
+
"loss": 0.6353,
|
107 |
+
"step": 140
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.37641154328732745,
|
111 |
+
"grad_norm": 0.8031543297119933,
|
112 |
+
"learning_rate": 5e-06,
|
113 |
+
"loss": 0.6257,
|
114 |
+
"step": 150
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.4015056461731493,
|
118 |
+
"grad_norm": 0.6565972172028122,
|
119 |
+
"learning_rate": 5e-06,
|
120 |
+
"loss": 0.6223,
|
121 |
+
"step": 160
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.42659974905897113,
|
125 |
+
"grad_norm": 0.5758668737369184,
|
126 |
+
"learning_rate": 5e-06,
|
127 |
+
"loss": 0.6238,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.451693851944793,
|
132 |
+
"grad_norm": 0.5079092787071162,
|
133 |
+
"learning_rate": 5e-06,
|
134 |
+
"loss": 0.6143,
|
135 |
+
"step": 180
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.4767879548306148,
|
139 |
+
"grad_norm": 0.6379157115232267,
|
140 |
+
"learning_rate": 5e-06,
|
141 |
+
"loss": 0.6199,
|
142 |
+
"step": 190
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.5018820577164367,
|
146 |
+
"grad_norm": 0.5743755502713278,
|
147 |
+
"learning_rate": 5e-06,
|
148 |
+
"loss": 0.6129,
|
149 |
+
"step": 200
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.5269761606022585,
|
153 |
+
"grad_norm": 0.7914784193340709,
|
154 |
+
"learning_rate": 5e-06,
|
155 |
+
"loss": 0.609,
|
156 |
+
"step": 210
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.5520702634880803,
|
160 |
+
"grad_norm": 0.6052863906299388,
|
161 |
+
"learning_rate": 5e-06,
|
162 |
+
"loss": 0.6191,
|
163 |
+
"step": 220
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.5771643663739021,
|
167 |
+
"grad_norm": 0.6079363974587813,
|
168 |
+
"learning_rate": 5e-06,
|
169 |
+
"loss": 0.6036,
|
170 |
+
"step": 230
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.6022584692597239,
|
174 |
+
"grad_norm": 0.6317013898545292,
|
175 |
+
"learning_rate": 5e-06,
|
176 |
+
"loss": 0.6101,
|
177 |
+
"step": 240
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.6273525721455459,
|
181 |
+
"grad_norm": 0.6772767650378945,
|
182 |
+
"learning_rate": 5e-06,
|
183 |
+
"loss": 0.6066,
|
184 |
+
"step": 250
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.6524466750313677,
|
188 |
+
"grad_norm": 0.7659397239810531,
|
189 |
+
"learning_rate": 5e-06,
|
190 |
+
"loss": 0.6085,
|
191 |
+
"step": 260
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.6775407779171895,
|
195 |
+
"grad_norm": 0.8301922378020979,
|
196 |
+
"learning_rate": 5e-06,
|
197 |
+
"loss": 0.6054,
|
198 |
+
"step": 270
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.7026348808030113,
|
202 |
+
"grad_norm": 0.4548488940244719,
|
203 |
+
"learning_rate": 5e-06,
|
204 |
+
"loss": 0.6039,
|
205 |
+
"step": 280
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.7277289836888331,
|
209 |
+
"grad_norm": 0.6991563441452833,
|
210 |
+
"learning_rate": 5e-06,
|
211 |
+
"loss": 0.6041,
|
212 |
+
"step": 290
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.7528230865746549,
|
216 |
+
"grad_norm": 0.7252866874449959,
|
217 |
+
"learning_rate": 5e-06,
|
218 |
+
"loss": 0.5982,
|
219 |
+
"step": 300
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.7779171894604768,
|
223 |
+
"grad_norm": 0.5621384726961683,
|
224 |
+
"learning_rate": 5e-06,
|
225 |
+
"loss": 0.5984,
|
226 |
+
"step": 310
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.8030112923462986,
|
230 |
+
"grad_norm": 0.5544205898879206,
|
231 |
+
"learning_rate": 5e-06,
|
232 |
+
"loss": 0.5938,
|
233 |
+
"step": 320
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.8281053952321205,
|
237 |
+
"grad_norm": 0.6591982327209397,
|
238 |
+
"learning_rate": 5e-06,
|
239 |
+
"loss": 0.5949,
|
240 |
+
"step": 330
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.8531994981179423,
|
244 |
+
"grad_norm": 0.4966951651690375,
|
245 |
+
"learning_rate": 5e-06,
|
246 |
+
"loss": 0.5939,
|
247 |
+
"step": 340
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.8782936010037641,
|
251 |
+
"grad_norm": 0.7936946361545921,
|
252 |
+
"learning_rate": 5e-06,
|
253 |
+
"loss": 0.5952,
|
254 |
+
"step": 350
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.903387703889586,
|
258 |
+
"grad_norm": 0.6049775996861211,
|
259 |
+
"learning_rate": 5e-06,
|
260 |
+
"loss": 0.5828,
|
261 |
+
"step": 360
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.9284818067754078,
|
265 |
+
"grad_norm": 0.5343638273778424,
|
266 |
+
"learning_rate": 5e-06,
|
267 |
+
"loss": 0.5851,
|
268 |
+
"step": 370
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.9535759096612296,
|
272 |
+
"grad_norm": 0.5723040103769105,
|
273 |
+
"learning_rate": 5e-06,
|
274 |
+
"loss": 0.5912,
|
275 |
+
"step": 380
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.9786700125470514,
|
279 |
+
"grad_norm": 0.5959442881234533,
|
280 |
+
"learning_rate": 5e-06,
|
281 |
+
"loss": 0.5915,
|
282 |
+
"step": 390
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.998745294855709,
|
286 |
+
"eval_loss": 0.5871068239212036,
|
287 |
+
"eval_runtime": 212.6533,
|
288 |
+
"eval_samples_per_second": 50.477,
|
289 |
+
"eval_steps_per_second": 0.395,
|
290 |
+
"step": 398
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 1.0037641154328734,
|
294 |
+
"grad_norm": 0.5888812035860913,
|
295 |
+
"learning_rate": 5e-06,
|
296 |
+
"loss": 0.5826,
|
297 |
+
"step": 400
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 1.0288582183186952,
|
301 |
+
"grad_norm": 0.496571742956618,
|
302 |
+
"learning_rate": 5e-06,
|
303 |
+
"loss": 0.5559,
|
304 |
+
"step": 410
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 1.053952321204517,
|
308 |
+
"grad_norm": 0.6292730066506935,
|
309 |
+
"learning_rate": 5e-06,
|
310 |
+
"loss": 0.5513,
|
311 |
+
"step": 420
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 1.0790464240903388,
|
315 |
+
"grad_norm": 0.588641857548959,
|
316 |
+
"learning_rate": 5e-06,
|
317 |
+
"loss": 0.5507,
|
318 |
+
"step": 430
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 1.1041405269761606,
|
322 |
+
"grad_norm": 0.6769239280680559,
|
323 |
+
"learning_rate": 5e-06,
|
324 |
+
"loss": 0.5503,
|
325 |
+
"step": 440
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 1.1292346298619824,
|
329 |
+
"grad_norm": 0.5417691042097619,
|
330 |
+
"learning_rate": 5e-06,
|
331 |
+
"loss": 0.548,
|
332 |
+
"step": 450
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 1.1543287327478042,
|
336 |
+
"grad_norm": 0.5991902330546697,
|
337 |
+
"learning_rate": 5e-06,
|
338 |
+
"loss": 0.5384,
|
339 |
+
"step": 460
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 1.179422835633626,
|
343 |
+
"grad_norm": 0.5820599790063293,
|
344 |
+
"learning_rate": 5e-06,
|
345 |
+
"loss": 0.5487,
|
346 |
+
"step": 470
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 1.2045169385194479,
|
350 |
+
"grad_norm": 0.5519292876234776,
|
351 |
+
"learning_rate": 5e-06,
|
352 |
+
"loss": 0.5427,
|
353 |
+
"step": 480
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 1.2296110414052697,
|
357 |
+
"grad_norm": 0.49516603784025776,
|
358 |
+
"learning_rate": 5e-06,
|
359 |
+
"loss": 0.546,
|
360 |
+
"step": 490
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 1.2547051442910915,
|
364 |
+
"grad_norm": 0.5743423113593866,
|
365 |
+
"learning_rate": 5e-06,
|
366 |
+
"loss": 0.5393,
|
367 |
+
"step": 500
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 1.2797992471769133,
|
371 |
+
"grad_norm": 0.5535831554138544,
|
372 |
+
"learning_rate": 5e-06,
|
373 |
+
"loss": 0.547,
|
374 |
+
"step": 510
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 1.3048933500627353,
|
378 |
+
"grad_norm": 0.5141692394527988,
|
379 |
+
"learning_rate": 5e-06,
|
380 |
+
"loss": 0.5411,
|
381 |
+
"step": 520
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 1.3299874529485571,
|
385 |
+
"grad_norm": 0.4854378839815677,
|
386 |
+
"learning_rate": 5e-06,
|
387 |
+
"loss": 0.5442,
|
388 |
+
"step": 530
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 1.355081555834379,
|
392 |
+
"grad_norm": 0.46518640648830495,
|
393 |
+
"learning_rate": 5e-06,
|
394 |
+
"loss": 0.5427,
|
395 |
+
"step": 540
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 1.3801756587202008,
|
399 |
+
"grad_norm": 0.534031920116045,
|
400 |
+
"learning_rate": 5e-06,
|
401 |
+
"loss": 0.5417,
|
402 |
+
"step": 550
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 1.4052697616060226,
|
406 |
+
"grad_norm": 0.5911980981423581,
|
407 |
+
"learning_rate": 5e-06,
|
408 |
+
"loss": 0.5435,
|
409 |
+
"step": 560
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 1.4303638644918444,
|
413 |
+
"grad_norm": 0.5763366884781533,
|
414 |
+
"learning_rate": 5e-06,
|
415 |
+
"loss": 0.5435,
|
416 |
+
"step": 570
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 1.4554579673776662,
|
420 |
+
"grad_norm": 0.6044164192343925,
|
421 |
+
"learning_rate": 5e-06,
|
422 |
+
"loss": 0.5458,
|
423 |
+
"step": 580
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 1.480552070263488,
|
427 |
+
"grad_norm": 0.5136929530377343,
|
428 |
+
"learning_rate": 5e-06,
|
429 |
+
"loss": 0.5433,
|
430 |
+
"step": 590
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 1.50564617314931,
|
434 |
+
"grad_norm": 0.6480890499633274,
|
435 |
+
"learning_rate": 5e-06,
|
436 |
+
"loss": 0.5412,
|
437 |
+
"step": 600
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 1.5307402760351319,
|
441 |
+
"grad_norm": 0.5778909116986595,
|
442 |
+
"learning_rate": 5e-06,
|
443 |
+
"loss": 0.5366,
|
444 |
+
"step": 610
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 1.5558343789209537,
|
448 |
+
"grad_norm": 0.554397297340124,
|
449 |
+
"learning_rate": 5e-06,
|
450 |
+
"loss": 0.5424,
|
451 |
+
"step": 620
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 1.5809284818067755,
|
455 |
+
"grad_norm": 0.512796007100603,
|
456 |
+
"learning_rate": 5e-06,
|
457 |
+
"loss": 0.5408,
|
458 |
+
"step": 630
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 1.6060225846925973,
|
462 |
+
"grad_norm": 0.4758665935260214,
|
463 |
+
"learning_rate": 5e-06,
|
464 |
+
"loss": 0.5418,
|
465 |
+
"step": 640
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 1.631116687578419,
|
469 |
+
"grad_norm": 0.4968644389707275,
|
470 |
+
"learning_rate": 5e-06,
|
471 |
+
"loss": 0.535,
|
472 |
+
"step": 650
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 1.656210790464241,
|
476 |
+
"grad_norm": 0.5920011846841533,
|
477 |
+
"learning_rate": 5e-06,
|
478 |
+
"loss": 0.54,
|
479 |
+
"step": 660
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 1.6813048933500627,
|
483 |
+
"grad_norm": 0.5905169032972927,
|
484 |
+
"learning_rate": 5e-06,
|
485 |
+
"loss": 0.5381,
|
486 |
+
"step": 670
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 1.7063989962358845,
|
490 |
+
"grad_norm": 0.6296689735308911,
|
491 |
+
"learning_rate": 5e-06,
|
492 |
+
"loss": 0.5358,
|
493 |
+
"step": 680
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 1.7314930991217063,
|
497 |
+
"grad_norm": 0.47536620723191336,
|
498 |
+
"learning_rate": 5e-06,
|
499 |
+
"loss": 0.5379,
|
500 |
+
"step": 690
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 1.7565872020075282,
|
504 |
+
"grad_norm": 0.5683042454275448,
|
505 |
+
"learning_rate": 5e-06,
|
506 |
+
"loss": 0.5353,
|
507 |
+
"step": 700
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 1.78168130489335,
|
511 |
+
"grad_norm": 0.5865132456497922,
|
512 |
+
"learning_rate": 5e-06,
|
513 |
+
"loss": 0.5341,
|
514 |
+
"step": 710
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 1.8067754077791718,
|
518 |
+
"grad_norm": 0.5863809886365764,
|
519 |
+
"learning_rate": 5e-06,
|
520 |
+
"loss": 0.5385,
|
521 |
+
"step": 720
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 1.8318695106649936,
|
525 |
+
"grad_norm": 0.47137949702370147,
|
526 |
+
"learning_rate": 5e-06,
|
527 |
+
"loss": 0.5349,
|
528 |
+
"step": 730
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 1.8569636135508154,
|
532 |
+
"grad_norm": 0.5139487832974206,
|
533 |
+
"learning_rate": 5e-06,
|
534 |
+
"loss": 0.5351,
|
535 |
+
"step": 740
|
536 |
+
},
|
537 |
+
{
|
538 |
+
"epoch": 1.8820577164366374,
|
539 |
+
"grad_norm": 0.5728562358927324,
|
540 |
+
"learning_rate": 5e-06,
|
541 |
+
"loss": 0.5387,
|
542 |
+
"step": 750
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 1.9071518193224593,
|
546 |
+
"grad_norm": 0.6768594215912966,
|
547 |
+
"learning_rate": 5e-06,
|
548 |
+
"loss": 0.5364,
|
549 |
+
"step": 760
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 1.932245922208281,
|
553 |
+
"grad_norm": 0.5485345915469325,
|
554 |
+
"learning_rate": 5e-06,
|
555 |
+
"loss": 0.5394,
|
556 |
+
"step": 770
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 1.9573400250941029,
|
560 |
+
"grad_norm": 0.5148704568756698,
|
561 |
+
"learning_rate": 5e-06,
|
562 |
+
"loss": 0.5358,
|
563 |
+
"step": 780
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 1.9824341279799247,
|
567 |
+
"grad_norm": 0.48466535956929385,
|
568 |
+
"learning_rate": 5e-06,
|
569 |
+
"loss": 0.5304,
|
570 |
+
"step": 790
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 2.0,
|
574 |
+
"eval_loss": 0.5621475577354431,
|
575 |
+
"eval_runtime": 213.3338,
|
576 |
+
"eval_samples_per_second": 50.316,
|
577 |
+
"eval_steps_per_second": 0.394,
|
578 |
+
"step": 797
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 2.0075282308657467,
|
582 |
+
"grad_norm": 0.6573006701729232,
|
583 |
+
"learning_rate": 5e-06,
|
584 |
+
"loss": 0.5167,
|
585 |
+
"step": 800
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 2.0326223337515685,
|
589 |
+
"grad_norm": 0.7871500030029548,
|
590 |
+
"learning_rate": 5e-06,
|
591 |
+
"loss": 0.4942,
|
592 |
+
"step": 810
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 2.0577164366373903,
|
596 |
+
"grad_norm": 0.5640563491273413,
|
597 |
+
"learning_rate": 5e-06,
|
598 |
+
"loss": 0.4956,
|
599 |
+
"step": 820
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 2.082810539523212,
|
603 |
+
"grad_norm": 0.7511306820222987,
|
604 |
+
"learning_rate": 5e-06,
|
605 |
+
"loss": 0.4938,
|
606 |
+
"step": 830
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 2.107904642409034,
|
610 |
+
"grad_norm": 0.5817278040608698,
|
611 |
+
"learning_rate": 5e-06,
|
612 |
+
"loss": 0.4925,
|
613 |
+
"step": 840
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 2.132998745294856,
|
617 |
+
"grad_norm": 0.5443042434696377,
|
618 |
+
"learning_rate": 5e-06,
|
619 |
+
"loss": 0.4924,
|
620 |
+
"step": 850
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 2.1580928481806776,
|
624 |
+
"grad_norm": 0.5307201281775036,
|
625 |
+
"learning_rate": 5e-06,
|
626 |
+
"loss": 0.5,
|
627 |
+
"step": 860
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 2.1831869510664994,
|
631 |
+
"grad_norm": 0.5134207088872962,
|
632 |
+
"learning_rate": 5e-06,
|
633 |
+
"loss": 0.4948,
|
634 |
+
"step": 870
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 2.208281053952321,
|
638 |
+
"grad_norm": 0.6926705508270693,
|
639 |
+
"learning_rate": 5e-06,
|
640 |
+
"loss": 0.497,
|
641 |
+
"step": 880
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 2.233375156838143,
|
645 |
+
"grad_norm": 0.6946700857047731,
|
646 |
+
"learning_rate": 5e-06,
|
647 |
+
"loss": 0.4922,
|
648 |
+
"step": 890
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 2.258469259723965,
|
652 |
+
"grad_norm": 0.5473927966647341,
|
653 |
+
"learning_rate": 5e-06,
|
654 |
+
"loss": 0.4992,
|
655 |
+
"step": 900
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 2.2835633626097867,
|
659 |
+
"grad_norm": 0.6500276609885082,
|
660 |
+
"learning_rate": 5e-06,
|
661 |
+
"loss": 0.4932,
|
662 |
+
"step": 910
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 2.3086574654956085,
|
666 |
+
"grad_norm": 0.5514076764002837,
|
667 |
+
"learning_rate": 5e-06,
|
668 |
+
"loss": 0.4915,
|
669 |
+
"step": 920
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 2.3337515683814303,
|
673 |
+
"grad_norm": 0.49943208945627254,
|
674 |
+
"learning_rate": 5e-06,
|
675 |
+
"loss": 0.4999,
|
676 |
+
"step": 930
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 2.358845671267252,
|
680 |
+
"grad_norm": 0.6060583960970398,
|
681 |
+
"learning_rate": 5e-06,
|
682 |
+
"loss": 0.4953,
|
683 |
+
"step": 940
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 2.383939774153074,
|
687 |
+
"grad_norm": 0.5320264242785274,
|
688 |
+
"learning_rate": 5e-06,
|
689 |
+
"loss": 0.4964,
|
690 |
+
"step": 950
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 2.4090338770388957,
|
694 |
+
"grad_norm": 0.5858837169303328,
|
695 |
+
"learning_rate": 5e-06,
|
696 |
+
"loss": 0.5006,
|
697 |
+
"step": 960
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 2.4341279799247175,
|
701 |
+
"grad_norm": 0.5441932891457427,
|
702 |
+
"learning_rate": 5e-06,
|
703 |
+
"loss": 0.4927,
|
704 |
+
"step": 970
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 2.4592220828105393,
|
708 |
+
"grad_norm": 0.49825625085166125,
|
709 |
+
"learning_rate": 5e-06,
|
710 |
+
"loss": 0.4986,
|
711 |
+
"step": 980
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 2.484316185696361,
|
715 |
+
"grad_norm": 0.5693348465052496,
|
716 |
+
"learning_rate": 5e-06,
|
717 |
+
"loss": 0.4923,
|
718 |
+
"step": 990
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 2.509410288582183,
|
722 |
+
"grad_norm": 0.5198895218070472,
|
723 |
+
"learning_rate": 5e-06,
|
724 |
+
"loss": 0.4961,
|
725 |
+
"step": 1000
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 2.5345043914680048,
|
729 |
+
"grad_norm": 0.5822359089459672,
|
730 |
+
"learning_rate": 5e-06,
|
731 |
+
"loss": 0.4948,
|
732 |
+
"step": 1010
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 2.5595984943538266,
|
736 |
+
"grad_norm": 0.7250677792140846,
|
737 |
+
"learning_rate": 5e-06,
|
738 |
+
"loss": 0.4988,
|
739 |
+
"step": 1020
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 2.584692597239649,
|
743 |
+
"grad_norm": 0.49974126038635164,
|
744 |
+
"learning_rate": 5e-06,
|
745 |
+
"loss": 0.4915,
|
746 |
+
"step": 1030
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 2.6097867001254706,
|
750 |
+
"grad_norm": 0.4964480117175315,
|
751 |
+
"learning_rate": 5e-06,
|
752 |
+
"loss": 0.4902,
|
753 |
+
"step": 1040
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 2.6348808030112925,
|
757 |
+
"grad_norm": 0.5288705472818386,
|
758 |
+
"learning_rate": 5e-06,
|
759 |
+
"loss": 0.497,
|
760 |
+
"step": 1050
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 2.6599749058971143,
|
764 |
+
"grad_norm": 0.4795064924818655,
|
765 |
+
"learning_rate": 5e-06,
|
766 |
+
"loss": 0.5,
|
767 |
+
"step": 1060
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 2.685069008782936,
|
771 |
+
"grad_norm": 0.5639285671354385,
|
772 |
+
"learning_rate": 5e-06,
|
773 |
+
"loss": 0.496,
|
774 |
+
"step": 1070
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 2.710163111668758,
|
778 |
+
"grad_norm": 0.4890610843848083,
|
779 |
+
"learning_rate": 5e-06,
|
780 |
+
"loss": 0.497,
|
781 |
+
"step": 1080
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 2.7352572145545797,
|
785 |
+
"grad_norm": 0.5718819316899499,
|
786 |
+
"learning_rate": 5e-06,
|
787 |
+
"loss": 0.4948,
|
788 |
+
"step": 1090
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 2.7603513174404015,
|
792 |
+
"grad_norm": 0.564322354041535,
|
793 |
+
"learning_rate": 5e-06,
|
794 |
+
"loss": 0.492,
|
795 |
+
"step": 1100
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 2.7854454203262233,
|
799 |
+
"grad_norm": 0.5775080175263282,
|
800 |
+
"learning_rate": 5e-06,
|
801 |
+
"loss": 0.4957,
|
802 |
+
"step": 1110
|
803 |
+
},
|
804 |
+
{
|
805 |
+
"epoch": 2.810539523212045,
|
806 |
+
"grad_norm": 0.553905770960013,
|
807 |
+
"learning_rate": 5e-06,
|
808 |
+
"loss": 0.4993,
|
809 |
+
"step": 1120
|
810 |
+
},
|
811 |
+
{
|
812 |
+
"epoch": 2.835633626097867,
|
813 |
+
"grad_norm": 0.5725357035362282,
|
814 |
+
"learning_rate": 5e-06,
|
815 |
+
"loss": 0.4972,
|
816 |
+
"step": 1130
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 2.8607277289836888,
|
820 |
+
"grad_norm": 0.5476057683573488,
|
821 |
+
"learning_rate": 5e-06,
|
822 |
+
"loss": 0.4928,
|
823 |
+
"step": 1140
|
824 |
+
},
|
825 |
+
{
|
826 |
+
"epoch": 2.8858218318695106,
|
827 |
+
"grad_norm": 0.49125993261554296,
|
828 |
+
"learning_rate": 5e-06,
|
829 |
+
"loss": 0.4908,
|
830 |
+
"step": 1150
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 2.9109159347553324,
|
834 |
+
"grad_norm": 0.530302463940866,
|
835 |
+
"learning_rate": 5e-06,
|
836 |
+
"loss": 0.4962,
|
837 |
+
"step": 1160
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 2.936010037641154,
|
841 |
+
"grad_norm": 0.47444202016080034,
|
842 |
+
"learning_rate": 5e-06,
|
843 |
+
"loss": 0.498,
|
844 |
+
"step": 1170
|
845 |
+
},
|
846 |
+
{
|
847 |
+
"epoch": 2.961104140526976,
|
848 |
+
"grad_norm": 0.49422829602754365,
|
849 |
+
"learning_rate": 5e-06,
|
850 |
+
"loss": 0.4885,
|
851 |
+
"step": 1180
|
852 |
+
},
|
853 |
+
{
|
854 |
+
"epoch": 2.9861982434127983,
|
855 |
+
"grad_norm": 0.47369939752959883,
|
856 |
+
"learning_rate": 5e-06,
|
857 |
+
"loss": 0.4907,
|
858 |
+
"step": 1190
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 2.9962358845671266,
|
862 |
+
"eval_loss": 0.555037796497345,
|
863 |
+
"eval_runtime": 214.1596,
|
864 |
+
"eval_samples_per_second": 50.121,
|
865 |
+
"eval_steps_per_second": 0.392,
|
866 |
+
"step": 1194
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 2.9962358845671266,
|
870 |
+
"step": 1194,
|
871 |
+
"total_flos": 1999575711744000.0,
|
872 |
+
"train_loss": 0.5572832309620664,
|
873 |
+
"train_runtime": 35786.5658,
|
874 |
+
"train_samples_per_second": 17.096,
|
875 |
+
"train_steps_per_second": 0.033
|
876 |
+
}
|
877 |
+
],
|
878 |
+
"logging_steps": 10,
|
879 |
+
"max_steps": 1194,
|
880 |
+
"num_input_tokens_seen": 0,
|
881 |
+
"num_train_epochs": 3,
|
882 |
+
"save_steps": 500,
|
883 |
+
"stateful_callbacks": {
|
884 |
+
"TrainerControl": {
|
885 |
+
"args": {
|
886 |
+
"should_epoch_stop": false,
|
887 |
+
"should_evaluate": false,
|
888 |
+
"should_log": false,
|
889 |
+
"should_save": true,
|
890 |
+
"should_training_stop": true
|
891 |
+
},
|
892 |
+
"attributes": {}
|
893 |
+
}
|
894 |
+
},
|
895 |
+
"total_flos": 1999575711744000.0,
|
896 |
+
"train_batch_size": 8,
|
897 |
+
"trial_name": null,
|
898 |
+
"trial_params": null
|
899 |
+
}
|
training_eval_loss.png
ADDED
training_loss.png
ADDED